libstdc++/7445: poor performance of std::locale::classic() in multi-threaded applications

[Alex Kompel]

The following reply was made to PR libstdc++/7445; it has been noted by GNATS.

From: "Alex Kompel" <shurik@sequoiap.com>
To: "Benjamin Kosnik" <bkoz@redhat.com>
Cc: <bkoz@gcc.gnu.org>, <gcc-bugs@gcc.gnu.org>, <gcc-prs@gcc.gnu.org>,
   <ljrittle@gcc.gnu.org>, <gcc-gnats@gcc.gnu.org>
Subject: Re: libstdc++/7445: poor performance of std::locale::classic() in multi-threaded applications
Date: Tue, 12 Nov 2002 12:48:46 -0800

 This is a multi-part message in MIME format.
 
 ------=_NextPart_000_0063_01C28A49.D6F2B070
 Content-Type: text/plain;
 	charset="iso-8859-1"
 Content-Transfer-Encoding: 7bit
 
 > 
 > >I am a bit confused. Audit trail is kind of hard to read. Have you been
 > >waiting on something from me?
 > 
 > Uh. Yeah.
 > 
 > We need a test case. Provide one and we'll re-open this. I thought I'd
 > made this clear, but apparently not.
 > 
 
 See the attached file. 
 get_locale() is functionally equivalent to std::locale::classic()
 
 ----- test results (RedHat 7.3 2.4.18-17.7.xsmp 2 CPU -----
 [root@epos4 test]# c++ -DDO_LOCK -o test_lock -pthread loc_thr.cpp
 [root@epos4 test]# c++ -o test_nolock -pthread loc_thr.cpp
 [root@epos4 test]# ./test_lock
 Creating thread 0
 Creating thread 1
 Creating thread 2
 Creating thread 3
 Starting sorting...
 Sorting time:    4.08
 Sorting time:    4.02
 Sorting time:    4.26
 Sorting time:    4.21
 [root@epos4 test]# ./test_nolock
 Creating thread 0
 Creating thread 1
 Creating thread 2
 Creating thread 3
 Starting sorting...
 Sorting time:    0.06
 Sorting time:    0.06
 Sorting time:    0.06
 Sorting time:    0.06
 
 ------=_NextPart_000_0063_01C28A49.D6F2B070
 Content-Type: application/octet-stream;
 	name="loc_thr.cpp"
 Content-Transfer-Encoding: quoted-printable
 Content-Disposition: attachment;
 	filename="loc_thr.cpp"
 
 #include <pthread.h>=0A=
 #include <locale>=0A=
 #include <string>=0A=
 #include <functional>=0A=
 #include <list>=0A=
 =0A=
 #define NUM_THREADS 4=0A=
 #define SORT_SIZE 1000=0A=
 #define NSAMPLES 5=0A=
 const char* samples[NSAMPLES] =3D {=0A=
 	"this is just a test 1",=0A=
 	"THIS IS JUST A TEST 1",=0A=
 	"this IS JUST A TEST 1",=0A=
 	"THIS IS JUST A TEST 2",=0A=
 	"this is just a test 2"=0A=
 };=0A=
 =0A=
 extern const std::locale& get_locale() {=0A=
       static const std::locale* l =3D 0;=0A=
 #ifdef DO_LOCK=0A=
       static std::_STL_mutex_lock __lock __STL_MUTEX_INITIALIZER;=0A=
       std::_STL_auto_lock __auto(__lock);=0A=
       if( !l ) {=0A=
 	 l =3D &std::locale::classic();=0A=
       }=0A=
 #else=0A=
       if( !l ) {=0A=
          static std::_STL_mutex_lock __lock __STL_MUTEX_INITIALIZER;=0A=
          std::_STL_auto_lock __auto(__lock);=0A=
 	 l =3D &std::locale::classic();=0A=
       }=0A=
 #endif=0A=
       return *l;=0A=
 }=0A=
 =0A=
 template <class T>=0A=
 bool lowercase_less( T c1, T c2 ) {=0A=
 	return std::tolower(c1, get_locale()) < std::tolower(c2, get_locale());=0A=
 }=0A=
 =0A=
 template <class T>=0A=
 bool str_case_less(const std::basic_string<T>& s1, const =
 std::basic_string<T>& s2)=0A=
 {=0A=
 	return std::lexicographical_compare(=0A=
 			s1.begin(), s1.end(),=0A=
 			s2.begin(), s2.end(),=0A=
 			std::ptr_fun( lowercase_less<T> )=0A=
 		 );=0A=
 }=0A=
 =0A=
 pthread_mutex_t count_mutex;=0A=
 pthread_cond_t ready_sort;=0A=
 int ready_count =3D 0;=0A=
 =0A=
 typedef std::list<std::string> test_list;=0A=
 void* thread_main( void* ) =0A=
 {=0A=
 	test_list tl;=0A=
 =0A=
 	for( int i=3D0; i<SORT_SIZE; i++ ) {=0A=
 		tl.push_back( samples[i%NSAMPLES] );=0A=
 	}=0A=
 =0A=
     	pthread_mutex_lock(&count_mutex);=0A=
 	if( ++ready_count<NUM_THREADS ) {=0A=
     		pthread_cond_wait(&ready_sort, &count_mutex);=0A=
 	} else {=0A=
 		printf( "Starting sorting...\n" );=0A=
 		pthread_cond_broadcast(&ready_sort);=0A=
 	}=0A=
     	pthread_mutex_unlock(&count_mutex);=0A=
 =0A=
 	clock_t t1, t2;=0A=
 	t1 =3D clock();=0A=
 	tl.sort( str_case_less<char> );=0A=
 	t2 =3D clock();=0A=
 	printf( "Sorting time: %7.2f\n", (float)(t2-t1)/CLOCKS_PER_SEC);=0A=
 	return 0;=0A=
 }=0A=
 =0A=
 =0A=
 int main()=0A=
 {=0A=
 	pthread_t thread[NUM_THREADS];=0A=
    	pthread_attr_t attr;=0A=
 	int t;=0A=
 =0A=
   	/* Initialize mutex and condition variable objects */=0A=
  	pthread_mutex_init(&count_mutex, NULL);=0A=
   	pthread_cond_init(&ready_sort, NULL);=0A=
 =0A=
    	/* Initialize and set thread detached attribute */=0A=
    	pthread_attr_init(&attr);=0A=
    	pthread_attr_setdetachstate(&attr, PTHREAD_CREATE_JOINABLE);=0A=
 =0A=
    	for(t=3D0;t < NUM_THREADS;t++) {=0A=
       		printf("Creating thread %d\n", t);=0A=
       		pthread_create(&thread[t], &attr, thread_main, NULL); =0A=
    	}=0A=
 =0A=
    	/* Free attribute and wait for the other threads */=0A=
    	for(t=3D0;t < NUM_THREADS;t++) {=0A=
        		pthread_join(thread[t], NULL);=0A=
    	}=0A=
 =0A=
    	pthread_attr_destroy(&attr);=0A=
  	pthread_mutex_destroy(&count_mutex);=0A=
   	pthread_cond_destroy(&ready_sort);=0A=
 =0A=
 	return 0;=0A=
 }=0A=
 
 ------=_NextPart_000_0063_01C28A49.D6F2B070--