|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
|
/**
* coprocessor
* 当用户在使用get命令从表中取特定的row时，就会触发这个自定义的observer coprocessor
* 触发条件是用户使用get指定的rowkey与程序中指定的FIXED_ROW一致为@@@GETTIME@@@时
* 触发后的操作是程序会在服务端生成一个keyvalue实例，并将这个实例返回给客户端。这个kv实例是以
* @@@GETTIME@@@为rowkey，列族和列标识符均为@@@GETTIME@@@，列值为服务器端的时间
*/
package org.apache.hbase.kora.coprocessor;
import java.io.IOException;
import java.util.List;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.hadoop.hbase.KeyValue;
import org.apache.hadoop.hbase.client.Get;
import org.apache.hadoop.hbase.coprocessor.BaseRegionObserver;
import org.apache.hadoop.hbase.coprocessor.ObserverContext;
import org.apache.hadoop.hbase.coprocessor.RegionCoprocessorEnvironment;
import org.apache.hadoop.hbase.regionserver.HRegion;
import org.apache.hadoop.hbase.util.Bytes;
public
class
RegionObserverExample
extends
BaseRegionObserver {
public
static
final
Log LOG = LogFactory.getLog(HRegion.
class
);
public
static
final
byte[] FIXED_ROW = Bytes.toBytes(
"@@@GETTIME@@@"
);
@Override
public
void preGet(ObserverContext<RegionCoprocessorEnvironment> c,
Get get, List<KeyValue> result) throws IOException {
LOG.debug(
"Got preGet for row: "
+ Bytes.toStringBinary(get.getRow()));
if
(Bytes.equals(get.getRow(), FIXED_ROW)) {
KeyValue kv =
new
KeyValue(get.getRow(), FIXED_ROW, FIXED_ROW,
Bytes.toBytes(System.currentTimeMillis()));
LOG.debug(
"Had a match, adding fake kv: "
+ kv);
result.add(kv);
}
}
}
|
|
1
2
3
4
5
6
7
8
9
|
## 已经上传到hadoop1上
[grid@hadoop1 ~]$ ls /
var
/ftp/pub/RegionObserverExample.jar
/
var
/ftp/pub/RegionObserverExample.jar
## 由于是完全分布式系统，为了方便管理，我们将jar包存放到hadoop hdfs的根目录下的jars目录下
[grid@hadoop1 ~]$ hdfs dfs -put /
var
/ftp/pub/RegionObserverExample.jar /jars
## OK，验证已经上传成功
[grid@hadoop1 ~]$ hdfs dfs -ls /jars
Found 1 items
-rw-r--r-- 4 grid supergroup 3884 2014-11-15 04:46 /jars/RegionObserverExample.jar
|
|
1
2
3
4
5
6
7
8
9
|
## 首先修改hbase-env.sh中的这行，将存放Coprocessor jar文件的目录添加到Hbase的classpath中
export HBASE_CLASSPATH=hdfs:
//hadoop1:8020/jars
## 然后修改hbase-site.xml文件，添加一个选项
<!-- 这里要注意value中一定要写完整的类名(即把包名写全)，否则报ClassNotFound错 -->
<property>
<name>hbase.coprocessor.region.classes</name>
<value>org.apache.hbase.kora.coprocessor.RegionObserverExample</value>
</property>
|
|
1
2
3
4
5
6
7
8
9
10
|
## 使用get命令从kora表中取rowkey为@@@GETTIME@@@的行
hbase(main):014:0> get
'kora'
,
'@@@GETTIME@@@'
COLUMN CELL
@@@GETTIME@@@:@@@GETTIM timestamp=9223372036854775807, value=\x00\x00\x01I\xB0@\xA0\xE0
E@@@
1 row(s) in 0.0420 seconds
## 将列值转化为uninx 时间
hbase(main):015:0> Time.at(Bytes.toLong(
"\x00\x00\x01I\xB0\x0BZ\x0B"
.to_java_bytes)/ 1000)
=> Sat Nov 15 04:42:54 +0800 2014
## 从上面的测试中看出，我们自定义的Coprocessor已经成功的部署到分布式系统中了。
|
|
1
2
3
4
5
6
7
8
9
10
11
12
13
|
## 看hbase-env.sh的配置
[grid@hadoop1 ~]$ grep
"jars"
/opt/hbase-0.98.4-hadoop2/conf/hbase-env.sh
export HBASE_CLASSPATH=hdfs:
//hadoop1:8020/jars
## 注释掉hbase-site.xml中的Coprocessor的配置
[grid@hadoop1 ~]$ tail -7 /opt/hbase-0.98.4-hadoop2/conf/hbase-site.xml
<!--
<property>
<name>hbase.coprocessor.region.classes</name>
<value>org.apache.hbase.kora.coprocessor.RegionObserverExample</value>
</property>
-->
</configuration>
|
|
1
2
3
4
5
6
7
8
9
10
11
|
## 格式：[coprocessor jar file location] |
class
name | [priority] | [arguments]
## 列子：hbase> alter
't1'
,
##
'coprocessor'
=>
'hdfs:///foo.jar|com.foo.FooRegionObserver|1001|arg1=1,arg2=2'
## 由于一定设置了classpath，所以可以忽略jar file location，如下：
hbase(main):101:0> alter
'kora'
,
hbase(main):102:0*
'coprocessor'
=>
'|org.apache.hbase.kora.coprocessor.RegionObserverExample|'
Updating all regions with the
new
schema...
0/1 regions updated.
1/1 regions updated.
Done.
0 row(s) in 2.5670 seconds
|
|
1
2
3
4
5
6
7
|
hbase(main):103:0> describe
'kora'
DESCRIPTION ENABLED
'kora'
, {TABLE_ATTRIBUTES => {coprocessor
$1
=> '|org.apache.hbase.kora.coprocessor.RegionObserverExa true
mple|
'}, {NAME => '
project
', DATA_BLOCK_ENCODING => '
NONE
', BLOOMFILTER => '
ROW', REPLICATION_SCOPE
=>
'0'
, VERSIONS =>
'1'
, COMPRESSION =>
'NONE'
, MIN_VERSIONS =>
'0'
, TTL =>
'FOREVER'
, KEEP_DELETED_
CELLS =>
'false'
, BLOCKSIZE =>
'65536'
, IN_MEMORY =>
'false'
, BLOCKCACHE =>
'true'
}
1 row(s) in 0.0580 seconds
|
|
1
2
3
4
5
6
7
8
9
|
## kora表，指定了Coprocessor
hbase(main):104:0> get
'kora'
,
'@@@GETTIME@@@'
COLUMN CELL
@@@GETTIME@@@:@@@GETTIME@@@ timestamp=9223372036854775807, value=\x00\x00\x01I\xB0\x985W
1 row(s) in 0.0360 seconds
## testtable，没有指定Coprocessor
hbase(main):105:0> get
'testtable'
,
'@@@GETTIME@@@'
COLUMN CELL
0 row(s) in 0.0180 seconds
|
|
1
|
'coprocessor'
=>
'|org.apache.hbase.kora.coprocessor.RegionObserverExample|USER|'
|
