agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms 261+ messages / 2 participants [nested] [flat]
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms @ 2023-01-17 04:38 Andres Freund <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Andres Freund @ 2023-01-17 04:38 UTC (permalink / raw) Until now we used struct timespec on all platforms but windows. Using struct timespe causes a fair bit of memory (struct timeval is 16 bytes) and runtime overhead (much more complicated additions). Instead we can convert the time to nanoseconds in INSTR_TIME_SET_CURRENT(), making the remaining operations cheaper. Representing time as int64 nanoseconds provides sufficient range, ~292 years relative to a starting point (depending on clock source, relative to the unix epoch or the system's boot time). That'd not be sufficient for calendar time stored on disk, but is plenty for runtime interval time measurement. On windows instr_time already is represented as cycles. It might make sense to represent time as cycles on other platforms as well, as using cycle acquisition instructions like rdtsc directly can reduce the overhead of time acquisition substantially. This could be done in a fairly localized manner as the code stands after this commit. Because the windows and non-windows paths are now more similar, use a common set of macros. To make that possible, most of the use of LARGE_INTEGER had to be removed, which looks nicer anyway. To avoid users of the API relying on the integer representation, we wrap the 64bit integer inside struct struct instr_time. Author: Andres Freund <[email protected]> Author: Lukas Fittl <[email protected]> Author: David Geier <[email protected]> Reviewed-by: Tom Lane <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/include/portability/instr_time.h | 162 ++++++++++++++------------- 1 file changed, 86 insertions(+), 76 deletions(-) diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h index 9ea1a68bd94..c0ed491395d 100644 --- a/src/include/portability/instr_time.h +++ b/src/include/portability/instr_time.h @@ -34,6 +34,8 @@ * * INSTR_TIME_GET_MICROSEC(t) convert t to uint64 (in microseconds) * + * INSTR_TIME_GET_NANOSEC(t) convert t to uint64 (in nanoseconds) + * * Note that INSTR_TIME_SUBTRACT and INSTR_TIME_ACCUM_DIFF convert * absolute times to intervals. The INSTR_TIME_GET_xxx operations are * only useful on intervals. @@ -54,8 +56,32 @@ #ifndef INSTR_TIME_H #define INSTR_TIME_H + +/* + * We store interval times as an int64 integer on all platforms, as int64 is + * cheap to add/subtract, the most common operation for instr_time. The + * acquisition of time and converting to specific units of time is platform + * specific. + * + * To avoid users of the API relying on the integer representation, we wrap + * the 64bit integer in a struct. + */ +typedef struct instr_time +{ + int64 ticks; /* in platforms specific unit */ +} instr_time; + + +/* helpers macros used in platform specific code below */ + +#define NS_PER_S INT64CONST(1000000000) +#define NS_PER_MS INT64CONST(1000000) +#define NS_PER_US INT64CONST(1000) + + #ifndef WIN32 + /* Use clock_gettime() */ #include <time.h> @@ -80,93 +106,43 @@ #define PG_INSTR_CLOCK CLOCK_REALTIME #endif -typedef struct timespec instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_clock_gettime_ns(void) +{ + instr_time now; + struct timespec tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).tv_nsec == 0 && (t).tv_sec == 0) + clock_gettime(PG_INSTR_CLOCK, &tmp); + now.ticks = tmp.tv_sec * NS_PER_S + tmp.tv_nsec; -#define INSTR_TIME_SET_ZERO(t) ((t).tv_sec = 0, (t).tv_nsec = 0) + return now; +} -#define INSTR_TIME_SET_CURRENT(t) ((void) clock_gettime(PG_INSTR_CLOCK, &(t))) +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_clock_gettime_ns()) -#define INSTR_TIME_ADD(x,y) \ - do { \ - (x).tv_sec += (y).tv_sec; \ - (x).tv_nsec += (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (t).ticks) -#define INSTR_TIME_SUBTRACT(x,y) \ - do { \ - (x).tv_sec -= (y).tv_sec; \ - (x).tv_nsec -= (y).tv_nsec; \ - /* Normalize */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - } while (0) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - do { \ - (x).tv_sec += (y).tv_sec - (z).tv_sec; \ - (x).tv_nsec += (y).tv_nsec - (z).tv_nsec; \ - /* Normalize after each add to avoid overflow/underflow of tv_nsec */ \ - while ((x).tv_nsec < 0) \ - { \ - (x).tv_nsec += 1000000000; \ - (x).tv_sec--; \ - } \ - while ((x).tv_nsec >= 1000000000) \ - { \ - (x).tv_nsec -= 1000000000; \ - (x).tv_sec++; \ - } \ - } while (0) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).tv_sec) + ((double) (t).tv_nsec) / 1000000000.0) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).tv_sec * 1000.0) + ((double) (t).tv_nsec) / 1000000.0) - -#define INSTR_TIME_GET_MICROSEC(t) \ - (((uint64) (t).tv_sec * (uint64) 1000000) + (uint64) ((t).tv_nsec / 1000)) #else /* WIN32 */ + /* Use QueryPerformanceCounter() */ -typedef LARGE_INTEGER instr_time; +/* helper for INSTR_TIME_SET_CURRENT */ +static inline instr_time +pg_query_performance_counter(void) +{ + instr_time now; + LARGE_INTEGER tmp; -#define INSTR_TIME_IS_ZERO(t) ((t).QuadPart == 0) + QueryPerformanceCounter(&tmp); + now.ticks = tmp.QuadPart; -#define INSTR_TIME_SET_ZERO(t) ((t).QuadPart = 0) - -#define INSTR_TIME_SET_CURRENT(t) QueryPerformanceCounter(&(t)) - -#define INSTR_TIME_ADD(x,y) \ - ((x).QuadPart += (y).QuadPart) - -#define INSTR_TIME_SUBTRACT(x,y) \ - ((x).QuadPart -= (y).QuadPart) - -#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ - ((x).QuadPart += (y).QuadPart - (z).QuadPart) - -#define INSTR_TIME_GET_DOUBLE(t) \ - (((double) (t).QuadPart) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MILLISEC(t) \ - (((double) (t).QuadPart * 1000.0) / GetTimerFrequency()) - -#define INSTR_TIME_GET_MICROSEC(t) \ - ((uint64) (((double) (t).QuadPart * 1000000.0) / GetTimerFrequency())) + return now; +} static inline double GetTimerFrequency(void) @@ -177,11 +153,45 @@ GetTimerFrequency(void) return (double) f.QuadPart; } +#define INSTR_TIME_SET_CURRENT(t) \ + ((t) = pg_query_performance_counter()) + +#define INSTR_TIME_GET_NANOSEC(t) \ + ((int64) (((double) (t).ticks * NS_PER_S) / GetTimerFrequency())) + #endif /* WIN32 */ -/* same macro on all platforms */ + +/* + * Common macros + */ + +#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) + +#define INSTR_TIME_SUBTRACT(x,y) \ + ((x).ticks -= (y).ticks) + +#define INSTR_TIME_ACCUM_DIFF(x,y,z) \ + ((x).ticks += (y).ticks - (z).ticks) + + +#define INSTR_TIME_GET_DOUBLE(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S) + +#define INSTR_TIME_GET_MILLISEC(t) \ + ((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_MS) + +#define INSTR_TIME_GET_MICROSEC(t) \ + (INSTR_TIME_GET_NANOSEC(t) / NS_PER_US) + #endif /* INSTR_TIME_H */ -- 2.38.0 --vt42kbp2j7rjcapp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v8-0003-instr_time-Add-INSTR_TIME_SET_SECONDS-INSTR_TIME_.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v10 1/7] Row pattern recognition patch for raw parser. @ 2023-10-22 02:22 Tatsuo Ishii <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Tatsuo Ishii @ 2023-10-22 02:22 UTC (permalink / raw) --- src/backend/parser/gram.y | 222 ++++++++++++++++++++++++++++++-- src/include/nodes/parsenodes.h | 56 ++++++++ src/include/parser/kwlist.h | 8 ++ src/include/parser/parse_node.h | 1 + 4 files changed, 273 insertions(+), 14 deletions(-) diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y index c224df4ecc..e09eb061f8 100644 --- a/src/backend/parser/gram.y +++ b/src/backend/parser/gram.y @@ -251,6 +251,8 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query); DefElem *defelt; SortBy *sortby; WindowDef *windef; + RPCommonSyntax *rpcom; + RPSubsetItem *rpsubset; JoinExpr *jexpr; IndexElem *ielem; StatsElem *selem; @@ -278,6 +280,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query); MergeWhenClause *mergewhen; struct KeyActions *keyactions; struct KeyAction *keyaction; + RPSkipTo skipto; } %type <node> stmt toplevel_stmt schema_stmt routine_body_stmt @@ -453,8 +456,12 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query); TriggerTransitions TriggerReferencing vacuum_relation_list opt_vacuum_relation_list drop_option_list pub_obj_list - -%type <node> opt_routine_body + row_pattern_measure_list row_pattern_definition_list + opt_row_pattern_subset_clause + row_pattern_subset_list row_pattern_subset_rhs + row_pattern +%type <rpsubset> row_pattern_subset_item +%type <node> opt_routine_body row_pattern_term %type <groupclause> group_clause %type <list> group_by_list %type <node> group_by_item empty_grouping_set rollup_clause cube_clause @@ -551,6 +558,8 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query); %type <range> relation_expr_opt_alias %type <node> tablesample_clause opt_repeatable_clause %type <target> target_el set_target insert_column_item + row_pattern_measure_item row_pattern_definition +%type <skipto> first_or_last %type <str> generic_option_name %type <node> generic_option_arg @@ -633,6 +642,9 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query); %type <list> window_clause window_definition_list opt_partition_clause %type <windef> window_definition over_clause window_specification opt_frame_clause frame_extent frame_bound +%type <rpcom> opt_row_pattern_common_syntax opt_row_pattern_skip_to +%type <boolean> opt_row_pattern_initial_or_seek +%type <list> opt_row_pattern_measures %type <ival> opt_window_exclusion_clause %type <str> opt_existing_window_name %type <boolean> opt_if_not_exists @@ -659,7 +671,6 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query); json_object_constructor_null_clause_opt json_array_constructor_null_clause_opt - /* * Non-keyword token types. These are hard-wired into the "flex" lexer. * They must be listed first so that their numeric codes do not depend on @@ -702,7 +713,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query); CURRENT_TIME CURRENT_TIMESTAMP CURRENT_USER CURSOR CYCLE DATA_P DATABASE DAY_P DEALLOCATE DEC DECIMAL_P DECLARE DEFAULT DEFAULTS - DEFERRABLE DEFERRED DEFINER DELETE_P DELIMITER DELIMITERS DEPENDS DEPTH DESC + DEFERRABLE DEFERRED DEFINE DEFINER DELETE_P DELIMITER DELIMITERS DEPENDS DEPTH DESC DETACH DICTIONARY DISABLE_P DISCARD DISTINCT DO DOCUMENT_P DOMAIN_P DOUBLE_P DROP @@ -718,7 +729,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query); HANDLER HAVING HEADER_P HOLD HOUR_P IDENTITY_P IF_P ILIKE IMMEDIATE IMMUTABLE IMPLICIT_P IMPORT_P IN_P INCLUDE - INCLUDING INCREMENT INDENT INDEX INDEXES INHERIT INHERITS INITIALLY INLINE_P + INCLUDING INCREMENT INDENT INDEX INDEXES INHERIT INHERITS INITIAL INITIALLY INLINE_P INNER_P INOUT INPUT_P INSENSITIVE INSERT INSTEAD INT_P INTEGER INTERSECT INTERVAL INTO INVOKER IS ISNULL ISOLATION @@ -731,7 +742,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query); LEADING LEAKPROOF LEAST LEFT LEVEL LIKE LIMIT LISTEN LOAD LOCAL LOCALTIME LOCALTIMESTAMP LOCATION LOCK_P LOCKED LOGGED - MAPPING MATCH MATCHED MATERIALIZED MAXVALUE MERGE METHOD + MAPPING MATCH MATCHED MATERIALIZED MAXVALUE MEASURES MERGE METHOD MINUTE_P MINVALUE MODE MONTH_P MOVE NAME_P NAMES NATIONAL NATURAL NCHAR NEW NEXT NFC NFD NFKC NFKD NO NONE @@ -743,8 +754,8 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query); ORDER ORDINALITY OTHERS OUT_P OUTER_P OVER OVERLAPS OVERLAY OVERRIDING OWNED OWNER - PARALLEL PARAMETER PARSER PARTIAL PARTITION PASSING PASSWORD - PLACING PLANS POLICY + PARALLEL PARAMETER PARSER PARTIAL PARTITION PASSING PASSWORD PAST + PATTERN_P PERMUTE PLACING PLANS POLICY POSITION PRECEDING PRECISION PRESERVE PREPARE PREPARED PRIMARY PRIOR PRIVILEGES PROCEDURAL PROCEDURE PROCEDURES PROGRAM PUBLICATION @@ -755,12 +766,13 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query); RESET RESTART RESTRICT RETURN RETURNING RETURNS REVOKE RIGHT ROLE ROLLBACK ROLLUP ROUTINE ROUTINES ROW ROWS RULE - SAVEPOINT SCALAR SCHEMA SCHEMAS SCROLL SEARCH SECOND_P SECURITY SELECT + SAVEPOINT SCALAR SCHEMA SCHEMAS SCROLL SEARCH SECOND_P SECURITY SEEK SELECT SEQUENCE SEQUENCES + SERIALIZABLE SERVER SESSION SESSION_USER SET SETS SETOF SHARE SHOW SIMILAR SIMPLE SKIP SMALLINT SNAPSHOT SOME SQL_P STABLE STANDALONE_P START STATEMENT STATISTICS STDIN STDOUT STORAGE STORED STRICT_P STRIP_P - SUBSCRIPTION SUBSTRING SUPPORT SYMMETRIC SYSID SYSTEM_P SYSTEM_USER + SUBSCRIPTION SUBSET SUBSTRING SUPPORT SYMMETRIC SYSID SYSTEM_P SYSTEM_USER TABLE TABLES TABLESAMPLE TABLESPACE TEMP TEMPLATE TEMPORARY TEXT_P THEN TIES TIME TIMESTAMP TO TRAILING TRANSACTION TRANSFORM @@ -853,6 +865,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query); */ %nonassoc UNBOUNDED /* ideally would have same precedence as IDENT */ %nonassoc IDENT PARTITION RANGE ROWS GROUPS PRECEDING FOLLOWING CUBE ROLLUP +%nonassoc MEASURES AFTER INITIAL SEEK PATTERN_P %left Op OPERATOR /* multi-character ops and user-defined operators */ %left '+' '-' %left '*' '/' '%' @@ -15901,7 +15914,8 @@ over_clause: OVER window_specification ; window_specification: '(' opt_existing_window_name opt_partition_clause - opt_sort_clause opt_frame_clause ')' + opt_sort_clause opt_row_pattern_measures opt_frame_clause + opt_row_pattern_common_syntax ')' { WindowDef *n = makeNode(WindowDef); @@ -15909,10 +15923,12 @@ window_specification: '(' opt_existing_window_name opt_partition_clause n->refname = $2; n->partitionClause = $3; n->orderClause = $4; + n->rowPatternMeasures = $5; /* copy relevant fields of opt_frame_clause */ - n->frameOptions = $5->frameOptions; - n->startOffset = $5->startOffset; - n->endOffset = $5->endOffset; + n->frameOptions = $6->frameOptions; + n->startOffset = $6->startOffset; + n->endOffset = $6->endOffset; + n->rpCommonSyntax = $7; n->location = @1; $$ = n; } @@ -15936,6 +15952,31 @@ opt_partition_clause: PARTITION BY expr_list { $$ = $3; } | /*EMPTY*/ { $$ = NIL; } ; +/* + * ROW PATTERN_P MEASURES + */ +opt_row_pattern_measures: MEASURES row_pattern_measure_list { $$ = $2; } + | /*EMPTY*/ { $$ = NIL; } + ; + +row_pattern_measure_list: + row_pattern_measure_item + { $$ = list_make1($1); } + | row_pattern_measure_list ',' row_pattern_measure_item + { $$ = lappend($1, $3); } + ; + +row_pattern_measure_item: + a_expr AS ColLabel + { + $$ = makeNode(ResTarget); + $$->name = $3; + $$->indirection = NIL; + $$->val = (Node *) $1; + $$->location = @1; + } + ; + /* * For frame clauses, we return a WindowDef, but only some fields are used: * frameOptions, startOffset, and endOffset. @@ -16095,6 +16136,143 @@ opt_window_exclusion_clause: | /*EMPTY*/ { $$ = 0; } ; +opt_row_pattern_common_syntax: +opt_row_pattern_skip_to opt_row_pattern_initial_or_seek + PATTERN_P '(' row_pattern ')' + opt_row_pattern_subset_clause + DEFINE row_pattern_definition_list + { + RPCommonSyntax *n = makeNode(RPCommonSyntax); + n->rpSkipTo = $1->rpSkipTo; + n->rpSkipVariable = $1->rpSkipVariable; + n->initial = $2; + n->rpPatterns = $5; + n->rpSubsetClause = $7; + n->rpDefs = $9; + $$ = n; + } + | /*EMPTY*/ { $$ = NULL; } + ; + +opt_row_pattern_skip_to: + AFTER MATCH SKIP TO NEXT ROW + { + RPCommonSyntax *n = makeNode(RPCommonSyntax); + n->rpSkipTo = ST_NEXT_ROW; + n->rpSkipVariable = NULL; + $$ = n; + } + | AFTER MATCH SKIP PAST LAST_P ROW + { + RPCommonSyntax *n = makeNode(RPCommonSyntax); + n->rpSkipTo = ST_PAST_LAST_ROW; + n->rpSkipVariable = NULL; + $$ = n; + } + | AFTER MATCH SKIP TO first_or_last ColId + { + RPCommonSyntax *n = makeNode(RPCommonSyntax); + n->rpSkipTo = $5; + n->rpSkipVariable = $6; + $$ = n; + } +/* + | AFTER MATCH SKIP TO LAST_P ColId %prec LAST_P + { + RPCommonSyntax *n = makeNode(RPCommonSyntax); + n->rpSkipTo = ST_LAST_VARIABLE; + n->rpSkipVariable = $6; + $$ = n; + } + | AFTER MATCH SKIP TO ColId + { + RPCommonSyntax *n = makeNode(RPCommonSyntax); + n->rpSkipTo = ST_VARIABLE; + n->rpSkipVariable = $5; + $$ = n; + } +*/ + | /*EMPTY*/ + { + RPCommonSyntax *n = makeNode(RPCommonSyntax); + /* temporary set default to ST_NEXT_ROW */ + n->rpSkipTo = ST_PAST_LAST_ROW; + n->rpSkipVariable = NULL; + $$ = n; + } + ; + +first_or_last: + FIRST_P { $$ = ST_FIRST_VARIABLE; } + | LAST_P { $$ = ST_LAST_VARIABLE; } + ; + +opt_row_pattern_initial_or_seek: + INITIAL { $$ = true; } + | SEEK + { + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("SEEK is not supported"), + errhint("Use INITIAL."), + parser_errposition(@1))); + } + | /*EMPTY*/ { $$ = true; } + ; + +row_pattern: + row_pattern_term { $$ = list_make1($1); } + | row_pattern row_pattern_term { $$ = lappend($1, $2); } + ; + +row_pattern_term: + ColId { $$ = (Node *) makeSimpleA_Expr(AEXPR_OP, "", (Node *)makeString($1), NULL, @1); } + | ColId '*' { $$ = (Node *) makeSimpleA_Expr(AEXPR_OP, "*", (Node *)makeString($1), NULL, @1); } + | ColId '+' { $$ = (Node *) makeSimpleA_Expr(AEXPR_OP, "+", (Node *)makeString($1), NULL, @1); } + | ColId '?' { $$ = (Node *) makeSimpleA_Expr(AEXPR_OP, "?", (Node *)makeString($1), NULL, @1); } + ; + +opt_row_pattern_subset_clause: + SUBSET row_pattern_subset_list { $$ = $2; } + | /*EMPTY*/ { $$ = NIL; } + ; + +row_pattern_subset_list: + row_pattern_subset_item { $$ = list_make1($1); } + | row_pattern_subset_list ',' row_pattern_subset_item { $$ = lappend($1, $3); } + | /*EMPTY*/ { $$ = NIL; } + ; + +row_pattern_subset_item: ColId '=' '(' row_pattern_subset_rhs ')' + { + RPSubsetItem *n = makeNode(RPSubsetItem); + n->name = $1; + n->rhsVariable = $4; + $$ = n; + } + ; + +row_pattern_subset_rhs: + ColId { $$ = list_make1(makeStringConst($1, @1)); } + | row_pattern_subset_rhs ',' ColId { $$ = lappend($1, makeStringConst($3, @1)); } + | /*EMPTY*/ { $$ = NIL; } + ; + +row_pattern_definition_list: + row_pattern_definition { $$ = list_make1($1); } + | row_pattern_definition_list ',' row_pattern_definition { $$ = lappend($1, $3); } + ; + +row_pattern_definition: + ColId AS a_expr + { + $$ = makeNode(ResTarget); + $$->name = $1; + $$->indirection = NIL; + $$->val = (Node *) $3; + $$->location = @1; + } + ; /* * Supporting nonterminals for expressions. @@ -17190,6 +17368,7 @@ unreserved_keyword: | INDEXES | INHERIT | INHERITS + | INITIAL | INLINE_P | INPUT_P | INSENSITIVE @@ -17217,6 +17396,7 @@ unreserved_keyword: | MATCHED | MATERIALIZED | MAXVALUE + | MEASURES | MERGE | METHOD | MINUTE_P @@ -17259,6 +17439,9 @@ unreserved_keyword: | PARTITION | PASSING | PASSWORD + | PAST + | PATTERN_P + | PERMUTE | PLANS | POLICY | PRECEDING @@ -17309,6 +17492,7 @@ unreserved_keyword: | SEARCH | SECOND_P | SECURITY + | SEEK | SEQUENCE | SEQUENCES | SERIALIZABLE @@ -17334,6 +17518,7 @@ unreserved_keyword: | STRICT_P | STRIP_P | SUBSCRIPTION + | SUBSET | SUPPORT | SYSID | SYSTEM_P @@ -17521,6 +17706,7 @@ reserved_keyword: | CURRENT_USER | DEFAULT | DEFERRABLE + | DEFINE | DESC | DISTINCT | DO @@ -17683,6 +17869,7 @@ bare_label_keyword: | DEFAULTS | DEFERRABLE | DEFERRED + | DEFINE | DEFINER | DELETE_P | DELIMITER @@ -17758,6 +17945,7 @@ bare_label_keyword: | INDEXES | INHERIT | INHERITS + | INITIAL | INITIALLY | INLINE_P | INNER_P @@ -17807,6 +17995,7 @@ bare_label_keyword: | MATCHED | MATERIALIZED | MAXVALUE + | MEASURES | MERGE | METHOD | MINVALUE @@ -17860,6 +18049,9 @@ bare_label_keyword: | PARTITION | PASSING | PASSWORD + | PAST + | PATTERN_P + | PERMUTE | PLACING | PLANS | POLICY @@ -17916,6 +18108,7 @@ bare_label_keyword: | SCROLL | SEARCH | SECURITY + | SEEK | SELECT | SEQUENCE | SEQUENCES @@ -17947,6 +18140,7 @@ bare_label_keyword: | STRICT_P | STRIP_P | SUBSCRIPTION + | SUBSET | SUBSTRING | SUPPORT | SYMMETRIC diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h index f637937cd2..31b04d6919 100644 --- a/src/include/nodes/parsenodes.h +++ b/src/include/nodes/parsenodes.h @@ -547,6 +547,44 @@ typedef struct SortBy int location; /* operator location, or -1 if none/unknown */ } SortBy; +/* + * AFTER MATCH row pattern skip to types in row pattern common syntax + */ +typedef enum RPSkipTo +{ + ST_NONE, /* AFTER MATCH omitted */ + ST_NEXT_ROW, /* SKIP TO NEXT ROW */ + ST_PAST_LAST_ROW, /* SKIP TO PAST LAST ROW */ + ST_FIRST_VARIABLE, /* SKIP TO FIRST variable name */ + ST_LAST_VARIABLE, /* SKIP TO LAST variable name */ + ST_VARIABLE /* SKIP TO variable name */ +} RPSkipTo; + +/* + * Row Pattern SUBSET clause item + */ +typedef struct RPSubsetItem +{ + NodeTag type; + char *name; /* Row Pattern SUBSET clause variable name */ + List *rhsVariable; /* Row Pattern SUBSET rhs variables (list of char *string) */ +} RPSubsetItem; + +/* + * RowPatternCommonSyntax - raw representation of row pattern common syntax + * + */ +typedef struct RPCommonSyntax +{ + NodeTag type; + RPSkipTo rpSkipTo; /* Row Pattern AFTER MATCH SKIP type */ + char *rpSkipVariable; /* Row Pattern Skip To variable name, if any */ + bool initial; /* true if <row pattern initial or seek> is initial */ + List *rpPatterns; /* PATTERN variables (list of A_Expr) */ + List *rpSubsetClause; /* row pattern subset clause (list of RPSubsetItem), if any */ + List *rpDefs; /* row pattern definitions clause (list of ResTarget) */ +} RPCommonSyntax; + /* * WindowDef - raw representation of WINDOW and OVER clauses * @@ -562,6 +600,8 @@ typedef struct WindowDef char *refname; /* referenced window name, if any */ List *partitionClause; /* PARTITION BY expression list */ List *orderClause; /* ORDER BY (list of SortBy) */ + List *rowPatternMeasures; /* row pattern measures (list of ResTarget) */ + RPCommonSyntax *rpCommonSyntax; /* row pattern common syntax */ int frameOptions; /* frame_clause options, see below */ Node *startOffset; /* expression for starting bound, if any */ Node *endOffset; /* expression for ending bound, if any */ @@ -1483,6 +1523,11 @@ typedef struct GroupingSet * the orderClause might or might not be copied (see copiedOrder); the framing * options are never copied, per spec. * + * "defineClause" is Row Pattern Recognition DEFINE clause (list of + * TargetEntry). TargetEntry.resname represents row pattern definition + * variable name. "patternVariable" and "patternRegexp" represents PATTERN + * clause. + * * The information relevant for the query jumbling is the partition clause * type and its bounds. */ @@ -1514,6 +1559,17 @@ typedef struct WindowClause Index winref; /* ID referenced by window functions */ /* did we copy orderClause from refname? */ bool copiedOrder pg_node_attr(query_jumble_ignore); + /* Row Pattern AFTER MACH SKIP clause */ + RPSkipTo rpSkipTo; /* Row Pattern Skip To type */ + bool initial; /* true if <row pattern initial or seek> is initial */ + /* Row Pattern DEFINE clause (list of TargetEntry) */ + List *defineClause; + /* Row Pattern DEFINE variable initial names (list of String) */ + List *defineInitial; + /* Row Pattern PATTERN variable name (list of String) */ + List *patternVariable; + /* Row Pattern PATTERN regular expression quantifier ('+' or ''. list of String) */ + List *patternRegexp; } WindowClause; /* diff --git a/src/include/parser/kwlist.h b/src/include/parser/kwlist.h index 5984dcfa4b..2804333b53 100644 --- a/src/include/parser/kwlist.h +++ b/src/include/parser/kwlist.h @@ -128,6 +128,7 @@ PG_KEYWORD("default", DEFAULT, RESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("defaults", DEFAULTS, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("deferrable", DEFERRABLE, RESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("deferred", DEFERRED, UNRESERVED_KEYWORD, BARE_LABEL) +PG_KEYWORD("define", DEFINE, RESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("definer", DEFINER, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("delete", DELETE_P, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("delimiter", DELIMITER, UNRESERVED_KEYWORD, BARE_LABEL) @@ -212,6 +213,7 @@ PG_KEYWORD("index", INDEX, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("indexes", INDEXES, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("inherit", INHERIT, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("inherits", INHERITS, UNRESERVED_KEYWORD, BARE_LABEL) +PG_KEYWORD("initial", INITIAL, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("initially", INITIALLY, RESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("inline", INLINE_P, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("inner", INNER_P, TYPE_FUNC_NAME_KEYWORD, BARE_LABEL) @@ -265,6 +267,7 @@ PG_KEYWORD("match", MATCH, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("matched", MATCHED, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("materialized", MATERIALIZED, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("maxvalue", MAXVALUE, UNRESERVED_KEYWORD, BARE_LABEL) +PG_KEYWORD("measures", MEASURES, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("merge", MERGE, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("method", METHOD, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("minute", MINUTE_P, UNRESERVED_KEYWORD, AS_LABEL) @@ -326,6 +329,9 @@ PG_KEYWORD("partial", PARTIAL, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("partition", PARTITION, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("passing", PASSING, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("password", PASSWORD, UNRESERVED_KEYWORD, BARE_LABEL) +PG_KEYWORD("past", PAST, UNRESERVED_KEYWORD, BARE_LABEL) +PG_KEYWORD("pattern", PATTERN_P, UNRESERVED_KEYWORD, BARE_LABEL) +PG_KEYWORD("permute", PERMUTE, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("placing", PLACING, RESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("plans", PLANS, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("policy", POLICY, UNRESERVED_KEYWORD, BARE_LABEL) @@ -385,6 +391,7 @@ PG_KEYWORD("scroll", SCROLL, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("search", SEARCH, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("second", SECOND_P, UNRESERVED_KEYWORD, AS_LABEL) PG_KEYWORD("security", SECURITY, UNRESERVED_KEYWORD, BARE_LABEL) +PG_KEYWORD("seek", SEEK, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("select", SELECT, RESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("sequence", SEQUENCE, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("sequences", SEQUENCES, UNRESERVED_KEYWORD, BARE_LABEL) @@ -416,6 +423,7 @@ PG_KEYWORD("stored", STORED, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("strict", STRICT_P, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("strip", STRIP_P, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("subscription", SUBSCRIPTION, UNRESERVED_KEYWORD, BARE_LABEL) +PG_KEYWORD("subset", SUBSET, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("substring", SUBSTRING, COL_NAME_KEYWORD, BARE_LABEL) PG_KEYWORD("support", SUPPORT, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("symmetric", SYMMETRIC, RESERVED_KEYWORD, BARE_LABEL) diff --git a/src/include/parser/parse_node.h b/src/include/parser/parse_node.h index f589112d5e..6640090910 100644 --- a/src/include/parser/parse_node.h +++ b/src/include/parser/parse_node.h @@ -51,6 +51,7 @@ typedef enum ParseExprKind EXPR_KIND_WINDOW_FRAME_RANGE, /* window frame clause with RANGE */ EXPR_KIND_WINDOW_FRAME_ROWS, /* window frame clause with ROWS */ EXPR_KIND_WINDOW_FRAME_GROUPS, /* window frame clause with GROUPS */ + EXPR_KIND_RPR_DEFINE, /* DEFINE */ EXPR_KIND_SELECT_TARGET, /* SELECT target list item */ EXPR_KIND_INSERT_TARGET, /* INSERT target list item */ EXPR_KIND_UPDATE_SOURCE, /* UPDATE assignment source item */ -- 2.25.1 ----Next_Part(Sun_Oct_22_11_39_20_2023_140)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v10-0002-Row-pattern-recognition-patch-parse-analysis.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
end of thread, other threads:[~2023-10-22 02:22 UTC | newest] Thread overview: 261+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-01-17 04:38 [PATCH v8 2/5] instr_time: Represent time as an int64 on all platforms Andres Freund <[email protected]> 2023-10-22 02:22 [PATCH v10 1/7] Row pattern recognition patch for raw parser. Tatsuo Ishii <[email protected]>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox