深刻研究BufferedInputStream內幕
[TOC]html
1 概述
最近研究JDK源碼，發現IO體系中的BufferedInputStream，頗有意思，平時對這個類有很多誤解，因而寫下這篇博客，以供學習java
2 BufferedInputStream源碼分析
/**
* 此類繼承FilterInputStream，該類使用了裝飾着設計模式，FilterInputStream的源碼超級簡單
*/
public class BufferedInputStream extends FilterInputStream {
// 默認的buf[]緩存數組大小
private static int DEFAULT_BUFFER_SIZE = 8192;
/**
* The maximum size of array to allocate.
* Some VMs reserve some header words in an array.
* Attempts to allocate larger arrays may result in
* OutOfMemoryError: Requested array size exceeds VM limit
*
* buf[]緩存數組最大值 爲何會 減去8呢？由於一些JVM會數組頭部存一些數據
*/
private static int MAX_BUFFER_SIZE = Integer.MAX_VALUE - 8;
/**
* The internal buffer array where the data is stored. When necessary,
* it may be replaced by another array of
* a different size.
*
* 緩存數組，核心成員變量，全部操做都是圍繞buf[]
*/
protected volatile byte buf[];
/**
* Atomic updater to provide compareAndSet for buf. This is
* necessary because closes can be asynchronous. We use nullness
* of buf[] as primary indicator that this stream is closed. (The
* "in" field is also nulled out on close.)
*
* 多線程相關，確保操做線程安全
*/
private static final
AtomicReferenceFieldUpdater<BufferedInputStream, byte[]> bufUpdater =
AtomicReferenceFieldUpdater.newUpdater
(BufferedInputStream.class, byte[].class, "buf");
/**
* The index one greater than the index of the last valid byte in
* the buffer.
* This value is always
* in the range <code>0</code> through <code>buf.length</code>;
* elements <code>buf[0]</code> through <code>buf[count-1]
* </code>contain buffered input data obtained
* from the underlying input stream.
*
* buf[]數組中，有效數據的總數
*/
protected int count;
/**
* The current position in the buffer. This is the index of the next
* character to be read from the <code>buf</code> array.
* <p>
* This value is always in the range <code>0</code>
* through <code>count</code>. If it is less
* than <code>count</code>, then <code>buf[pos]</code>
* is the next byte to be supplied as input;
* if it is equal to <code>count</code>, then
* the next <code>read</code> or <code>skip</code>
* operation will require more bytes to be
* read from the contained input stream.
*
* @see java.io.BufferedInputStream#buf
*
* buf[]數組中，當前讀取位置
*/
protected int pos;
/**
* The value of the <code>pos</code> field at the time the last
* <code>mark</code> method was called.
* <p>
* This value is always
* in the range <code>-1</code> through <code>pos</code>.
* If there is no marked position in the input
* stream, this field is <code>-1</code>. If
* there is a marked position in the input
* stream, then <code>buf[markpos]</code>
* is the first byte to be supplied as input
* after a <code>reset</code> operation. If
* <code>markpos</code> is not <code>-1</code>,
* then all bytes from positions <code>buf[markpos]</code>
* through <code>buf[pos-1]</code> must remain
* in the buffer array (though they may be
* moved to another place in the buffer array,
* with suitable adjustments to the values
* of <code>count</code>, <code>pos</code>,
* and <code>markpos</code>); they may not
* be discarded unless and until the difference
* between <code>pos</code> and <code>markpos</code>
* exceeds <code>marklimit</code>.
*
* @see java.io.BufferedInputStream#mark(int)
* @see java.io.BufferedInputStream#pos
*
* 最後一次，調用mark方法，標記的位置
*/
protected int markpos = -1;
/**
* The maximum read ahead allowed after a call to the
* <code>mark</code> method before subsequent calls to the
* <code>reset</code> method fail.
* Whenever the difference between <code>pos</code>
* and <code>markpos</code> exceeds <code>marklimit</code>,
* then the mark may be dropped by setting
* <code>markpos</code> to <code>-1</code>.
*
* @see java.io.BufferedInputStream#mark(int)
* @see java.io.BufferedInputStream#reset()
*
* 該變量惟一入口就是mark(int readLimit)，好比調用方法，mark(1024)，那麼後面讀取的數據若是
* 超過了1024字節，那麼這次mark就爲無效標記，子類能夠選擇拋棄該mark標記，從頭開始。不過具體實現
* 跟具體的子類有關，在BufferedInputStream中，會拋棄mark標記，從新將markpos賦值爲-1
*/
protected int marklimit;
/**
* Check to make sure that underlying input stream has not been
* nulled out due to close; if not return it;
*
* 獲取真正的輸入流
*/
private InputStream getInIfOpen() throws IOException {
InputStream input = in;
if (input == null)
throw new IOException("Stream closed");
return input;
}
/**
* Check to make sure that buffer has not been nulled out due to
* close; if not return it;
*
* 獲取緩存數組
*/
private byte[] getBufIfOpen() throws IOException {
byte[] buffer = buf;
if (buffer == null)
throw new IOException("Stream closed");
return buffer;
}
/**
* Creates a <code>BufferedInputStream</code>
* and saves its argument, the input stream
* <code>in</code>, for later use. An internal
* buffer array is created and stored in <code>buf</code>.
*
* @param in the underlying input stream.
*
* 默認緩存數組大小爲8kb
*/
public BufferedInputStream(InputStream in) {
this(in, DEFAULT_BUFFER_SIZE);
}
/**
* Creates a <code>BufferedInputStream</code>
* with the specified buffer size,
* and saves its argument, the input stream
* <code>in</code>, for later use. An internal
* buffer array of length <code>size</code>
* is created and stored in <code>buf</code>.
*
* @param in the underlying input stream.
* @param size the buffer size.
* @exception IllegalArgumentException if {@code size <= 0}.
*/
public BufferedInputStream(InputStream in, int size) {
super(in);
if (size <= 0) {
throw new IllegalArgumentException("Buffer size <= 0");
}
buf = new byte[size];
}
/**
* Fills the buffer with more data, taking into account
* shuffling and other tricks for dealing with marks.
* Assumes that it is being called by a synchronized method.
* This method also assumes that all data has already been read in,
* hence pos > count.
*
* 該方法做用，經過丟棄buf[]數據、增大buf[]數組，以騰出位置，將輸入流中新的數據保存到buf[]緩存數組中
*/
private void fill() throws IOException {
byte[] buffer = getBufIfOpen();
if (markpos < 0)
// 由於沒有mark標記，直接丟棄buf[]數據
pos = 0; /* no mark: throw away the buffer */
else if (pos >= buffer.length) /* no room left in buffer */
if (markpos > 0) { /* can throw away early part of the buffer */
int sz = pos - markpos;
System.arraycopy(buffer, markpos, buffer, 0, sz);
pos = sz;
markpos = 0;
// ！！！往下執行，markpos所有等於0
} else if (buffer.length >= marklimit) {
markpos = -1; /* buffer got too big, invalidate mark */
pos = 0; /* drop buffer contents */
} else if (buffer.length >= MAX_BUFFER_SIZE) {
throw new OutOfMemoryError("Required array size too large");
} else { /* grow buffer */
int nsz = (pos <= MAX_BUFFER_SIZE - pos) ?
pos * 2 : MAX_BUFFER_SIZE;
if (nsz > marklimit)
// buf[]長度不超過marklimit，這樣mark標記始終有效
nsz = marklimit;
byte nbuf[] = new byte[nsz];
System.arraycopy(buffer, 0, nbuf, 0, pos);
if (!bufUpdater.compareAndSet(this, buffer, nbuf)) {
// Can't replace buf if there was an async close.
// Note: This would need to be changed if fill()
// is ever made accessible to multiple threads.
// But for now, the only way CAS can fail is via close.
// assert buf == null;
throw new IOException("Stream closed");
}
buffer = nbuf;
}
count = pos;
// 將輸入流中的數據獨到buf[]數組中
int n = getInIfOpen().read(buffer, pos, buffer.length - pos);
if (n > 0)
count = n + pos;
}
/**
* See
* the general contract of the <code>read</code>
* method of <code>InputStream</code>.
*
* @return the next byte of data, or <code>-1</code> if the end of the
* stream is reached.
* @exception IOException if this input stream has been closed by
* invoking its {@link #close()} method,
* or an I/O error occurs.
* @see java.io.FilterInputStream#in
*/
public synchronized int read() throws IOException {
// 說明當前buf[]數組大小不夠了，須要fill()
if (pos >= count) {
fill();
// 說明沒有讀取到任何數據
if (pos >= count)
return -1;
}
return getBufIfOpen()[pos++] & 0xff;
}
/**
* Read characters into a portion of an array, reading from the underlying
* stream at most once if necessary.
*/
private int read1(byte[] b, int off, int len) throws IOException {
int avail = count - pos;
if (avail <= 0) {
/* If the requested length is at least as large as the buffer, and
if there is no mark/reset activity, do not bother to copy the
bytes into the local buffer. In this way buffered streams will
cascade harmlessly. */
// ！！！這個位置代碼很重要
// ！！！這個位置代碼很重要
// ！！！這個位置代碼很重要
/**
* 當寫入指定數組b的長度大小超過BufferedInputStream中核心緩存數組buf[]的大小而且
* markpos < 0，那麼就直接從數據流中讀取數據給b數組，而不經過buf[]緩存數組，避免buf[]數組急劇增大
*
*/
if (len >= getBufIfOpen().length && markpos < 0) {
return getInIfOpen().read(b, off, len);
}
fill();
avail = count - pos;
if (avail <= 0) return -1;
}
int cnt = (avail < len) ? avail : len;
System.arraycopy(getBufIfOpen(), pos, b, off, cnt);
pos += cnt;
return cnt;
}
/**
* Reads bytes from this byte-input stream into the specified byte array,
* starting at the given offset.
*
* <p> This method implements the general contract of the corresponding
* <code>{@link InputStream#read(byte[], int, int) read}</code> method of
* the <code>{@link InputStream}</code> class. As an additional
* convenience, it attempts to read as many bytes as possible by repeatedly
* invoking the <code>read</code> method of the underlying stream. This
* iterated <code>read</code> continues until one of the following
* conditions becomes true: <ul>
*
* <li> The specified number of bytes have been read,
*
* <li> The <code>read</code> method of the underlying stream returns
* <code>-1</code>, indicating end-of-file, or
*
* <li> The <code>available</code> method of the underlying stream
* returns zero, indicating that further input requests would block.
*
* </ul> If the first <code>read</code> on the underlying stream returns
* <code>-1</code> to indicate end-of-file then this method returns
* <code>-1</code>. Otherwise this method returns the number of bytes
* actually read.
*
* <p> Subclasses of this class are encouraged, but not required, to
* attempt to read as many bytes as possible in the same fashion.
*
* @param b destination buffer.
* @param off offset at which to start storing bytes.
* @param len maximum number of bytes to read.
* @return the number of bytes read, or <code>-1</code> if the end of
* the stream has been reached.
* @exception IOException if this input stream has been closed by
* invoking its {@link #close()} method,
* or an I/O error occurs.
*
* 該方法主要調用read1(byte[] b, int off, int len)
*/
public synchronized int read(byte b[], int off, int len)
throws IOException
{
getBufIfOpen(); // Check for closed stream
if ((off | len | (off + len) | (b.length - (off + len))) < 0) {
throw new IndexOutOfBoundsException();
} else if (len == 0) {
return 0;
}
int n = 0;
for (;;) {
int nread = read1(b, off + n, len - n);
if (nread <= 0)
return (n == 0) ? nread : n;
n += nread;
if (n >= len)
return n;
// if not closed but no bytes available, return
InputStream input = in;
if (input != null && input.available() <= 0)
return n;
}
}
/**
* See the general contract of the <code>skip</code>
* method of <code>InputStream</code>.
*
* @exception IOException if the stream does not support seek,
* or if this input stream has been closed by
* invoking its {@link #close()} method, or an
* I/O error occurs.
*
* 跳過流中指定字節數，感受該方法用處不大，至少到目前爲止，我本人還歷來沒有用過skip方法
*/
public synchronized long skip(long n) throws IOException {
getBufIfOpen(); // Check for closed stream
if (n <= 0) {
return 0;
}
long avail = count - pos;
if (avail <= 0) {
// If no mark position set then don't keep in buffer
if (markpos <0)
return getInIfOpen().skip(n);
// Fill in buffer to save bytes for reset
fill();
avail = count - pos;
if (avail <= 0)
return 0;
}
long skipped = (avail < n) ? avail : n;
pos += skipped;
return skipped;
}
/**
* Returns an estimate of the number of bytes that can be read (or
* skipped over) from this input stream without blocking by the next
* invocation of a method for this input stream. The next invocation might be
* the same thread or another thread. A single read or skip of this
* many bytes will not block, but may read or skip fewer bytes.
* <p>
* This method returns the sum of the number of bytes remaining to be read in
* the buffer (<code>count - pos</code>) and the result of calling the
* {@link java.io.FilterInputStream#in in}.available().
*
* @return an estimate of the number of bytes that can be read (or skipped
* over) from this input stream without blocking.
* @exception IOException if this input stream has been closed by
* invoking its {@link #close()} method,
* or an I/O error occurs.
*
* buf[]數組剩餘字節數+輸入流中剩餘字節數
*/
public synchronized int available() throws IOException {
int n = count - pos;
int avail = getInIfOpen().available();
return n > (Integer.MAX_VALUE - avail)
? Integer.MAX_VALUE
: n + avail;
}
/**
* See the general contract of the <code>mark</code>
* method of <code>InputStream</code>.
*
* @param readlimit the maximum limit of bytes that can be read before
* the mark position becomes invalid.
* @see java.io.BufferedInputStream#reset()
*
* 標記位置，marklimit只有在這裏纔可以被賦值，readlimit表示mark()方法執行後，最多可以從流中
* 讀取的數據，若是超過該字節大小，那麼在fill()的時候，就會認爲此mark()標記無效，從新將
* markpos = -1，pos = 0
*/
public synchronized void mark(int readlimit) {
marklimit = readlimit;
markpos = pos;
}
/**
* See the general contract of the <code>reset</code>
* method of <code>InputStream</code>.
* <p>
* If <code>markpos</code> is <code>-1</code>
* (no mark has been set or the mark has been
* invalidated), an <code>IOException</code>
* is thrown. Otherwise, <code>pos</code> is
* set equal to <code>markpos</code>.
*
* @exception IOException if this stream has not been marked or,
* if the mark has been invalidated, or the stream
* has been closed by invoking its {@link #close()}
* method, or an I/O error occurs.
* @see java.io.BufferedInputStream#mark(int)
*/
public synchronized void reset() throws IOException {
getBufIfOpen(); // Cause exception if closed
if (markpos < 0)
throw new IOException("Resetting to invalid mark");
pos = markpos;
}
/**
* Tests if this input stream supports the <code>mark</code>
* and <code>reset</code> methods. The <code>markSupported</code>
* method of <code>BufferedInputStream</code> returns
* <code>true</code>.
*
* @return a <code>boolean</code> indicating if this stream type supports
* the <code>mark</code> and <code>reset</code> methods.
* @see java.io.InputStream#mark(int)
* @see java.io.InputStream#reset()
*/
public boolean markSupported() {
return true;
}
/**
* Closes this input stream and releases any system resources
* associated with the stream.
* Once the stream has been closed, further read(), available(), reset(),
* or skip() invocations will throw an IOException.
* Closing a previously closed stream has no effect.
*
* @exception IOException if an I/O error occurs.
*/
public void close() throws IOException {
byte[] buffer;
while ( (buffer = buf) != null) {
if (bufUpdater.compareAndSet(this, buffer, null)) {
InputStream input = in;
in = null;
if (input != null)
input.close();
return;
}
// Else retry in case a new buf was CASed in fill()
}
}
}
3 BufferedInputStream在實際場景中，沒有太多用處
網上不少博客，說BufferedInputStream頗有用，能夠一次性從IO中讀入不少數據，而後緩存在buf[]中，這樣就減小了IO消耗，不少博主，甚至給出了一些代碼實操，證實BufferedInputStream確實能夠提升效率，這自己沒有任何問題，可是經我深刻源碼研究事後，卻發現實際場景中，該類使用頻率不多，根本不須要BufferedInputStream設計模式
我將結合代碼，進行更有力的說明：數組
// file文件大小1個G
private static String file = "D:\\StudySoftware\\VMware_virtualbox\\Data_vmware\\VMwareMachine\\kafka_single\\kafka-single-103-da5cf665.vmem";
private static void file() throws IOException{
long beginTime = System.currentTimeMillis();
FileInputStream input = new FileInputStream(file);
byte[] bytes = new byte[1024 * 1];
int read = 0;
while ((read = input.read(bytes, 0, bytes.length)) != -1) {
// 不執行任何操做，僅僅讀取文件
}
long endTime = System.currentTimeMillis();
System.out.println("file: 耗費時間：" + (endTime - beginTime));
}
private static void bufferd() throws IOException{
long beginTime = System.currentTimeMillis();
FileInputStream input = new FileInputStream(file);
BufferedInputStream bufferedInput = new BufferedInputStream(input);
byte[] bytes = new byte[1024 * 1];
int read = 0;
while ((read = bufferedInput.read(bytes, 0, bytes.length)) != -1) {
//不執行任何操做，僅僅讀取文件
}
long endTime = System.currentTimeMillis();
System.out.println("buffered: 耗費時間：" + (endTime - beginTime));
}
注意：緩存
代碼操做的時候，兩個方法不可以對同一個文件進行操做，防止JVM會自動優化，由於第一個方法讀完整個文件，第二個方法再讀的時候，JVM可能保存了部分信息，從而形成測試數據的不許確。而且爲了最大程度保證測試數據的準確性，一次JVM啓動，只測試一個方法安全
結果：多線程
①當 byte[] bytes = new byte[1024 * 1]; 數組大小爲1024less
buffered: 耗費時間：855 file: 耗費時間：3073async
②當 byte[] bytes = new byte[1024 * 2]; 數組大小爲2018ide
buffered: 耗費時間：813 file: 耗費時間：1909
③當 byte[] bytes = new byte[1024 * 3]; 數組大小爲3072
buffered: 耗費時間：1304 file: 耗費時間：1476
④當 byte[] bytes = new byte[1024 * 4]; 數組大小爲4096
buffered: 耗費時間：844 file: 耗費時間：1287
⑤當 byte[] bytes = new byte[1024 * 5]; 數組大小爲5120
buffered: 耗費時間：1343 file: 耗費時間：1061
⑥當 byte[] bytes = new byte[1024 * 6]; 數組大小爲6144
buffered: 耗費時間：1280 file: 耗費時間：985
⑦當 byte[] bytes = new byte[1024 * 7]; 數組大小爲7168
buffered: 耗費時間：1443 file: 耗費時間：851
⑧當 byte[] bytes = new byte[1024 * 8]; 數組大小爲8192
buffered: 耗費時間：774 file: 耗費時間：739
⑨當 byte[] bytes = new byte[1024 * 9]; 數組大小爲9216
buffered: 耗費時間：734 file: 耗費時間：749
⑩當 byte[] bytes = new byte[1024 * 10]; 數組大小爲10240
buffered: 耗費時間：739 file: 耗費時間：697
... ... ...
咱們能夠得出如下重要結論：
<font color="red">當bytes比較小時，使用BufferedInputStream確實讀取文件時要快很多，但是當bytes逐步增大，尤爲是達到8kb的時候，咱們會發現 BufferedInputStream和FileInputStream讀取文件速度差很少了，沒有明顯差別</font>
咱們深刻源碼，便可發現：
所以當咱們把 while ((read = input.read(bytes, 0, bytes.length)) != -1)中的bytes增大時，BufferedInputStream沒有任何做用(<font color="red">除非有mark、reset需求</font>)
有的小夥伴，確定會說，那我將BufferedInputStream中的buf[]大小提升不就好了嗎？
能夠是能夠，可是我將 while ((read = input.read(bytes, 0, bytes.length)) != -1)中的bytes大小增大不就好了？ 說到底都是字節數組，一個是在BufferedInputStream外面，一個是在BufferedInputStream內部，而如今咱們進行流讀取的時候，不少時候是不須要mark、reset操做的，而且咱們設置外部bytes大小一般會比較大，這個時候，徹底能夠不使用BufferedInputStream
4 BufferedInputStream使用場景
①第一種使用場景，就是當咱們須要mark、reset特性時。不過要特別注意，mark、reset的使用，裏面涉及到不少東西，特別是當BufferedInputStream執行fill()操做時
public static void main(String[] args) {
try {
final byte[] src = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20};
final ByteArrayInputStream bis = new ByteArrayInputStream(src);
final BufferedInputStream bufis = new BufferedInputStream(bis, 5);
int data = -1;
int i = 0;
while((data = bufis.read()) != -1) {
if(data == 4) {
bufis.mark(2);
}
if(i++ == 9) {
bufis.reset();
}
System.out.printf("%d", data);
}
} catch(IOException ioex) {
ioex.printStackTrace();
}
}
// 原文連接：https://blog.csdn.net/qq_26971305/article/details/79472696
有興趣的朋友，能夠debug上面的代碼，debug下面的狀況，相應你對BufferedInputStream有更深的理解
if(i++ == 5)
if(i++ == 6)
if(i++ == 7)
if(i++ == 8)
if(i++ == 9)
if(i++ == 10)
... ... ... 時間多的朋友，能夠設置BufferedInputStream中buf[]的大小長度和if(i++ == xx)判斷語句中的值來看看BufferedInputStream類的執行流程
mark、reset特性不可亂用，否則會拋出異常的
public synchronized void reset() throws IOException {
getBufIfOpen(); // Cause exception if closed
if (markpos < 0)
throw new IOException("Resetting to invalid mark");
pos = markpos;
}
②第二種使用場景，當BufferedInputStream配合DataInputStream和ObjectOutputStream使用時
ObjectInputStream input = new ObjectInputStream(new BufferedInputStream(new FileInputStream("E:\\obejct.txt")));
DataInputStream input = new DataInputStream(new BufferedInputStream(new FileInputStream("E:\\obejct.txt")));
當DataXxxStream從管道讀取字節流的時候，是一個一個字節讀取的
而ObjectInputStream底層依賴了DataXxxStream對象
<br /> 參考連接： <https://blog.csdn.net/qq_26971305/article/details/79472696> <br />
<div style="font-size:18px;background-color: #CCFFFF"> 做者：<font color="#551A8B" size="5px">一杯熱咖啡AAA</font> <br /> 出處：<a href="https://www.cnblogs.com/AdaiCoffee/">https://www.cnblogs.com/AdaiCoffee/</a> <br /> 本文以學習、研究和分享爲主，歡迎轉載。若是文中有不妥或者錯誤的地方還望指出，以避免誤人子弟。若是你有更好的想法和意見，能夠留言討論，謝謝！ </div>
原文出處：https://www.cnblogs.com/AdaiCoffee/p/11369699.html
相關文章
- 1. GDB深刻研究
- 2. redis深刻研究
- 3. 深刻研究cleardlg
- 4. git深刻研究
- 5. WWDC 2018：iOS 內存深刻研究
- 6. Object類深刻研究
- 7. 深刻研究java.lang.ThreadLocal類
- 8. Spring 3 MVC深刻研究
- 9. 深刻研究Clang（三） libclang
- 10. 深刻研究Java String
- 更多相關文章...
- • 屏幕分辨率 統計 - 瀏覽器信息
- • Eclipse 內容輔助 - Eclipse 教程
- • 三篇文章瞭解 TiDB 技術內幕——說存儲
- • 三篇文章瞭解 TiDB 技術內幕 —— 說計算
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
最新文章
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. GDB深刻研究
- 2. redis深刻研究
- 3. 深刻研究cleardlg
- 4. git深刻研究
- 5. WWDC 2018：iOS 內存深刻研究
- 6. Object類深刻研究
- 7. 深刻研究java.lang.ThreadLocal類
- 8. Spring 3 MVC深刻研究
- 9. 深刻研究Clang（三） libclang
- 10. 深刻研究Java String