[RFC/PATCH v4 1/3] add high resolution timer function to debug performance issues

[Karsten Blees <karsten.blees@gmail.com>]

Add a getnanotime() function that returns nanoseconds since 01/01/1970 as
unsigned 64-bit integer (i.e. overflows in july 2554). This is easier to
work with than e.g. struct timeval or struct timespec.

The implementation uses gettimeofday() by default; supports high precision
time sources on the following platforms:
 * Linux: using clock_gettime(CLOCK_MONOTONIC)
 * Windows: using QueryPerformanceCounter()

Todo:
 * enable clock_gettime() on more platforms
 * implement Mac OSX version using mach_absolute_time

Signed-off-by: Karsten Blees <blees@dcon.de>
---
 Makefile         |  7 +++++
 cache.h          |  1 +
 config.mak.uname |  1 +
 trace.c          | 82 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 91 insertions(+)

diff --git a/Makefile b/Makefile
index a53f3a8..3c05f8c 100644
--- a/Makefile
+++ b/Makefile
@@ -341,6 +341,8 @@ all::
 #
 # Define GMTIME_UNRELIABLE_ERRORS if your gmtime() function does not
 # return NULL when it receives a bogus time_t.
+#
+# Define HAVE_CLOCK_GETTIME if your platform has clock_gettime in librt.
 
 GIT-VERSION-FILE: FORCE
 	@$(SHELL_PATH) ./GIT-VERSION-GEN
@@ -1497,6 +1499,11 @@ ifdef GMTIME_UNRELIABLE_ERRORS
 	BASIC_CFLAGS += -DGMTIME_UNRELIABLE_ERRORS
 endif
 
+ifdef HAVE_CLOCK_GETTIME
+	BASIC_CFLAGS += -DHAVE_CLOCK_GETTIME
+	EXTLIBS += -lrt
+endif
+
 ifeq ($(TCLTK_PATH),)
 NO_TCLTK = NoThanks
 endif
diff --git a/cache.h b/cache.h
index 107ac61..48fc616 100644
--- a/cache.h
+++ b/cache.h
@@ -1362,6 +1362,7 @@ extern int trace_want(const char *key);
 __attribute__((format (printf, 2, 3)))
 extern void trace_printf_key(const char *key, const char *fmt, ...);
 extern void trace_strbuf(const char *key, const struct strbuf *buf);
+extern uint64_t getnanotime(void);
 
 void packet_trace_identity(const char *prog);
 
diff --git a/config.mak.uname b/config.mak.uname
index 23a8803..5e3b1dd 100644
--- a/config.mak.uname
+++ b/config.mak.uname
@@ -33,6 +33,7 @@ ifeq ($(uname_S),Linux)
 	HAVE_PATHS_H = YesPlease
 	LIBC_CONTAINS_LIBINTL = YesPlease
 	HAVE_DEV_TTY = YesPlease
+	HAVE_CLOCK_GETTIME = YesPlease
 endif
 ifeq ($(uname_S),GNU/kFreeBSD)
 	NO_STRLCPY = YesPlease
diff --git a/trace.c b/trace.c
index 08180a9..3d72084 100644
--- a/trace.c
+++ b/trace.c
@@ -187,3 +187,85 @@ int trace_want(const char *key)
 		return 0;
 	return 1;
 }
+
+#ifdef HAVE_CLOCK_GETTIME
+
+static inline uint64_t highres_nanos(void)
+{
+	struct timespec ts;
+	if (clock_gettime(CLOCK_MONOTONIC, &ts))
+		return 0;
+	return (uint64_t) ts.tv_sec * 1000000000 + ts.tv_nsec;
+}
+
+#elif defined (GIT_WINDOWS_NATIVE)
+
+static inline uint64_t highres_nanos(void)
+{
+	static uint64_t high_ns, scaled_low_ns;
+	static int scale;
+	LARGE_INTEGER cnt;
+
+	if (!scale) {
+		if (!QueryPerformanceFrequency(&cnt))
+			return 0;
+
+		/* high_ns = number of ns per cnt.HighPart */
+		high_ns = (1000000000LL << 32) / (uint64_t) cnt.QuadPart;
+
+		/*
+		 * Number of ns per cnt.LowPart is 10^9 / frequency (or
+		 * high_ns >> 32). For maximum precision, we scale this factor
+		 * so that it just fits within 32 bit (i.e. won't overflow if
+		 * multiplied with cnt.LowPart).
+		 */
+		scaled_low_ns = high_ns;
+		scale = 32;
+		while (scaled_low_ns >= 0x100000000LL) {
+			scaled_low_ns >>= 1;
+			scale--;
+		}
+	}
+
+	/* if QPF worked on initialization, we expect QPC to work as well */
+	QueryPerformanceCounter(&cnt);
+
+	return (high_ns * cnt.HighPart) +
+	       ((scaled_low_ns * cnt.LowPart) >> scale);
+}
+
+#else
+# define highres_nanos() 0
+#endif
+
+static inline uint64_t gettimeofday_nanos(void)
+{
+	struct timeval tv;
+	gettimeofday(&tv, NULL);
+	return (uint64_t) tv.tv_sec * 1000000000 + tv.tv_usec * 1000;
+}
+
+/*
+ * Returns nanoseconds since the epoch (01/01/1970), for performance tracing
+ * (i.e. favoring high precision over wall clock time accuracy).
+ */
+inline uint64_t getnanotime(void)
+{
+	static uint64_t offset;
+	if (offset > 1) {
+		/* initialization succeeded, return offset + high res time */
+		return offset + highres_nanos();
+	} else if (offset == 1) {
+		/* initialization failed, fall back to gettimeofday */
+		return gettimeofday_nanos();
+	} else {
+		/* initialize offset if high resolution timer works */
+		uint64_t now = gettimeofday_nanos();
+		uint64_t highres = highres_nanos();
+		if (highres)
+			offset = now - highres;
+		else
+			offset = 1;
+		return now;
+	}
+}
-- 
1.9.2.msysgit.0.493.g47a82c3

-- 
-- 
*** Please reply-to-all at all times ***
*** (do not pretend to know who is subscribed and who is not) ***
*** Please avoid top-posting. ***
The msysGit Wiki is here: https://github.com/msysgit/msysgit/wiki - Github accounts are free.

You received this message because you are subscribed to the Google
Groups "msysGit" group.
To post to this group, send email to msysgit@googlegroups.com
To unsubscribe from this group, send email to
msysgit+unsubscribe@googlegroups.com
For more options, and view previous threads, visit this group at
http://groups.google.com/group/msysgit?hl=en_US?hl=en

--- 
You received this message because you are subscribed to the Google Groups "msysGit" group.
To unsubscribe from this group and stop receiving emails from it, send an email to msysgit+unsubscribe@googlegroups.com.
For more options, visit https://groups.google.com/d/optout.