pack-objects: Add runtime detection of online CPU's

Packing objects can be done in parallell nowadays, but it's
only done if the config option pack.threads is set to a value
above 1. Because of that, the code-path used is often not the
most optimal one.

This patch adds a routine to detect the number of online CPU's
at runtime (online_cpus()). When pack.threads (or --threads=) is
given a value of 0, the number of threads is set to the number of
online CPU's. This feature is also documented.

As per Nicolas Pitre's recommendations, the default is still to
run pack-objects single-threaded unless explicitly activated,
either by configuration or by command line parameter.

The routine online_cpus() is a rework of "numcpus.c", written by
one Philip Willoughby <pgw99@doc.ic.ac.uk>. numcpus.c is in the
public domain and can presently be downloaded from
http://csgsoft.doc.ic.ac.uk/numcpus/

Signed-off-by: Andreas Ericsson <ae@op5.se>
Signed-off-by: Brandon Casey <casey@nrlssc.navy.mil>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Documentation/config.txt

@@ -808,6 +808,8 @@ pack.threads::
 	warning. This is meant to reduce packing time on multiprocessor
 	machines. The required amount of memory for the delta search window
 	is however multiplied by the number of threads.
+	Specifying 0 will cause git to auto-detect the number of CPU's
+	and set the number of threads accordingly.
 
 pack.indexVersion::
 	Specify the default pack index version.  Valid values are 1 for

Documentation/git-pack-objects.txt

@@ -177,6 +177,8 @@ base-name::
 	This is meant to reduce packing time on multiprocessor machines.
 	The required amount of memory for the delta search window is
 	however multiplied by the number of threads.
+	Specifying 0 will cause git to auto-detect the number of CPU's
+	and set the number of threads accordingly.
 
 --index-version=<version>[,<offset>]::
 	This is intended to be used by the test suite only. It allows

Makefile

@@ -741,6 +741,7 @@ endif
 ifdef THREADED_DELTA_SEARCH
 	BASIC_CFLAGS += -DTHREADED_DELTA_SEARCH
 	EXTLIBS += -lpthread
+	LIB_OBJS += thread-utils.o
 endif
 
 ifeq ($(TCLTK_PATH),)

builtin-pack-objects.c

@@ -16,6 +16,7 @@
 #include "progress.h"
 
 #ifdef THREADED_DELTA_SEARCH
+#include "thread-utils.h"
 #include <pthread.h>
 #endif
 
@@ -1852,11 +1853,11 @@ static int git_pack_config(const char *k, const char *v)
 	}
 	if (!strcmp(k, "pack.threads")) {
 		delta_search_threads = git_config_int(k, v);
-		if (delta_search_threads < 1)
+		if (delta_search_threads < 0)
 			die("invalid number of threads specified (%d)",
 			    delta_search_threads);
 #ifndef THREADED_DELTA_SEARCH
-		if (delta_search_threads > 1)
+		if (delta_search_threads != 1)
 			warning("no threads support, ignoring %s", k);
 #endif
 		return 0;
@@ -2122,10 +2123,10 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 		if (!prefixcmp(arg, "--threads=")) {
 			char *end;
 			delta_search_threads = strtoul(arg+10, &end, 0);
-			if (!arg[10] || *end || delta_search_threads < 1)
+			if (!arg[10] || *end || delta_search_threads < 0)
 				usage(pack_usage);
 #ifndef THREADED_DELTA_SEARCH
-			if (delta_search_threads > 1)
+			if (delta_search_threads != 1)
 				warning("no threads support, "
 					"ignoring %s", arg);
 #endif
@@ -2235,6 +2236,11 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 	if (!pack_to_stdout && thin)
 		die("--thin cannot be used to build an indexable pack.");
 
+#ifdef THREADED_DELTA_SEARCH
+	if (!delta_search_threads)	/* --threads=0 means autodetect */
+		delta_search_threads = online_cpus();
+#endif
+
 	prepare_packed_git();
 
 	if (progress)

thread-utils.c

@@ -0,0 +1,48 @@
+#include "cache.h"
+
+#ifdef _WIN32
+#  define WIN32_LEAN_AND_MEAN
+#  include <windows.h>
+#elif defined(hpux) || defined(__hpux) || defined(_hpux)
+#  include <sys/pstat.h>
+#endif
+
+/*
+ * By doing this in two steps we can at least get
+ * the function to be somewhat coherent, even
+ * with this disgusting nest of #ifdefs.
+ */
+#ifndef _SC_NPROCESSORS_ONLN
+#  ifdef _SC_NPROC_ONLN
+#    define _SC_NPROCESSORS_ONLN _SC_NPROC_ONLN
+#  elif defined _SC_CRAY_NCPU
+#    define _SC_NPROCESSORS_ONLN _SC_CRAY_NCPU
+#  endif
+#endif
+
+int online_cpus(void)
+{
+#ifdef _SC_NPROCESSORS_ONLN
+	long ncpus;
+#endif
+
+#ifdef _WIN32
+	SYSTEM_INFO info;
+	GetSystemInfo(&info);
+
+	if ((int)info.dwNumberOfProcessors > 0)
+		return (int)info.dwNumberOfProcessors;
+#elif defined(hpux) || defined(__hpux) || defined(_hpux)
+	struct pst_dynamic psd;
+
+	if (!pstat_getdynamic(&psd, sizeof(psd), (size_t)1, 0))
+		return (int)psd.psd_proc_cnt;
+#endif
+
+#ifdef _SC_NPROCESSORS_ONLN
+	if ((ncpus = (long)sysconf(_SC_NPROCESSORS_ONLN)) > 0)
+		return (int)ncpus;
+#endif
+
+	return 1;
+}

thread-utils.h

@@ -0,0 +1,6 @@
+#ifndef THREAD_COMPAT_H
+#define THREAD_COMPAT_H
+
+extern int online_cpus(void);
+
+#endif /* THREAD_COMPAT_H */