我想尽可能快地从文件读取单个字节到D2应用程序。应用程序需要每字节字节,因此读取较大的数据块不是读取器接口的选项。
为此我在C ++,Java,D2中创建了一些简单的实现:https://github.com/gizmomogwai/performance。
如您所见,我尝试了普通读取,应用程序代码和内存映射文件中的缓冲区。 对于我的用例,内存映射解决方案效果最好,但奇怪的是D2比java慢。我希望D2能够在C ++和Java之间着陆(C ++代码用-O3 -g编译,D2代码用-O -release编译)。
所以请告诉我这里我做错了什么以及如何加快D2的实施。
为了让您了解用例,这里是一个C ++实现:
class StdioFileReader {
private:
FILE* fFile;
static const size_t BUFFER_SIZE = 1024;
unsigned char fBuffer[BUFFER_SIZE];
unsigned char* fBufferPtr;
unsigned char* fBufferEnd;
public:
StdioFileReader(std::string s) : fFile(fopen(s.c_str(), "rb")), fBufferPtr(fBuffer), fBufferEnd(fBuffer) {
assert(fFile);
}
~StdioFileReader() {
fclose(fFile);
}
int read() {
bool finished = fBufferPtr == fBufferEnd;
if (finished) {
finished = fillBuffer();
if (finished) {
return -1;
}
}
return *fBufferPtr++;
}
private:
bool fillBuffer() {
size_t l = fread(fBuffer, 1, BUFFER_SIZE, fFile);
fBufferPtr = fBuffer;
fBufferEnd = fBufferPtr+l;
return l == 0;
}
};
size_t readBytes() {
size_t res = 0;
for (int i=0; i<10; i++) {
StdioFileReader r("/tmp/shop_with_ids.pb");
int read = r.read();
while (read != -1) {
++res;
read = r.read();
}
}
return res;
}
与D中的“相同”解决方案相比要快得多:
struct FileReader {
private FILE* fFile;
private static const BUFFER_SIZE = 8192;
private ubyte fBuffer[BUFFER_SIZE];
private ubyte* fBufferPtr;
private ubyte* fBufferEnd;
public this(string fn) {
fFile = std.c.stdio.fopen("/tmp/shop_with_ids.pb", "rb");
fBufferPtr = fBuffer.ptr;
fBufferEnd = fBuffer.ptr;
}
public int read(ubyte* targetBuffer) {
auto finished = fBufferPtr == fBufferEnd;
if (finished) {
finished = fillBuffer();
if (finished) {
return 0;
}
}
*targetBuffer = *fBufferPtr++;
return 1;
}
private bool fillBuffer() {
fBufferPtr = fBuffer.ptr;
auto l = std.c.stdio.fread(fBufferPtr, 1, BUFFER_SIZE, fFile);
fBufferEnd = fBufferPtr + l;
return l == 0;
}
}
size_t readBytes() {
size_t count = 0;
for (int i=0; i<10; i++) {
auto reader = FileReader("/tmp/shop_with_ids.pb");
ubyte buffer[1];
ubyte* p = buffer.ptr;
auto c = reader.read(p);
while (1 == c) {
++count;
c = reader.read(p);
}
}
return count;
}
答案 0 :(得分:3)
这很可能是因为sfread
。没有人保证它在D中和在C中做同样的事情 - 你很可能完全使用不同的CRT(除非你使用的是Digital Mars C ++编译器?)。
这意味着图书馆可能会做同步等事情,这会减慢速度。你可以知道的唯一方法是强制 D使用与C相同的库,告诉链接器链接到相同的库。
直到你能做到这一点,你才能将苹果与橘子进行比较。如果那是不可能的,那么直接从两个调用操作系统,然后然后比较结果 - 这样就可以保证底层调用对两者都是相同的。
答案 1 :(得分:1)
如果您使用std.stdio
module:
import std.stdio;
struct FileReader {
private File fFile;
private enum BUFFER_SIZE = 8192;//why not enum?
private ubyte[BUFFER_SIZE] fBuffer=void;//avoid (costly) initialization to 0
private ubyte[] buff;
public this(string fn) {
fFile = File("/tmp/shop_with_ids.pb", "rb");
}
/+
public ~this(){//you really should have been doing this if you used std.c.stdio.fopen
//but it's unnecessary for std.stdio's File (it's ref counted)
fFile.close();
}
+/
public int read(out ubyte targetBuffer) {
auto finished = buff.length==0;
if (finished) {
finished = fillBuffer();
if (finished) {
return 0;
}
}
targetBuffer = buff[0];
buff = buff[1..$];
return 1;
}
private bool fillBuffer() {
if(!fFile.isOpen())return false;
buff = fFile.rawRead(fBuffer[]);
return buff.length>0;
}
}
size_t readBytes() {
size_t count = 0;
for (int i=0; i<10; i++) {
auto reader = FileReader("/tmp/shop_with_ids.pb");
ubyte buffer;
auto c = reader.read(buffer);
while (1 == c) {
++count;
c = reader.read(buffer);
}
}
return count;
}
如果你想要真正的速度比较,你应该使用-release -O -inline进行编译(这将关闭调试(主要是数组OOB检查)优化并内联它)(当然也与c ++解决方案类似)< / p>