經常使用的oracle、mySQL數據庫都是面向行儲存的,而hbase是面向列儲存的數據庫,儲存自己具備水平延展性。html
hbase有兩個主要概念:Row key和Column Famliyjava
Column Famliy又稱爲「列族」,每個Column Family均可以根據「限定符」有多個column。數據庫
例如:有一個User表,傳統的數據庫中,表的列是固定的,name,age,sex等屬性,User的屬性不能動態增長。apache
但採用列儲存系統,好比Hbase,那麼咱們能夠定義User表,而後定義info 列族,User的數據能夠分爲:info:name = zhangsan,info:age=30,info:sex=male等,併發
若是後來你又想增長另外的屬性,這樣很方便只須要info:newProperty就能夠了。oracle
又好比儲存用戶信息,信息並不必定完整,而null的單元會形成空間浪費,在Hbase裏,若是每個column 單元沒有值,那麼是不佔用空間的。分佈式
採用Hbase的這種方式,還有一個很是重要的好處就是會自動切分,當表中的數據超過某一個閥值之後,Hbase會自動爲咱們切分數據,這樣的話,查詢就具備了伸縮性,而再加上Hbase的弱事務性的特性,對Hbase的寫入操做也將變得很是快。函數
另外一個主要概念:Row key,其實能夠理解row key 是某一行的主鍵,可是由於Hbase不支持條件查詢以及Order by等查詢,所以Row key的設計就要根據你係統的查詢需求來設計了。高併發
例如咱們查詢某人信息,所以咱們的Row key能夠有如下三個部分構成<userId><timestamp><feedId>,這樣以來當咱們要查詢某我的的最進的Feed就能夠指定Start Rowkey爲<userId><0><0>,End Rowkey爲<userId><Long.MAX_VALUE><Long.MAX_VALUE>來查詢了,同時由於Hbase中的記錄是按照rowkey來排序的,這樣就使得查詢變得很是快。oop
Hbase的優缺點
1 列的能夠動態增長,而且列爲空就不存儲數據,節省存儲空間.
2 Hbase自動切分數據,使得數據存儲自動具備水平可擴展性
3 Hbase能夠提供高併發讀寫操做的支持
Hbase的缺點:
1 不能支持條件查詢,只支持按照Row key來查詢.
2 暫時不能支持Master server的故障切換,當Master宕機後,整個存儲系統就會掛掉.
補充:
1.數據類型,HBase只有簡單的字符類型,全部的類型都是交由用戶本身處理,它只保存字符串。而關係數據庫有豐富的類型和存儲方式。
2.數據操做:HBase只有很簡單的插入、查詢、刪除、清空等操做,表和表之間是分離的,沒有複雜的表和表之間的關係,而傳統數據庫一般有各式各樣的函數和鏈接操做。
3.存儲模式:HBase是基於列存儲的,每一個列族都由幾個文件保存,不一樣的列族的文件時分離的。而傳統的關係型數據庫是基於表格結構和行模式保存的
4.數據維護,HBase的更新操做不該該叫更新,它其實是插入了新的數據,而傳統數據庫是替換修改
5.可伸縮性,Hbase這類分佈式數據庫就是爲了這個目的而開發出來的,因此它可以輕鬆增長或減小硬件的數量,而且對錯誤的兼容性比較高。而傳統數據庫一般須要增長中間層才能實現相似的功能
只要Row key相同就能夠看做一條數據,該數據的列,也就是屬性能夠添加。
import java.io.IOException; import java.util.ArrayList; import java.util.List; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.hbase.HBaseConfiguration; import org.apache.hadoop.hbase.HColumnDescriptor; import org.apache.hadoop.hbase.HTableDescriptor; import org.apache.hadoop.hbase.KeyValue; import org.apache.hadoop.hbase.MasterNotRunningException; import org.apache.hadoop.hbase.ZooKeeperConnectionException; import org.apache.hadoop.hbase.client.Delete; 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.HTablePool; 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.filter.Filter; import org.apache.hadoop.hbase.filter.FilterList; import org.apache.hadoop.hbase.filter.SingleColumnValueFilter; import org.apache.hadoop.hbase.filter.CompareFilter.CompareOp; import org.apache.hadoop.hbase.util.Bytes; public class HbaseTest { public static Configuration configuration; static { configuration = HBaseConfiguration.create(); configuration.set("hbase.zookeeper.property.clientPort", "2181"); configuration.set("hbase.zookeeper.quorum", "192.168.1.100"); configuration.set("hbase.master", "192.168.1.100:600000"); } public static void main(String[] args) { // createTable("wujintao"); // insertData("wujintao"); // QueryAll("wujintao"); // QueryByCondition1("wujintao"); // QueryByCondition2("wujintao"); //QueryByCondition3("wujintao"); //deleteRow("wujintao","abcdef"); deleteByCondition("wujintao","abcdef"); } public static void createTable(String tableName) { System.out.println("start create table ......"); try { HBaseAdmin hBaseAdmin = new HBaseAdmin(configuration); if (hBaseAdmin.tableExists(tableName)) {// 若是存在要建立的表,那麼先刪除,再建立 hBaseAdmin.disableTable(tableName); hBaseAdmin.deleteTable(tableName); System.out.println(tableName + " is exist,detele...."); } HTableDescriptor tableDescriptor = new HTableDescriptor(tableName); tableDescriptor.addFamily(new HColumnDescriptor("column1")); tableDescriptor.addFamily(new HColumnDescriptor("column2")); tableDescriptor.addFamily(new HColumnDescriptor("column3")); hBaseAdmin.createTable(tableDescriptor); } catch (MasterNotRunningException e) { e.printStackTrace(); } catch (ZooKeeperConnectionException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } System.out.println("end create table ......"); } public static void insertData(String tableName) { System.out.println("start insert data ......"); HTablePool pool = new HTablePool(configuration, 1000); HTable table = (HTable) pool.getTable(tableName); Put put = new Put("112233bbbcccc".getBytes());// 一個PUT表明一行數據,再NEW一個PUT表示第二行數據,每行一個惟一的ROWKEY,此處rowkey爲put構造方法中傳入的值 put.add("column1".getBytes(), null, "aaa".getBytes());// 本行數據的第一列 put.add("column2".getBytes(), null, "bbb".getBytes());// 本行數據的第三列 put.add("column3".getBytes(), null, "ccc".getBytes());// 本行數據的第三列 try { table.put(put); } catch (IOException e) { e.printStackTrace(); } System.out.println("end insert data ......"); } public static void dropTable(String tableName) { try { HBaseAdmin admin = new HBaseAdmin(configuration); admin.disableTable(tableName); admin.deleteTable(tableName); } catch (MasterNotRunningException e) { e.printStackTrace(); } catch (ZooKeeperConnectionException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } } public static void deleteRow(String tablename, String rowkey) { try { HTable table = new HTable(configuration, tablename); List list = new ArrayList(); Delete d1 = new Delete(rowkey.getBytes()); list.add(d1); table.delete(list); System.out.println("刪除行成功!"); } catch (IOException e) { e.printStackTrace(); } } public static void deleteByCondition(String tablename, String rowkey) { //目前尚未發現有效的API可以實現根據非rowkey的條件刪除這個功能能,還有清空表所有數據的API操做 } public static void QueryAll(String tableName) { HTablePool pool = new HTablePool(configuration, 1000); HTable table = (HTable) pool.getTable(tableName); try { ResultScanner rs = table.getScanner(new Scan()); for (Result r : rs) { System.out.println("得到到rowkey:" + new String(r.getRow())); for (KeyValue keyValue : r.raw()) { System.out.println("列:" + new String(keyValue.getFamily()) + "====值:" + new String(keyValue.getValue())); } } } catch (IOException e) { e.printStackTrace(); } } public static void QueryByCondition1(String tableName) { HTablePool pool = new HTablePool(configuration, 1000); HTable table = (HTable) pool.getTable(tableName); try { Get scan = new Get("abcdef".getBytes());// 根據rowkey查詢 Result r = table.get(scan); System.out.println("得到到rowkey:" + new String(r.getRow())); for (KeyValue keyValue : r.raw()) { System.out.println("列:" + new String(keyValue.getFamily()) + "====值:" + new String(keyValue.getValue())); } } catch (IOException e) { e.printStackTrace(); } } public static void QueryByCondition2(String tableName) { try { HTablePool pool = new HTablePool(configuration, 1000); HTable table = (HTable) pool.getTable(tableName); Filter filter = new SingleColumnValueFilter(Bytes .toBytes("column1"), null, CompareOp.EQUAL, Bytes .toBytes("aaa")); // 當列column1的值爲aaa時進行查詢 Scan s = new Scan(); s.setFilter(filter); ResultScanner rs = table.getScanner(s); for (Result r : rs) { System.out.println("得到到rowkey:" + new String(r.getRow())); for (KeyValue keyValue : r.raw()) { System.out.println("列:" + new String(keyValue.getFamily()) + "====值:" + new String(keyValue.getValue())); } } } catch (Exception e) { e.printStackTrace(); } } public static void QueryByCondition3(String tableName) { try { HTablePool pool = new HTablePool(configuration, 1000); HTable table = (HTable) pool.getTable(tableName); List<Filter> filters = new ArrayList<Filter>(); Filter filter1 = new SingleColumnValueFilter(Bytes .toBytes("column1"), null, CompareOp.EQUAL, Bytes .toBytes("aaa")); filters.add(filter1); Filter filter2 = new SingleColumnValueFilter(Bytes .toBytes("column2"), null, CompareOp.EQUAL, Bytes .toBytes("bbb")); filters.add(filter2); Filter filter3 = new SingleColumnValueFilter(Bytes .toBytes("column3"), null, CompareOp.EQUAL, Bytes .toBytes("ccc")); filters.add(filter3); FilterList filterList1 = new FilterList(filters); Scan scan = new Scan(); scan.setFilter(filterList1); ResultScanner rs = table.getScanner(scan); for (Result r : rs) { System.out.println("得到到rowkey:" + new String(r.getRow())); for (KeyValue keyValue : r.raw()) { System.out.println("列:" + new String(keyValue.getFamily()) + "====值:" + new String(keyValue.getValue())); } } rs.close(); } catch (Exception e) { e.printStackTrace(); } } }
/* * Need Packages: * commons-codec-1.4.jar * * commons-logging-1.1.1.jar * * hadoop-0.20.2-core.jar * * hbase-0.90.2.jar * * log4j-1.2.16.jar * * zookeeper-3.3.2.jar * */ import java.io.IOException; import java.util.ArrayList; import java.util.List; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.hbase.HBaseConfiguration; import org.apache.hadoop.hbase.KeyValue; import org.apache.hadoop.hbase.client.Get; import org.apache.hadoop.hbase.client.HTable; 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.filter.CompareFilter.CompareOp; import org.apache.hadoop.hbase.filter.FilterList; import org.apache.hadoop.hbase.filter.SingleColumnValueFilter; import org.apache.hadoop.hbase.util.Bytes; public class HbaseSelecter { public static Configuration configuration = null; static { configuration = HBaseConfiguration.create(); //configuration.set("hbase.master", "192.168.0.201:60000"); configuration.set("hbase.zookeeper.quorum", "idc01-hd-nd-03,idc01-hd-nd-04,idc01-hd-nd-05"); //configuration.set("hbase.zookeeper.property.clientPort", "2181"); } public static void selectRowKey(String tablename, String rowKey) throws IOException { HTable table = new HTable(configuration, tablename); Get g = new Get(rowKey.getBytes()); Result rs = table.get(g); for (KeyValue kv : rs.raw()) { System.out.println("--------------------" + new String(kv.getRow()) + "----------------------------"); System.out.println("Column Family: " + new String(kv.getFamily())); System.out.println("Column :" + new String(kv.getQualifier())); System.out.println("value : " + new String(kv.getValue())); } } public static void selectRowKeyFamily(String tablename, String rowKey, String family) throws IOException { HTable table = new HTable(configuration, tablename); Get g = new Get(rowKey.getBytes()); g.addFamily(Bytes.toBytes(family)); Result rs = table.get(g); for (KeyValue kv : rs.raw()) { System.out.println("--------------------" + new String(kv.getRow()) + "----------------------------"); System.out.println("Column Family: " + new String(kv.getFamily())); System.out.println("Column :" + new String(kv.getQualifier())); System.out.println("value : " + new String(kv.getValue())); } } public static void selectRowKeyFamilyColumn(String tablename, String rowKey, String family, String column) throws IOException { HTable table = new HTable(configuration, tablename); Get g = new Get(rowKey.getBytes()); g.addColumn(family.getBytes(), column.getBytes()); Result rs = table.get(g); for (KeyValue kv : rs.raw()) { System.out.println("--------------------" + new String(kv.getRow()) + "----------------------------"); System.out.println("Column Family: " + new String(kv.getFamily())); System.out.println("Column :" + new String(kv.getQualifier())); System.out.println("value : " + new String(kv.getValue())); } } public static void selectFilter(String tablename, List<String> arr) throws IOException { HTable table = new HTable(configuration, tablename); Scan scan = new Scan();// 實例化一個遍歷器 FilterList filterList = new FilterList(); // 過濾器List for (String v : arr) { // 下標0爲列簇,1爲列名,3爲條件 String[] wheres = v.split(","); filterList.addFilter(new SingleColumnValueFilter(// 過濾器 wheres[0].getBytes(), wheres[1].getBytes(), CompareOp.EQUAL,// 各個條件之間是" and "的關係 wheres[2].getBytes())); } scan.setFilter(filterList); ResultScanner ResultScannerFilterList = table.getScanner(scan); for (Result rs = ResultScannerFilterList.next(); rs != null; rs = ResultScannerFilterList.next()) { for (KeyValue kv : rs.list()) { System.out.println("--------------------" + new String(kv.getRow()) + "----------------------------"); System.out.println("Column Family: " + new String(kv.getFamily())); System.out.println("Column :" + new String(kv.getQualifier())); System.out.println("value : " + new String(kv.getValue())); } } } public static void main(String[] args) throws Exception { if(args.length < 2){ System.out.println("Usage: HbaseSelecter table key"); System.exit(-1); } System.out.println("Table: " + args[0] + " , key: " + args[1]); selectRowKey(args[0], args[1]); /* System.out.println("------------------------行鍵 查詢----------------------------------"); selectRowKey("b2c", "yihaodian1002865"); selectRowKey("b2c", "yihaodian1003396"); System.out.println("------------------------行鍵+列簇 查詢----------------------------------"); selectRowKeyFamily("riapguh", "用戶A", "user"); selectRowKeyFamily("riapguh", "用戶B", "user"); System.out.println("------------------------行鍵+列簇+列名 查詢----------------------------------"); selectRowKeyFamilyColumn("riapguh", "用戶A", "user", "user_code"); selectRowKeyFamilyColumn("riapguh", "用戶B", "user", "user_code"); System.out.println("------------------------條件 查詢----------------------------------"); List<String> arr = new ArrayList<String>(); arr.add("dpt,dpt_code,d_001"); arr.add("user,user_code,u_0001"); selectFilter("riapguh", arr); */ } }
摘自:https://www.cnblogs.com/zhenjing/p/hbase_example.html