CODEWITHSUNDEEP
c++runtime
Baykal
Baykal

Reputation: 569

C++ Code is running slower over time

I have a long C++ program consisting of thousands of lines of codes, several classes, functions etc. The program basically reads info from an input file, runs an algorithm, and writes the results in output files.

Today I realized that run time of the program drastically changes from time to time. So I do a small test by restarting my computer, closing every other thing possible, and running the code 5 times in a row using the same input file. The run times are 50, 80, 130, 180, 190 seconds, respectively.

My first guess in this situation is the non-deleted dynamic memories. But I have been using dynamic arrays just twice in the whole code, and I am sure I delete those arrays.

Do you guys have any explanation for this? I am using Visual Studio 2010 on Windows 7 computer.

Upvotes: 3

Views: 4308

Answers (2)

Carl
Carl

Reputation: 44448

Your code runs in an environment, which includes the state of the operating system, disk, network, time, memory, other processes launched, etc.

Executing the same code in the same environment will give the same result, every time.

Now, you're getting different results (execution times). If you're running the same executable repeatedly, then something is changing in the surrounding environment.

Now, the most obvious question is : Is your code causing a change to the outside environment? A simple example would be: It reads in a file, changes the data and writes it back out to the same file.

You know your code. Just use this approach to isolate any effects your code may be having on its environment and you'll find the reason.

Upvotes: 2

racingsnail
racingsnail

Reputation: 153

Beware running programs from within visual studio debugger as the LFH (low fragmentation heap) memory allocator is disabled in this case. Try the software from outside of VS.

I have seen cases where tasks would take seconds to complete normally take hours to complete just by running from within visual studio.

Above all if you still don't know what is going on divide and conquer. Instrument the app to see runtimes of subsystems or just place debug timers in various areas to see where execution time is changing drastically and drill down from there. If it is a memory allocator issue you will normally see large runtimes while freeing the arrays.

Upvotes: 3

Related Questions