Java-使用Byteoutputstream写入大文件

我正在尝试使用以下命令写入大小在 1kb 到 10GB 之间的文件ByteArrayOutputStream但抛出以下异常。我正在使用jdk 6。请建议任何更好的高性能Api。我使用同一个网络盒来读取和写入。

Exception in thread "main" java.lang.OutOfMemoryError:   Requested array size exceeds VM limit
        at java.util.Arrays.copyOf(Unknown Source)
        at java.io.ByteArrayOutputStream.grow(Unknown Source)
        at java.io.ByteArrayOutputStream.ensureCapacity(Unknown Source)
        at java.io.ByteArrayOutputStream.write(Unknown Source)
        at java.io.OutputStream.write(Unknown Source)
        at

Code:

import java.io.BufferedOutputStream;
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;


public class PrepareFile {

    /**
     * @param args
     * @throws Exception 
     */
    public static void main(String[] args) throws Exception {
        // TODO Auto-generated method stub

        new PrepareFile().constructFile("f:\\hello","f:\\output",10000000);

    }

    //Writes a large file of 10 GB using input file data of small size by duplicating
    public void constructFile(String fileName, String outPath, int multiplier) throws Exception {
        BufferedOutputStream fos = null;
        FileInputStream fis = null;

        final File inputFile = new File(fileName);
        String path = inputFile.getParent();
        if (outPath != null && !outPath.isEmpty()) {
            path = outPath;
        }

        fis = new FileInputStream(fileName);

        try {



            // read the transactions in the input file.
            byte[] txnData = new byte[(int) inputFile.length()];
            fis.read(txnData);

            final File outFile = new File(path, "Myfile");
            fos = new BufferedOutputStream(new FileOutputStream(outFile));
            final ByteArrayOutputStream baos = new ByteArrayOutputStream();
            final ByteArrayOutputStream baos1 = new ByteArrayOutputStream();

            //multiplier if input file size is 1 KB and output file is 10 GB, then multiplier value is (1024*1024)

            for (long i = 1; i <= multiplier; i++) {

                if(i >=40000 && i % 40000==0){
                    System.out.println("i value now: "+i);
                    baos.writeTo(fos);
                    baos.reset();
                    //baos.write(txnData);
                }

                // write transactions
                baos.write(txnData);
                baos1.write(txnData); //Exception is coming at this line
            }

            int Padding = myCustomMethod(baos1.toByteArray());

            // write all out data to the output stream
            baos.writeTo(fos);

            baos.flush();
            baos1.flush();
        } catch(Exception e){
            e.printStackTrace();
        }finally {
            fos.close();
            fis.close();
        }

    }

    public int myCustomMethod(byte[] b){

        //Need complete bytes to prepare the file trailer
        return 0;
    }


}

您不能在内存中拥有 2 GB 或更多的缓冲区ByteArrayOutputStream因为大小是 32 位有符号的。

如果您想要性能，我会逐步处理文件并避免如此大的内存副本，因为它们非常昂贵。

顺便说一句，我有一个图书馆编年史字节 https://github.com/OpenHFT/Chronicle-Bytes它支持大于 2 GB 的缓冲区，可以使用本机内存并映射到文件以避免使用堆，并且可以大于主内存。

但是，如果您逐步处理数据，则不需要这么大的缓冲区。

我还建议您使用 Java 8，因为它比 Java 6（十年前发布）执行 64 位操作更好

编辑根据您的代码，无需使用 ByteArrayOutputStream，您可以逐步准备文件。

//Writes a large file of 10 GB using input file data of small size by duplicating
public void constructFile(String fileName, String outFileName, int multiplier) throws IOException {
    byte[] bytes;
    try (FileInputStream fis = new FileInputStream(fileName)) {
        bytes = new byte[fis.available()];
        fis.read(bytes);
    }

    try (FileOutputStream fos = new FileOutputStream(outFileName)) {
        for (int i = 0; i < multiplier; i++) {
            fos.write(bytes);
        }
    }

    // now process the file "outFileName"
    // how depends on what you are trying to do.
    // NOTE: It is entirely possible the file should be processed as it is written.
}