Some experiment:
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <Windows.h>
void generateFiles(int n) {
char fileName[32];
char fileStr[1032];
for (int i=0;i<n;i++) {
sprintf( fileName, "c:\\t\\%i.txt", i );
FILE * f = fopen( fileName, "w" );
for (int j=0;j<256;j++) {
int lineLen = rand() % 1024;
memset(fileStr, 'X', lineLen );
fileStr[lineLen] = 0x0D;
fileStr[lineLen+1] = 0x0A;
fileStr[lineLen+2] = 0x00;
fwrite( fileStr, 1, lineLen+2, f );
}
fclose(f);
}
}
void readFiles(int n) {
char fileName[32];
for (int i=0;i<n;i++) {
sprintf( fileName, "c:\\t\\%i.txt", i );
FILE * f = fopen( fileName, "r" );
fseek(f, 0L, SEEK_END);
int size = ftell(f);
fseek(f, 0L, SEEK_SET);
char * data = (char*)malloc(size);
fread(data, size, 1, f);
free(data);
fclose(f);
}
}
DWORD WINAPI readInThread( LPVOID lpParam )
{
int * number = (int *)lpParam;
char fileName[32];
sprintf( fileName, "c:\\t\\%i.txt", *number );
FILE * f = fopen( fileName, "r" );
fseek(f, 0L, SEEK_END);
int size = ftell(f);
fseek(f, 0L, SEEK_SET);
char * data = (char*)malloc(size);
fread(data, size, 1, f);
free(data);
fclose(f);
return 0;
}
int main(int argc, char ** argv) {
long t1 = GetTickCount();
generateFiles(256);
printf("Write: %li ms\n", GetTickCount() - t1 );
t1 = GetTickCount();
readFiles(256);
printf("Read: %li ms\n", GetTickCount() - t1 );
t1 = GetTickCount();
const int MAX_THREADS = 256;
int pDataArray[MAX_THREADS];
DWORD dwThreadIdArray[MAX_THREADS];
HANDLE hThreadArray[MAX_THREADS];
for( int i=0; i<MAX_THREADS; i++ )
{
pDataArray[i] = (int) HeapAlloc(GetProcessHeap(), HEAP_ZERO_MEMORY,
sizeof(int));
pDataArray[i] = i;
hThreadArray[i] = CreateThread(
NULL,
0,
readInThread,
&pDataArray[i],
0,
&dwThreadIdArray[i]);
}
WaitForMultipleObjects(MAX_THREADS, hThreadArray, TRUE, INFINITE);
printf("Read (threaded): %li ms\n", GetTickCount() - t1 );
}
first function just ugly thing to make a test dataset ( I know it can be done much better, but I honestly have no time )
1st experiment - sequential read
2nd experiment - read all in parallel
results:
256 files:
Write: 250 ms
Read: 140 ms
Read (threaded): 78 ms
1024 files:
Write: 1250 ms
Read: 547 ms
Read (threaded): 843 ms
I think second attempt clearly shows that on a long run 'dumb' thread creation just makes things even worse. Of course it needs improvements in a sense of preallocated workers, some thread pool etc, but I think with such fast operation as reading 100-200k from disk there is no really benefit of moving this functionality into thread. I have no time to write more 'clever' solution, but I have my doubts that it will be much faster because you will have to add system calls for mutexes etc...
going extreme you could think of preallocating memory pools etc.. but as being mentioned before code your posted just wrong.. it's a matter of milliseconds, but for sure not seconds
800 files (20 chars per line, 256 lines)
Write: 250 ms
Read: 63 ms
Read (threaded): 500 ms
Conclusion:
ANSWER IS:
Your reading code is wrong, you reading files so slow that there is a significant increase in speed then you make tasks runs in parallel. In the code above reading is actually faster then an expenses to spawn a thread