MySQL分布式集群-6.Mycat数据切分

1.示例

mysql> insert into employee(id, name, sharding_id) values (2,'hello',10010);
Query OK, 1 row affected (0.01 sec)

mysql> explain insert into employee(id, name, sharding_id) values (2,'hello',10010);
+-----------+---------------------------------------------------------------------------+
| DATA_NODE | SQL                                                                       |
+-----------+---------------------------------------------------------------------------+
| dn2       | INSERT INTO employee (id, name, sharding_id) VALUES (2, 'hello', '10010') |
+-----------+---------------------------------------------------------------------------+
1 row in set (0.00 sec)

mysql> select * from employee;
+----+-------+-------------+
| id | name  | sharding_id |
+----+-------+-------------+
|  1 | hello |       10000 |
|  2 | hello |       10010 |
+----+-------+-------------+
2 rows in set (0.00 sec)

2.数据切分规则

<tableRule name="sharding-by-intfile">
       <rule>
            <columns>sharding_id</columns>
            <algorithm>hash-int</algorithm>
       </rule>
</tableRule>

hash-int 用到mycat源码中的PartitionByFileMap通过读取partition-hash-int.txt的内容来生成Map<Object, Integer>的键值对



自定义规则可以通过：
public class PartitionByCustomMap extends AbstractPartitionAlgorithm implements RuleAlgorithm{
    实现自定义规则
}



默认定义规则汇总
<mycat:rule xmlns:mycat="http://io.mycat/">
    <tableRule name="rule1">
        <rule>
            <columns>id</columns>
            <algorithm>func1</algorithm>
        </rule>
    </tableRule>

    <tableRule name="rule2">
        <rule>
            <columns>user_id</columns>
            <algorithm>func1</algorithm>
        </rule>
    </tableRule>

    <tableRule name="sharding-by-intfile">
        <rule>
            <columns>sharding_id</columns>
            <algorithm>hash-int</algorithm>
        </rule>
    </tableRule>
    <tableRule name="auto-sharding-long">
        <rule>
            <columns>id</columns>
            <algorithm>rang-long</algorithm>
        </rule>
    </tableRule>
    <tableRule name="mod-long">
        <rule>
            <columns>id</columns>
            <algorithm>mod-long</algorithm>
        </rule>
    </tableRule>
    <tableRule name="sharding-by-murmur">
        <rule>
            <columns>id</columns>
            <algorithm>murmur</algorithm>
        </rule>
    </tableRule>
    <tableRule name="crc32slot">
        <rule>
            <columns>id</columns>
            <algorithm>crc32slot</algorithm>
        </rule>
    </tableRule>
    <tableRule name="sharding-by-month">
        <rule>
            <columns>create_time</columns>
            <algorithm>partbymonth</algorithm>
        </rule>
    </tableRule>
    <tableRule name="latest-month-calldate">
        <rule>
            <columns>calldate</columns>
            <algorithm>latestMonth</algorithm>
        </rule>
    </tableRule>
    
    <tableRule name="auto-sharding-rang-mod">
        <rule>
            <columns>id</columns>
            <algorithm>rang-mod</algorithm>
        </rule>
    </tableRule>
    
    <tableRule name="jch">
        <rule>
            <columns>id</columns>
            <algorithm>jump-consistent-hash</algorithm>
        </rule>
    </tableRule>

    <function name="murmur"
        class="io.mycat.route.function.PartitionByMurmurHash">
        <property name="seed">0</property><!-- 默认是0 -->
        <property name="count">2</property><!-- 要分片的数据库节点数量，必须指定，否则没法分片 -->
        <property name="virtualBucketTimes">160</property><!-- 一个实际的数据库节点被映射为这么多虚拟节点，默认是160倍，也就是虚拟节点数是物理节点数的160倍 -->
        <!-- <property name="weightMapFile">weightMapFile</property> 节点的权重，没有指定权重的节点默认是1。以properties文件的格式填写，以从0开始到count-1的整数值也就是节点索引为key，以节点权重值为值。所有权重值必须是正整数，否则以1代替 -->
        <!-- <property name="bucketMapPath">/etc/mycat/bucketMapPath</property> 
            用于测试时观察各物理节点与虚拟节点的分布情况，如果指定了这个属性，会把虚拟节点的murmur hash值与物理节点的映射按行输出到这个文件，没有默认值，如果不指定，就不会输出任何东西 -->
    </function>

    <function name="crc32slot"
              class="io.mycat.route.function.PartitionByCRC32PreSlot">
    </function>
    <function name="hash-int"
        class="io.mycat.route.function.PartitionByFileMap">
        <property name="mapFile">partition-hash-int.txt</property>
    </function>
    <function name="rang-long"
        class="io.mycat.route.function.AutoPartitionByLong">
        <property name="mapFile">autopartition-long.txt</property>
    </function>
    <function name="mod-long" class="io.mycat.route.function.PartitionByMod">
        <!-- how many data nodes -->
        <property name="count">3</property>
    </function>

    <function name="func1" class="io.mycat.route.function.PartitionByLong">
        <property name="partitionCount">8</property>
        <property name="partitionLength">128</property>
    </function>
    <function name="latestMonth"
        class="io.mycat.route.function.LatestMonthPartion">
        <property name="splitOneDay">24</property>
    </function>
    <function name="partbymonth"
        class="io.mycat.route.function.PartitionByMonth">
        <property name="dateFormat">yyyy-MM-dd</property>
        <property name="sBeginDate">2015-01-01</property>
    </function>
    
    <function name="rang-mod" class="io.mycat.route.function.PartitionByRangeMod">
            <property name="mapFile">partition-range-mod.txt</property>
    </function>
    
    <function name="jump-consistent-hash" class="io.mycat.route.function.PartitionByJumpConsistentHash">
        <property name="totalBuckets">3</property>
    </function>
</mycat:rule>