From Bugzilla Helper:
User-Agent: Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0; T312461)

Description of problem:
A simple 4-thread code runs significantly slower on a 4-CPU computer than on a 
1-CPU computer. Apparently a scalability problem. When the code runs CPUs are 
mostly in idle state (60%) while the rest is split between user and system. 

Version-Release number of selected component (if applicable):


How reproducible:
Always

Steps to Reproduce:
1. Take the code 
2. Compile 
3. Run on a 4-CPU computer with 1 thread and 4 threads.
4. Watch CPU states 
5. Compare the results (seconds per iteration)
	

Actual Results:  STL C++ code with standard alloc

Launching 1 threads
6.1344e-06 sec per iteration

With 4 threads 
9.64e-5 sec per iteration


Expected Results:  maximum 10-20% degradation due to lock contention, not order 
of magnitude.

Additional info:

/////////////////
////
////  test with: c++  -pthread  PTest.C  -lpthread
////  actual code does nothing but fills a hash map. Memory 
////  consumption is 80-100 M per thread for  NUM_ITERATION=500000

#include <pthread.h>
#include <cstdlib>
#include <unistd.h>
#include <sys/time.h>

#include <map>
#include <string>
#include <utility>
#include <iostream>
#include <iomanip>
#include <bits/stl_pthread_alloc.h>
using namespace  std;

const int NUM_ITERATIONS=500000;

void *f(void *arg)
{
  using std::cout;
  using std::endl;
  using std::string;
  
  struct timeval tv_start, tv_end;

//  typedef 
std::map<int,string,std::less<int>,std::pthread_allocator<std::pair<int, 
string> > > map_str_int;
  typedef std::map<int,string,std::less<int> > map_str_int;

  map_str_int msi;
  gettimeofday(&tv_start, NULL);
  for(int i = 0; i < NUM_ITERATIONS; i++) msi.insert(std::pair<int, string >
(i, "value"));
  gettimeofday(&tv_end, NULL);
  cout << ( (tv_end.tv_sec - tv_start.tv_sec) + (tv_end.tv_usec - 
tv_start.tv_usec)/1.e6)/NUM_ITERATIONS << " sec per iteration" << endl;
  map_str_int::const_iterator fi;
  if((fi=msi.find(1491)) != msi.end())
    cout << "found 1491 " << fi->first << ';' << fi->second << endl;
  return 0;
}



main( int argc, char ** argv) {


  int NUM_THREADS = atoi(argv[1]);
  cerr << "Launching " << NUM_THREADS << " threads" << endl;
  void* ret=0;
  pthread_t thread[NUM_THREADS];
  for(int i=0;i<NUM_THREADS;++i)
    pthread_create(&thread[i], NULL, f, (void*)i);
  for(int i=0 ; i < NUM_THREADS; ++i)
    pthread_join(thread[i], &ret);

  sleep(1);
}