之前要处理一个25W行的文件,用shell,慢的简直不能忍,即使优化了把那种通过管道启动新程序的脚本,如echo 'aaa' |grep xxx这种去掉,也用了7分钟,

于是乎,我又拿起了2年前用的perl重写一份,耗时0.6秒 !!!

real    0m0.647s
user    0m0.560s
sys    0m0.032s

本着我是c++爱好者的兴趣,我用c++重写了一份,发现还是0.5-0.6秒,怎么c++也没比perl快多少嘛

改编译参数,加了个-O3,发现速度没多少变化

real    0m0.560s
user    0m0.236s
sys        0m0.276s

我想,肯定是我写的有问题

看到sys 用了0.27,比perl的0.03多很多,我就猜测可能是io方面没有写好

后来,我发现我写的程序有诸如cout<< "xxx"<<endl;获取此处有问题

于是乎我改成了cout<<"xxx\n";

效率马上提高了

real    0m0.205s
user    0m0.160s
sys    0m0.024s

以上

	my $PREV_TIME="";
	my $SUM=0;
	my $INIT=1;
	my $line;
	my $TIME;
	my $TPS;
	my $MSG;
	while(<>)
	{
	  # Remove the line break
	  chomp; 
	  $line=$_;
	  # Skip blank line
	  if (!$line){next;} 
	  $TIME=substr($line,8);
	  $TPS=substr($line,10,99);
	  # Handle TPS Log is Enabled/Disabled
	  $MSG=substr($TPS,10);
	  if ( $MSG eq "TPS Log is" )
	  {
		print "$line\n";
		next;
	  } 
	  $TPS=substr($TPS,rindex($TPS,"TPS")-1);
	  if ($INIT==1)
	  {
		$PREV_TIME=$TIME;
		$INIT=0;
	  }
	  if ($PREV_TIME eq $TIME)
	  {
		$SUM=$SUM+$TPS;
	  }else
	  {
		print "$PREV_TIME  $SUM TPS\n";
		$SUM=$TPS;
	  }
	  $PREV_TIME=$TIME;
	}
	print "$PREV_TIME  $SUM TPS\n";

	string PREV_TIME;
	int SUM = 0;
	int INIT = 1;
	string line;
	string TIME;
	string TPS;
	fstream ifs;
	string MSG;
	int tps_number = 0;
	ifs.open("/var/tmp/sorted.tmp");
	while (!std::getline(ifs,line).eof())
	{
		if (line == "")
			continue;
		TIME = line.substr(0,8);
		TPS = line.substr(10,99);
		MSG = TPS.substr(0,10);
		if (MSG == "TPS Log is")
		{
			cout << line << endl;
			continue;
		}
		int index = TPS.rfind("TPS");
		tps_number = atoi(TPS.substr(0,index - 1).c_str());
		if (INIT == 1)
		{
			PREV_TIME = TIME;
			INIT = 0;
		}
		if (PREV_TIME == TIME)
		{
			SUM = SUM + tps_number;
		}
		else
		{
			cout << PREV_TIME << "  " << SUM << " " << "TPS\n";
			SUM = tps_number;
		}
		PREV_TIME = TIME;
	}
	cout << PREV_TIME << "  " << SUM << " " << "TPS\n";