Obtaining actual effective execution time per thread with hyperthreading
CodeGuru Home VC++ / MFC / C++ .NET / C# Visual Basic VB Forums Developer.com
Results 1 to 9 of 9

Thread: Obtaining actual effective execution time per thread with hyperthreading

  1. #1
    Join Date
    Jun 2002
    Location
    Stockholm, Sweden
    Posts
    1,567

    Obtaining actual effective execution time per thread with hyperthreading

    Hi!

    I'm looking for a function like GetThreadTimes, but one that gives correct results in a hyperthreading CPU.

    For instance, if you start 2 threads on a CPU with 1 physical core and 2 logical cores, GetThreadTimes will say that both these threads use 100% CPU.

    However, in reality they only use 50% each. Is there a function that returns correct results, or is there another workaround?

    Regards / Z
    Nobody cares how it works as long as it works

  2. #2
    Join Date
    Nov 2003
    Posts
    1,778

    Re: Obtaining actual effective execution time per thread with hyperthreading

    GetThreadTimes returns elapsed time in kernel + user-space. It doesn't really care what cores they were run on.

    In what way do you see the returned values from GetThreadTimes as being incorrect?

    gg

  3. #3
    Join Date
    Jun 2002
    Location
    Stockholm, Sweden
    Posts
    1,567

    Re: Obtaining actual effective execution time per thread with hyperthreading

    Quote Originally Posted by Codeplug View Post
    In what way do you see the returned values from GetThreadTimes as being incorrect?
    Well, this problem is not only hyperthreading related. The issue is that GetThreadTimes returns the time the thread wanted to run, not the time when it was actually allowed to run by the scheduler (or CPU in case of HT). If I start 10 threads on a single core machine, and let each thread call GetThreadTimes after 10 seconds, it will return 10 seconds for each thread when it IMO should only return ~1 second.
    Nobody cares how it works as long as it works

  4. #4
    Join Date
    Dec 2012
    Location
    England
    Posts
    1,997

    Re: Obtaining actual effective execution time per thread with hyperthreading

    GetThreadTimes returns info about
    creation time of the thread
    exit time of the thread of if the thread has terminated
    time spent in kernal mode
    time spent in user mode

    Which values are you using that you think are not correct when multi-threads are used?
    All advice is offered in good faith only. You are ultimately responsible for effects of your programs and the integrity of the machines they run on.

  5. #5
    Join Date
    Jun 2002
    Location
    Stockholm, Sweden
    Posts
    1,567

    Re: Obtaining actual effective execution time per thread with hyperthreading

    Quote Originally Posted by 2kaud View Post
    Which values are you using that you think are not correct when multi-threads are used?
    Not wrong I guess, I'm only looking for a different function.

    A function that takes the timeslices used by the scheduler into account - so that the value returned will be lower if many threads are competing to run on a single CPU.
    Nobody cares how it works as long as it works

  6. #6
    Join Date
    Nov 2003
    Posts
    1,778

    Re: Obtaining actual effective execution time per thread with hyperthreading

    >> The issue is that GetThreadTimes returns the time the thread wanted to run, not the time when it was actually allowed to run by the scheduler (or CPU in case of HT).
    That's not what I see...
    Code:
    #include <Windows.h>
    #include <iostream>
    using namespace std;
    
    CRITICAL_SECTION cs;
    
    DWORD WINAPI MyThread(void *p)
    {
        int n = reinterpret_cast<int>(p);
    
        if (n)
        {
            EnterCriticalSection(&cs);
            Sleep(10 * 1000);
            LeaveCriticalSection(&cs);
        }//if
        else
        {
            Sleep(1000);
            EnterCriticalSection(&cs); // should block
            LeaveCriticalSection(&cs);
        }//else
    
        return 0;
    }//MyThread
    
    ostream& operator<< (ostream &out, const FILETIME &ft)
    {
        const ULONGLONG &ll = *reinterpret_cast<const ULONGLONG*>(&ft);
        out << ll / 10000.0 << "ms";
        return out;
    }//<<FILETIME
    
    void PrintThreadTimes(HANDLE t, const char *name)
    {
        FILETIME create_t, exit_t, kernel_t, user_t;
        if (!GetThreadTimes(t, &create_t, &exit_t, &kernel_t, &user_t))
        {
            cout << "GetThreadTimes failed, ec = " << GetLastError() << endl;
            return;
        }//if
    
        cout << name << " , kernel=" << kernel_t << ", user=" << user_t << endl;
    }//PrintThreadTimes
    
    int main()
    {
        InitializeCriticalSection(&cs);
    
        HANDLE t[2];
        t[0] = CreateThread(0, 0, &MyThread, reinterpret_cast<void*>(1), 0, 0);
        t[1] = CreateThread(0, 0, &MyThread, reinterpret_cast<void*>(0), 0, 0);
    
        WaitForMultipleObjects(2, t, TRUE, INFINITE);
    
        PrintThreadTimes(t[0], "Thread 1");
        PrintThreadTimes(t[1], "Thread 2");
    
        CloseHandle(t[0]);
        CloseHandle(t[1]);
    
        DeleteCriticalSection(&cs);
    
        return 0;
    }//main
    Output:
    Code:
    Thread 1 , kernel=0ms, user=0ms
    Thread 2 , kernel=0ms, user=0ms
    A whole lot of nothing going on for 10 seconds.

    gg

  7. #7
    Join Date
    Dec 2012
    Location
    England
    Posts
    1,997

    Re: Obtaining actual effective execution time per thread with hyperthreading

    From this code

    Code:
    #include <windows.h>
    #include <process.h>
    #include <ctime>
    #include <iostream>
    #include <iomanip>
    using namespace std;
    
    const int NOTHREADS = 10;	//Number of threads to start
    const int THREADTIME = 10;	//Seconds for each thread to run
    
    UINT __stdcall threadfunc(void* pArgs);
    void PrintTime(FILETIME ft);
    
    int main()
    {
    HANDLE	hdls[NOTHREADS];
    
    UINT	id;
    
    FILETIME create,
    	 exit,
    	 kernel,
    	 user,
    	 process;
    
    	for (int i = 0; i < NOTHREADS; i++) {
    		hdls[i] = (HANDLE)_beginthreadex(NULL, 0, &threadfunc, NULL, 0, &id);
    	}
    
    	cout << "Waiting " << THREADTIME << " seconds for threads..." << endl;
    
    	if (WaitForMultipleObjects(NOTHREADS, hdls, TRUE, THREADTIME * 2000) - WAIT_OBJECT_0 >= NOTHREADS) {
    		cout << "Problem with threads" << endl;
    		return 1;
    	}
    
    	for (int i = 0; i < NOTHREADS; i++) {
    		if (!GetThreadTimes(hdls[i], &create, &exit, &kernel, &user)) {
    			cout << "GetThreadTimes() failed. Error: " << GetLastError() << endl;
    			return 2;
    		}
    
    		cout << "Thread " << i;
    
    		cout << " User: ";
    		PrintTime(user);
    
    		cout << " Kernel: ";
    		PrintTime(kernel);
    
    		cout << " Ran for: ";
    		process.dwHighDateTime = 0;
    		process.dwLowDateTime = exit.dwLowDateTime - create.dwLowDateTime;
    		PrintTime(process);
    
    		cout << endl;
    	}
    
    	return 0;
    }
    
    
    UINT __stdcall threadfunc(void* pArgs)
    {
    double	t = 0;
    
    const time_t	st = time(NULL);
    
    	while (time(NULL) - st < THREADTIME) {
    
    		//Do some work
    		for (int i = 0; i < 1000000; i++) {
    			t += i * 23.0 / 34.0 + i - 3456.0 / i;
    		}
    	}
    	return 0;
    }
    
    void PrintTime(FILETIME ft)
    {
    SYSTEMTIME	systim,
    		local;
    
    	if (!FileTimeToSystemTime(&ft, &systim)) {
    		cout << "File time conversion failed. Error: " << GetLastError() << endl;
    		return;
    	}
    
    	if (!SystemTimeToTzSpecificLocalTime(NULL, &systim, &local)) {
    		cout << "Local time conversion failed. Error: " << GetLastError() << endl;
    		return;
    	}
    
    	cout << setw(2) << setfill(' ') << right << local.wSecond << "." << left << setw(3) << setfill('0') << local.wMilliseconds << " secs";
    	return;
    }
    I get the following result

    Code:
    Waiting 10 seconds for threads...
    Thread 0 User:  3.460 secs Kernel:  0.000 secs Ran for:  9.218 secs
    Thread 1 User:  3.265 secs Kernel:  0.000 secs Ran for:  9.218 secs
    Thread 2 User:  4.265 secs Kernel:  0.000 secs Ran for:  9.218 secs
    Thread 3 User:  4.640 secs Kernel:  0.000 secs Ran for:  9.218 secs
    Thread 4 User:  3.460 secs Kernel:  0.000 secs Ran for:  9.218 secs
    Thread 5 User:  3.640 secs Kernel:  0.000 secs Ran for:  9.218 secs
    Thread 6 User:  4.109 secs Kernel:  0.000 secs Ran for:  9.218 secs
    Thread 7 User:  4.390 secs Kernel:  0.000 secs Ran for:  9.218 secs
    Thread 8 User:  3.937 secs Kernel:  0.150 secs Ran for: 10.140 secs
    Thread 9 User:  4.406 secs Kernel:  0.150 secs Ran for: 10.140 secs
    Where does this differ from you would want/expect?

    This system has 2 physical one-core processors using hyperthreading giving 4 CPUs.
    Last edited by 2kaud; June 13th, 2013 at 04:58 PM.
    All advice is offered in good faith only. You are ultimately responsible for effects of your programs and the integrity of the machines they run on.

  8. #8
    Join Date
    Apr 2000
    Location
    Belgium (Europe)
    Posts
    3,641

    Re: Obtaining actual effective execution time per thread with hyperthreading

    Quote Originally Posted by zerver View Post
    and let each thread call GetThreadTimes after 10 seconds, it will return 10 seconds for each thread when it IMO should only return ~1 second.
    and how ar eyou doing this ?

    if you have a loop that keeps checking the current time until 10 sec passed, then yes, that's 10 seconds of time the CPU was actually busy running your code, even if that code didn't do anything useful. (this is what 2kaud's example in #7 shows).

    if you used ::Sleep(), one of the WaitFor...(), or one of several other ways to make the CPU give up it's timeslice to other threads, then your code should be near 0 for that (as evidenced by codeplug's test in #6)

  9. #9
    Join Date
    Jun 2002
    Location
    Stockholm, Sweden
    Posts
    1,567

    Re: Obtaining actual effective execution time per thread with hyperthreading

    Thanks for the replies. I was getting incorrect results because my threads load the CPU in bursts, e.g. 2ms of work and 10ms of sleep, and GetThreadTimes only has a resolution of 15ms.

    GetThreadTimes works like this: Every 15ms it checks which thread is currently running, and then records the 15ms of execution time as belonging to that thread. This can of course give very skewed results. If a thread happens to be running at that very instant every 15ms and sleeps the rest, it will be recorded as a 100% load.

    The results in CodePlug's post is what I would expect, but since it is hyperthreading it would be more correct if it returned 2 seconds per thread instead of 4. However, I have given up on using GetThreadTimes due to the low resolution.
    Nobody cares how it works as long as it works

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •  


Azure Activities Information Page

Windows Mobile Development Center


Click Here to Expand Forum to Full Width

This is a CodeGuru survey question.


Featured


HTML5 Development Center