Can not create insert more than half million rows
--------------------------------------------------
Key: HBASE-2232
URL: https://issues.apache.org/jira/browse/HBASE-2232
Project: Hadoop HBase
Issue Type: Bug
Components: client, io, master, regionserver
Affects Versions: 0.20.3
Environment: Linux
Reporter: mingkeming
The following code, which attempts to insert certain number of rows into a
table.
This is running with hbase 0.20.3 after downloading without changing config.
Does not work if there is more than 500K or so rows .
I can see data being created in $HBASE_HOME/TestTable/xxxx/test_family where
xxxx is a number.
But the data disappear once it get files of size around 16MB.
I guess it is being compacted or moved to somewhere ? But I see nothing in
$HBASE_HOME/TestTable/compaction.dir.
import java.io.*;
import java.util.*;
import org.apache.hadoop.hbase.*;
import org.apache.hadoop.hbase.io.BatchUpdate;
import org.apache.hadoop.hbase.client.Get;
import org.apache.hadoop.hbase.client.HBaseAdmin;
import org.apache.hadoop.hbase.client.HTable;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.ResultScanner;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.util.Bytes;
public class Test{
public static HTable getTable(HBaseConfiguration config, String tableName,
String[] columnFamilies)throws IOException{
HBaseAdmin admin = new HBaseAdmin(config);
createTable(admin, tableName, columnFamilies);
HTable table = new HTable(config, tableName);
table.setAutoFlush(false);
table.setWriteBufferSize(1024*1024*12);
return table;
}
public static boolean createTable(HBaseAdmin admin, String tableName,
String[] columnFamilies)throws IOException{
if(admin.tableExists(tableName))return false;
HTableDescriptor desc = new HTableDescriptor(tableName);
for(String s : columnFamilies){
HColumnDescriptor col = new HColumnDescriptor(s.getBytes());
col.setMaxVersions(1);
desc.addFamily(col);
}
admin.createTable(desc);
return true;
}
public static void test_serial_insert(HTable table, String family, int
count)throws IOException{
byte[] bf = Bytes.toBytes(family);
for(int i = 0; i < count; i++){
int id = i;
byte[] qualifier = Bytes.toBytes(i); // "i"
byte[] key = Bytes.toBytes(i);
byte[] val = Bytes.toBytes(i);
Put put = new Put(key);
put.setWriteToWAL(false);
put.add(bf, qualifier, 0, val);
table.put(put);
if( (i+1) % 1000000 == 0){System.out.println( (i+1)/1000000 + "
M"); }
}
table.flushCommits();
}
public static void count(HTable table)throws IOException{
Scan scan = new Scan();
ResultScanner scanner = table.getScanner(scan);
Result result = null;
int i = 0;
while( (result = scanner.next()) != null ){
byte[] key = result.getRow();
++i;
if(i % 10000 == 0)System.out.println(i);
}
System.out.println("TOTAL========== "+i);
}
public static void removeTable(HBaseAdmin admin, String tableName)throws
IOException{
if(!admin.tableExists(tableName))return;
admin.disableTable(tableName);
admin.deleteTable(tableName);
}
public static void main(String[] args)throws Exception{
int k = 1000;
boolean insert = true;
if(args.length > 0){
if("read".equals(args[0]))insert = false;
else k = Integer.parseInt(args[0]);
}
HBaseConfiguration config = new HBaseConfiguration();
String tableName = "TestTable";
String familyName = "test_family";
HBaseAdmin admin = new HBaseAdmin(config);
removeTable(admin, tableName);
HTable table = getTable(config, tableName, new String[]{familyName});
if(insert)test_serial_insert(table, familyName, k*1000);
count(table);
}
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
