我试图在map reduce上运行一个weka分类器，加载整个arff文件（甚至200mb）会导致堆空间错误，所以我想将arff文件分割成块，但问题是它必须维护块信息，即每个块中的arff属性信息，以便在每个Map器中运行分类器。这是我试图分割数据但效率不高的代码，

List<InputSplit> splits = new ArrayList<InputSplit>();
        for (FileStatus file: listStatus(job)) {
            Path path = file.getPath();
            FileSystem fs = path.getFileSystem(job.getConfiguration());

            //number of bytes in this file
            long length = file.getLen();
            BlockLocation[] blkLocations = fs.getFileBlockLocations(file, 0, length);

            // make sure this is actually a valid file
            if(length != 0) {
                // set the number of splits to make. NOTE: the value can be changed to anything
                int count = job.getConfiguration().getInt("Run-num.splits",1);
                for(int t = 0; t < count; t++) {
                    //split the file and add each chunk to the list
                    splits.add(new FileSplit(path, 0, length, blkLocations[0].getHosts())); 
                }
            }
            else {
                // Create empty array for zero length files
                splits.add(new FileSplit(path, 0, length, new String[0]));
            }
        }
        return splits;