关于lucene的RAMDirectory和FSDirectory的性能问题的困惑
关于lucene的RAMDirectory和FSDirectory的性能问题的困惑
并附了测试用例
我根据测试用例去实际测试了一下，结果是相反的
这让我很困惑，内存没道理比文件系统慢啊。。
附上执行结果:
RAMDirectory Time: 500 ms
FSDirectory Time: 266 ms
以下是我的代码（基本照搬书中例子，只更改了for循环写法和使用了2.9的推荐方法取代了老版本的方法）
import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Collection;
import org.apache.lucene.analysis.SimpleAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.RAMDirectory;
import junit.framework.TestCase;
/**
* 测试FSDirectory和RAMDirectory之间的性能差异
* 理论上来说,后者应大于前者,但是实际测试值相反,why? lucifer 2010-5-10
* @author lucifer
*
*/
public class FSversusRAMDirectoryTest extends TestCase
{
private Directory fsDir;
private Directory ramDir;
private Collection<String> docs = loadDocuments(3000,5);
protected void setUp() throws Exception
{
String fsIndexDir = System.getProperty("java.io.tmpdir","tmp")+File.separator+"fs-index";
ramDir = new RAMDirectory();
fsDir = FSDirectory.open(new File(fsIndexDir));
}
public void testTiming() throws IOException
{
long ramTiming = timeIndexWriter(ramDir);
long fsTiming = timeIndexWriter(fsDir);
// assertTrue(fsTiming>ramTiming);
System.out.println("RAMDirectory Time: "+ ramTiming +" ms");
System.out.println("FSDirectory Time: "+ fsTiming +" ms");
}
private long timeIndexWriter(Directory dir)throws IOException
{
long start = System.currentTimeMillis();
addDocuments(dir);
long stop = System.currentTimeMillis();
return (stop - start);
}
private void addDocuments(Directory dir)throws IOException
{
/**
* SimpleAnalyzer:把所有字符过滤成小写
* 把参数设为false时,使用RAMDirectory出错,报文件找不到
*/
IndexWriter writer = new IndexWriter(dir,new SimpleAnalyzer(),true,IndexWriter.MaxFieldLength.UNLIMITED);
/**
* 以下参数影响FSDirectory性能
* MergeFactor的值不能小于2
* MaxMergeDocs的值可以设置的比MergeFactor小,未见异常抛出
*/
writer.setMergeFactor(10);
writer.setMaxMergeDocs(10000);
for(Object obj:docs)
{
Document doc = new Document();
String word = (String)obj;
doc.add(new Field("keyword",word,Field.Store.YES,Field.Index.NOT_ANALYZED));
doc.add(new Field("unindexed",word,Field.Store.YES,Field.Index.NO));
doc.add(new Field("unstored",word,Field.Store.NO,Field.Index.NOT_ANALYZED));
doc.add(new Field("text",word,Field.Store.NO,Field.Index.ANALYZED));
writer.addDocument(doc);
}
writer.optimize();
writer.close();
}
private Collection<String> loadDocuments(int numDocs,int wordsPerDoc)
{
Collection<String> docs = new ArrayList<String>(numDocs);
for(int i=0;i<numDocs;i++)
{
StringBuffer doc = new StringBuffer(wordsPerDoc);
for(int j=0;j<wordsPerDoc;j++)
doc.append("bibamus ");
docs.add(doc.toString());
}
return docs;
}
}
（转自：http://www.iteye.com/problems/42016）
