Cassandra Bulk Loader

Question

public class SimpleLoadExample 
{ 
    /** Default output directory */ 
    public static final String DEFAULT_OUTPUT_DIR = "/home/tamil/bdata"; 

    public static final SimpleDateFormat DATE_FORMAT = new SimpleDateFormat("yyyy-MM-dd"); 

    /** Keyspace name */ 
    public static final String KEYSPACE = "test"; 
    /** Table name */ 
    public static final String TABLE = "counter"; 

    public static final String SCHEMA = "CREATE TABLE test.counter (" + 
      "id varchar PRIMARY KEY," + 
      "count counter" + 
      ")"; 

    public static void main(String[] args) throws InvalidRequestException, IOException { 
     Config.setClientMode(true); 
     File outputDir = new File(DEFAULT_OUTPUT_DIR + File.separator + KEYSPACE + File.separator + TABLE); 
     if (!outputDir.exists() && !outputDir.mkdirs()) 
     { 
      throw new RuntimeException("Cannot create output directory: " + outputDir); 
     } 
     SSTableSimpleUnsortedWriter writer = new SSTableSimpleUnsortedWriter(outputDir, new Murmur3Partitioner(), KEYSPACE, TABLE, CounterColumnType.instance, null, 1000); 
     writer.newRow(bytes("2")); 
     writer.addCounterColumn(bytes("count"), 10L); 
     try 
     { 
      writer.close(); 
     } 
     catch (IOException ignore) { 
      System.out.println(ignore); 
     } 
    } 
} 

我试过上面这个简单的例子来生成sstables。但是

ERROR 21:05:14,287 Missing component: /home/tamil/bdata/test/counter/test-counter-jb-1-Summary.db 
    [ 
    {"key": "32","columns": [Exception in thread "main" java.lang.IllegalArgumentException 
     at java.nio.Buffer.limit(Buffer.java:267) 
     at org.apache.cassandra.utils.ByteBufferUtil.readBytes(ByteBufferUtil.java:587) 
     at org.apache.cassandra.utils.ByteBufferUtil.readBytesWithShortLength(ByteBufferUtil.java:596) 
     at org.apache.cassandra.db.marshal.AbstractCompositeType.getString(AbstractCompositeType.java:203) 
     at org.apache.cassandra.tools.SSTableExport.serializeColumn(SSTableExport.java:183) 
     at org.apache.cassandra.tools.SSTableExport.serializeAtom(SSTableExport.java:152) 
     at org.apache.cassandra.tools.SSTableExport.serializeAtoms(SSTableExport.java:140) 
     at org.apache.cassandra.tools.SSTableExport.serializeRow(SSTableExport.java:238) 
     at org.apache.cassandra.tools.SSTableExport.serializeRow(SSTableExport.java:223) 
     at org.apache.cassandra.tools.SSTableExport.export(SSTableExport.java:374) 
     at org.apache.cassandra.tools.SSTableExport.export(SSTableExport.java:399) 
     at org.apache.cassandra.tools.SSTableExport.export(SSTableExport.java:411) 
     at org.apache.cassandra.tools.SSTableExport.main(SSTableExport.java:494) 

有人可以指我到哪里我会出错吗？

This是我在网上找到的。但我认为我的比较器[同时使用UTF8Type和CounterColumn]非常好。还有什么可能导致这个缓冲区问题？

Answer 1

最后，下面的代码工作。发布它为人们引用遵循

SSTableSimpleUnsortedWriter writer = new SSTableSimpleUnsortedWriter(outputDir, new Murmur3Partitioner(), KEYSPACE, TABLE, CompositeType.getInstance(UTF8Type.instance), null, 1000); 
writer.newRow(bytes("2")); 
ByteBuffer name = CompositeType.getInstance(UTF8Type.instance).builder().add(bytes("count")).build(); 
writer.addCounterColumn(name, 10L); 

更妙的是，如果你能做到这一点

// SCHEMA is CQL Create table Query String and KEYSPACE is string keyspace name 
CFMetaData cfm = CFMetaData.compile(SCHEMA, KEYSPACE); 
SSTableSimpleUnsortedWriter writer = new SSTableSimpleUnsortedWriter(outputDir, cfm, new Murmur3Partitioner(), defaultSize);