【HBase——陌陌海量存储案例】6. 预分区表

6.5 预分区表

默认创建表的方式，则HBase顺序写入可能会受到RegionServer热点的影响。对行键进行加盐可以解决热点问题。在HBase中，可以使用两种方式：

1.ROWKEY预分区
2.加盐指定数量分区

6.5.1 ROWKEY预分区

按照用户ID来分区，一共4个分区。并指定数据的压缩格式为GZ。

drop table if exists ORDER_DTL;
create table if not exists ORDER_DTL(
    "id" varchar primary key,
    C1."status" varchar,
    C1."money" float,
    C1."pay_way" integer,
    C1."user_id" varchar,
    C1."operation_time" varchar,
    C1."category" varchar
) 
CONPRESSION='GZ'
SPLIT ON ('3','5','7');

我们尝试往表中插入一些数据，然后去HBase中查看数据的分布情况。

UPSERT INTO "ORDER_DTL" VALUES('02602f66-adc7-40d4-8485-76b5632b5b53','已提交',4070,1,'4944191','2020-04-25 12:09:16','手机;');
UPSERT INTO "ORDER_DTL" VALUES('0968a418-f2bc-49b4-b9a9-2157cf214cfd','已完成',4350,1,'1625615','2020-04-25 12:09:37','家用电器;;电脑;');
UPSERT INTO "ORDER_DTL" VALUES('0e01edba-5e55-425e-837a-7efb91c56630','已提交',6370,3,'3919700','2020-04-25 12:09:39','男装;男鞋;');
UPSERT INTO "ORDER_DTL" VALUES('0e01edba-5e55-425e-837a-7efb91c56630','已付款',6370,3,'3919700','2020-04-25 12:09:44','男装;男鞋;');
UPSERT INTO "ORDER_DTL" VALUES('0f46d542-34cb-4ef4-b7fe-6dcfa5f14751','已提交',9380,1,'2993700','2020-04-25 12:09:41','维修;手机;');
UPSERT INTO "ORDER_DTL" VALUES('0f46d542-34cb-4ef4-b7fe-6dcfa5f14751','已付款',9380,1,'2993700','2020-04-25 12:09:46','维修;手机;');
UPSERT INTO "ORDER_DTL" VALUES('1fb7c50f-9e26-4aa8-a140-a03d0de78729','已完成',6400,2,'5037058','2020-04-25 12:10:13','数码;女装;');
UPSERT INTO "ORDER_DTL" VALUES('23275016-996b-420c-8edc-3e3b41de1aee','已付款',280,1,'3018827','2020-04-25 12:09:53','男鞋;汽车;');
UPSERT INTO "ORDER_DTL" VALUES('2375a7cf-c206-4ac0-8de4-863e7ffae27b','已完成',5600,1,'6489579','2020-04-25 12:08:55','食品;家用电器;');
UPSERT INTO "ORDER_DTL" VALUES('2375a7cf-c206-4ac0-8de4-863e7ffae27b','已付款',5600,1,'6489579','2020-04-25 12:09:00','食品;家用电器;');
UPSERT INTO "ORDER_DTL" VALUES('269fe10c-740b-4fdb-ad25-7939094073de','已提交',8340,2,'2948003','2020-04-25 12:09:26','男装;男鞋;');
UPSERT INTO "ORDER_DTL" VALUES('269fe10c-740b-4fdb-ad25-7939094073de','已付款',8340,2,'2948003','2020-04-25 12:09:30','男装;男鞋;');
UPSERT INTO "ORDER_DTL" VALUES('2849fa34-6513-44d6-8f66-97bccb3a31a1','已提交',7060,2,'2092774','2020-04-25 12:09:38','酒店;旅游;');
UPSERT INTO "ORDER_DTL" VALUES('28b7e793-6d14-455b-91b3-0bd8b23b610c','已提交',640,3,'7152356','2020-04-25 12:09:49','维修;手机;');
UPSERT INTO "ORDER_DTL" VALUES('28b7e793-6d14-455b-91b3-0bd8b23b610c','已付款',9410,3,'7152356','2020-04-25 12:10:01','维修;手机;');
UPSERT INTO "ORDER_DTL" VALUES('2909b28a-5085-4f1d-b01e-a34fbaf6ce37','已提交',9390,3,'8237476','2020-04-25 12:10:08','男鞋;汽车;');
UPSERT INTO "ORDER_DTL" VALUES('2a01dfe5-f5dc-4140-b31b-a6ee27a6e51e','已提交',7490,2,'7813118','2020-04-25 12:09:05','机票;文娱;');
UPSERT INTO "ORDER_DTL" VALUES('2a01dfe5-f5dc-4140-b31b-a6ee27a6e51e','已付款',7490,2,'7813118','2020-04-25 12:09:06','机票;文娱;');
UPSERT INTO "ORDER_DTL" VALUES('2b86ab90-3180-4940-b624-c936a1e7568d','已付款',5360,2,'5301038','2020-04-25 12:08:50','维修;手机;');
UPSERT INTO "ORDER_DTL" VALUES('2b86ab90-3180-4940-b624-c936a1e7568d','已提交',5360,2,'5301038','2020-04-25 12:08:53','维修;手机;');
UPSERT INTO "ORDER_DTL" VALUES('2b86ab90-3180-4940-b624-c936a1e7568d','已取消',5360,2,'5301038','2020-04-25 12:08:58','维修;手机;');
UPSERT INTO "ORDER_DTL" VALUES('2e19fbe8-7970-4d62-8e8f-d364afc2dd41','已付款',6490,0,'3141181','2020-04-25 12:09:22','食品;家用电器;');
UPSERT INTO "ORDER_DTL" VALUES('2fc28d36-dca0-49e8-bad0-42d0602bdb40','已付款',3820,1,'9054826','2020-04-25 12:10:04','家用电器;;电脑;');
UPSERT INTO "ORDER_DTL" VALUES('31477850-8b15-4f1b-9ec3-939f7dc47241','已提交',4650,2,'5837271','2020-04-25 12:08:52','机票;文娱;');
UPSERT INTO "ORDER_DTL" VALUES('31477850-8b15-4f1b-9ec3-939f7dc47241','已付款',4650,2,'5837271','2020-04-25 12:08:57','机票;文娱;');
UPSERT INTO "ORDER_DTL" VALUES('39319322-2d80-41e7-a862-8b8858e63316','已提交',5000,1,'5686435','2020-04-25 12:08:51','家用电器;;电脑;');
UPSERT INTO "ORDER_DTL" VALUES('39319322-2d80-41e7-a862-8b8858e63316','已完成',5000,1,'5686435','2020-04-25 12:08:56','家用电器;;电脑;');
UPSERT INTO "ORDER_DTL" VALUES('3d2254bd-c25a-404f-8e42-2faa4929a629','已提交',5000,3,'1274270','2020-04-25 12:08:41','男装;男鞋;');
UPSERT INTO "ORDER_DTL" VALUES('3d2254bd-c25a-404f-8e42-2faa4929a629','已付款',5000,3,'1274270','2020-04-25 12:08:42','男装;男鞋;');
UPSERT INTO "ORDER_DTL" VALUES('3d2254bd-c25a-404f-8e42-2faa4929a629','已完成',5000,1,'1274270','2020-04-25 12:08:43','男装;男鞋;');
UPSERT INTO "ORDER_DTL" VALUES('42f7fe21-55a3-416f-9535-baa222cc0098','已完成',3600,2,'2661641','2020-04-25 12:09:58','维修;手机;');
UPSERT INTO "ORDER_DTL" VALUES('44231dbb-9e58-4f1a-8c83-be1aa814be83','已提交',3950,1,'3855371','2020-04-25 12:08:39','数码;女装;');
UPSERT INTO "ORDER_DTL" VALUES('44231dbb-9e58-4f1a-8c83-be1aa814be83','已付款',3950,1,'3855371','2020-04-25 12:08:40','数码;女装;');
UPSERT INTO "ORDER_DTL" VALUES('526e33d2-a095-4e19-b759-0017b13666ca','已完成',3280,0,'5553283','2020-04-25 12:09:01','食品;家用电器;');
UPSERT INTO "ORDER_DTL" VALUES('5a6932f4-b4a4-4a1a-b082-2475d13f9240','已提交',50,2,'1764961','2020-04-25 12:10:07','家用电器;;电脑;');
UPSERT INTO "ORDER_DTL" VALUES('5fc0093c-59a3-417b-a9ff-104b9789b530','已提交',6310,2,'1292805','2020-04-25 12:09:36','男装;男鞋;');
UPSERT INTO "ORDER_DTL" VALUES('605c6dd8-123b-4088-a047-e9f377fcd866','已完成',8980,2,'6202324','2020-04-25 12:09:54','机票;文娱;');
UPSERT INTO "ORDER_DTL" VALUES('613cfd50-55c7-44d2-bb67-995f72c488ea','已完成',6830,3,'6977236','2020-04-25 12:10:06','酒店;旅游;');
UPSERT INTO "ORDER_DTL" VALUES('62246ac1-3dcb-4f2c-8943-800c9216c29f','已提交',8610,1,'5264116','2020-04-25 12:09:14','维修;手机;');
UPSERT INTO "ORDER_DTL" VALUES('62246ac1-3dcb-4f2c-8943-800c9216c29f','已付款',8610,1,'5264116','2020-04-25 12:09:18','维修;手机;');
UPSERT INTO "ORDER_DTL" VALUES('625c7fef-de87-428a-b581-a63c71059b14','已提交',5970,0,'8051757','2020-04-25 12:09:07','男鞋;汽车;');
UPSERT INTO "ORDER_DTL" VALUES('625c7fef-de87-428a-b581-a63c71059b14','已付款',5970,0,'8051757','2020-04-25 12:09:19','男鞋;汽车;');
UPSERT INTO "ORDER_DTL" VALUES('6d43c490-58ab-4e23-b399-dda862e06481','已提交',4570,0,'5514248','2020-04-25 12:09:34','酒店;旅游;');
UPSERT INTO "ORDER_DTL" VALUES('70fa0ae0-6c02-4cfa-91a9-6ad929fe6b1b','已付款',4100,1,'8598963','2020-04-25 12:09:08','维修;手机;');
UPSERT INTO "ORDER_DTL" VALUES('7170ce71-1fc0-4b6e-a339-67f525536dcd','已完成',9740,1,'4816392','2020-04-25 12:09:51','数码;女装;');
UPSERT INTO "ORDER_DTL" VALUES('7170ce71-1fc0-4b6e-a339-67f525536dcd','已提交',9740,1,'4816392','2020-04-25 12:10:03','数码;女装;');
UPSERT INTO "ORDER_DTL" VALUES('71961b06-290b-457d-bbe0-86acb013b0e3','已付款',6550,3,'2393699','2020-04-25 12:08:47','男鞋;汽车;');
UPSERT INTO "ORDER_DTL" VALUES('71961b06-290b-457d-bbe0-86acb013b0e3','已付款',6550,3,'2393699','2020-04-25 12:08:48','男鞋;汽车;');
UPSERT INTO "ORDER_DTL" VALUES('71961b06-290b-457d-bbe0-86acb013b0e3','已完成',6550,3,'2393699','2020-04-25 12:08:49','男鞋;汽车;');
UPSERT INTO "ORDER_DTL" VALUES('72dc148e-ce64-432d-b99f-61c389cb82cd','已提交',4090,1,'2536942','2020-04-25 12:10:12','机票;文娱;');
UPSERT INTO "ORDER_DTL" VALUES('72dc148e-ce64-432d-b99f-61c389cb82cd','已付款',4090,1,'2536942','2020-04-25 12:10:14','机票;文娱;');
UPSERT INTO "ORDER_DTL" VALUES('7c0c1668-b783-413f-afc4-678a5a6d1033','已完成',3850,3,'6803936','2020-04-25 12:09:20','酒店;旅游;');
UPSERT INTO "ORDER_DTL" VALUES('7fa02f7a-10df-4247-9935-94c8b7d4dbc0','已提交',1060,0,'6119810','2020-04-25 12:09:21','维修;手机;');
UPSERT INTO "ORDER_DTL" VALUES('820c5e83-f2e0-42d4-b5f0-83802c75addc','已付款',9270,2,'5818454','2020-04-25 12:10:09','数码;女装;');
UPSERT INTO "ORDER_DTL" VALUES('83ed55ec-a439-44e0-8fe0-acb7703fb691','已完成',8380,2,'6804703','2020-04-25 12:09:52','男鞋;汽车;');
UPSERT INTO "ORDER_DTL" VALUES('85287268-f139-4d59-8087-23fa6454de9d','已提交',9750,1,'4382852','2020-04-25 12:09:43','数码;女装;');
UPSERT INTO "ORDER_DTL" VALUES('85287268-f139-4d59-8087-23fa6454de9d','已付款',9750,1,'4382852','2020-04-25 12:09:48','数码;女装;');
UPSERT INTO "ORDER_DTL" VALUES('85287268-f139-4d59-8087-23fa6454de9d','已取消',9750,1,'4382852','2020-04-25 12:10:00','数码;女装;');
UPSERT INTO "ORDER_DTL" VALUES('8d32669e-327a-4802-89f4-2e91303aee59','已提交',9390,1,'4182962','2020-04-25 12:09:57','机票;文娱;');
UPSERT INTO "ORDER_DTL" VALUES('8dadc2e4-63f1-490f-9182-793be64fed76','已付款',9350,1,'5937549','2020-04-25 12:09:02','酒店;旅游;');
UPSERT INTO "ORDER_DTL" VALUES('94ad8ee0-8898-442c-8cb1-083a4b609616','已提交',4370,0,'4666456','2020-04-25 12:09:13','维修;手机;');
UPSERT INTO "ORDER_DTL" VALUES('994cbb44-f0ee-45ff-a4f4-76c87bc2b972','已付款',3190,3,'3200759','2020-04-25 12:09:25','数码;女装;');
UPSERT INTO "ORDER_DTL" VALUES('9bf92519-6eb3-449a-853b-0e19f6005887','已提交',1100,0,'3457528','2020-04-25 12:10:11','数码;女装;');
UPSERT INTO "ORDER_DTL" VALUES('9ff3032c-8679-4247-9e6f-4caf2dc93aff','已提交',850,0,'8835231','2020-04-25 12:09:40','男鞋;汽车;');
UPSERT INTO "ORDER_DTL" VALUES('9ff3032c-8679-4247-9e6f-4caf2dc93aff','已付款',850,0,'8835231','2020-04-25 12:09:45','食品;家用电器;');
UPSERT INTO "ORDER_DTL" VALUES('a467ba42-f91e-48a0-865e-1703aaa45e0e','已提交',8040,0,'8206022','2020-04-25 12:09:50','家用电器;;电脑;');
UPSERT INTO "ORDER_DTL" VALUES('a467ba42-f91e-48a0-865e-1703aaa45e0e','已付款',8040,0,'8206022','2020-04-25 12:10:02','家用电器;;电脑;');
UPSERT INTO "ORDER_DTL" VALUES('a5302f47-96d9-41b4-a14c-c7a508f59282','已付款',8570,2,'5319315','2020-04-25 12:08:44','机票;文娱;');
UPSERT INTO "ORDER_DTL" VALUES('a5b57bec-6235-45f4-bd7e-6deb5cd1e008','已提交',5700,3,'6486444','2020-04-25 12:09:27','酒店;旅游;');
UPSERT INTO "ORDER_DTL" VALUES('a5b57bec-6235-45f4-bd7e-6deb5cd1e008','已付款',5700,3,'6486444','2020-04-25 12:09:31','酒店;旅游;');
UPSERT INTO "ORDER_DTL" VALUES('ae5c3363-cf8f-48a9-9676-701a7b0a7ca5','已付款',7460,1,'2379296','2020-04-25 12:09:23','维修;手机;');
UPSERT INTO "ORDER_DTL" VALUES('b1fb2399-7cf2-4af5-960a-a4d77f4803b8','已提交',2690,3,'6686018','2020-04-25 12:09:55','数码;女装;');
UPSERT INTO "ORDER_DTL" VALUES('b21c7dbd-dabd-4610-94b9-d7039866a8eb','已提交',6310,2,'1552851','2020-04-25 12:09:15','男鞋;汽车;');
UPSERT INTO "ORDER_DTL" VALUES('b4bfd4b7-51f5-480e-9e23-8b1579e36248','已提交',4000,1,'3260372','2020-04-25 12:09:35','机票;文娱;');
UPSERT INTO "ORDER_DTL" VALUES('b63983cc-2b59-4992-84c6-9810526d0282','已提交',7370,3,'3107867','2020-04-25 12:08:45','数码;女装;');
UPSERT INTO "ORDER_DTL" VALUES('b63983cc-2b59-4992-84c6-9810526d0282','已付款',7370,3,'3107867','2020-04-25 12:08:46','数码;女装;');
UPSERT INTO "ORDER_DTL" VALUES('bf60b752-1ccc-43bf-9bc3-b2aeccacc0ed','已提交',720,2,'5034117','2020-04-25 12:09:03','机票;文娱;');
UPSERT INTO "ORDER_DTL" VALUES('c808addc-8b8b-4d89-99b1-db2ed52e61b4','已提交',3630,1,'6435854','2020-04-25 12:09:10','酒店;旅游;');
UPSERT INTO "ORDER_DTL" VALUES('cc9dbd20-cf9f-4097-ae8b-4e73db1e4ba1','已付款',5000,0,'2007322','2020-04-25 12:08:38','维修;手机;');
UPSERT INTO "ORDER_DTL" VALUES('ccceaf57-a5ab-44df-834a-e7b32c63efc1','已提交',2660,2,'7928516','2020-04-25 12:09:42','数码;女装;');
UPSERT INTO "ORDER_DTL" VALUES('ccceaf57-a5ab-44df-834a-e7b32c63efc1','已付款',2660,2,'7928516','2020-04-25 12:09:47','数码;女装;');
UPSERT INTO "ORDER_DTL" VALUES('ccceaf57-a5ab-44df-834a-e7b32c63efc1','已完成',2660,2,'7928516','2020-04-25 12:09:59','数码;女装;');
UPSERT INTO "ORDER_DTL" VALUES('d7be5c39-e07c-40e8-bf09-4922fbc6335c','已付款',8750,2,'1250995','2020-04-25 12:09:09','食品;家用电器;');
UPSERT INTO "ORDER_DTL" VALUES('dfe16df7-4a46-4b6f-9c6d-083ec215218e','已完成',410,0,'1923817','2020-04-25 12:09:56','家用电器;;电脑;');
UPSERT INTO "ORDER_DTL" VALUES('e1241ad4-c9c1-4c17-93b9-ef2c26e7f2b2','已付款',6760,0,'2457464','2020-04-25 12:08:54','数码;女装;');
UPSERT INTO "ORDER_DTL" VALUES('e1241ad4-c9c1-4c17-93b9-ef2c26e7f2b2','已提交',6760,0,'2457464','2020-04-25 12:08:59','数码;女装;');
UPSERT INTO "ORDER_DTL" VALUES('e180a9f2-9f80-4b6d-99c8-452d6c037fc7','已付款',8120,2,'7645270','2020-04-25 12:09:28','男鞋;汽车;');
UPSERT INTO "ORDER_DTL" VALUES('e180a9f2-9f80-4b6d-99c8-452d6c037fc7','已完成',8120,2,'7645270','2020-04-25 12:09:32','男鞋;汽车;');
UPSERT INTO "ORDER_DTL" VALUES('e4418843-9ac0-47a7-bfd8-d61c4d296933','已付款',8170,2,'7695668','2020-04-25 12:09:11','家用电器;;电脑;');
UPSERT INTO "ORDER_DTL" VALUES('e8b3bb37-1019-4492-93c7-305177271a71','已完成',2560,2,'4405460','2020-04-25 12:10:05','男装;男鞋;');
UPSERT INTO "ORDER_DTL" VALUES('eb1a1a22-953a-42f1-b594-f5dfc8fb6262','已完成',2370,2,'8233485','2020-04-25 12:09:24','机票;文娱;');
UPSERT INTO "ORDER_DTL" VALUES('ecfd18f5-45f2-4dcd-9c47-f2ad9b216bd0','已付款',8070,3,'6387107','2020-04-25 12:09:04','酒店;旅游;');
UPSERT INTO "ORDER_DTL" VALUES('ecfd18f5-45f2-4dcd-9c47-f2ad9b216bd0','已完成',8070,3,'6387107','2020-04-25 12:09:17','酒店;旅游;');
UPSERT INTO "ORDER_DTL" VALUES('f1226752-7be3-4702-a496-3ddba56f66ec','已付款',4410,3,'1981968','2020-04-25 12:10:10','维修;手机;');
UPSERT INTO "ORDER_DTL" VALUES('f642b16b-eade-4169-9eeb-4d5f294ec594','已提交',4010,1,'6463215','2020-04-25 12:09:29','男鞋;汽车;');
UPSERT INTO "ORDER_DTL" VALUES('f642b16b-eade-4169-9eeb-4d5f294ec594','已付款',4010,1,'6463215','2020-04-25 12:09:33','男鞋;汽车;');
UPSERT INTO "ORDER_DTL" VALUES('f8f3ca6f-2f5c-44fd-9755-1792de183845','已付款',5950,3,'4060214','2020-04-25 12:09:12','机票;文娱;');

我们发现数据分布在每一个Region中。

6.5.2 加盐指定数量分区

drop table if exists ORDER_DTL;
create table if not exists ORDER_DTL(
    "id" varchar primary key,
    C1."status" varchar,
    C1."money" float,
    C1."pay_way" integer,
    C1."user_id" varchar,
    C1."operation_time" varchar,
    C1."category" varchar
) 
CONPRESSION='GZ', SALT_BUCKETS=10;

我们在HBase的Web UI中可以查看到生成了10个Region

插入数据后，发现数据分部在每一个Region中。

查看HBase中的表，我们发现Phoenix在每个ID前，都添加了一个Hash值，用来将分布分布到不同的Region中。

hbase(main):018:0> scan "ORDER_DTL", {LIMIT => 1}
ROW                                                          COLUMN+CELL                                                                                                                                                                     
 \x000f46d542-34cb-4ef4-b7fe-6dcfa5f14751                    column=C1:\x00\x00\x00\x00, timestamp=1589268724801, value=x                                                                                                                    
 \x000f46d542-34cb-4ef4-b7fe-6dcfa5f14751                    column=C1:\x80\x0B, timestamp=1589268724801, value=\xE5\xB7\xB2\xE4\xBB\x98\xE6\xAC\xBE                                                                                         
 \x000f46d542-34cb-4ef4-b7fe-6dcfa5f14751                    column=C1:\x80\x0C, timestamp=1589268724801, value=\xC6\x12\x90\x01                                                                                                             
 \x000f46d542-34cb-4ef4-b7fe-6dcfa5f14751                    column=C1:\x80\x0D, timestamp=1589268724801, value=\x80\x00\x00\x01                                                                                                             
 \x000f46d542-34cb-4ef4-b7fe-6dcfa5f14751                    column=C1:\x80\x0E, timestamp=1589268724801, value=2993700                                                                                                                      
 \x000f46d542-34cb-4ef4-b7fe-6dcfa5f14751                    column=C1:\x80\x0F, timestamp=1589268724801, value=2020-04-25 12:09:46                                                                                                          
 \x000f46d542-34cb-4ef4-b7fe-6dcfa5f14751                    column=C1:\x80\x10, timestamp=1589268724801, value=\xE7\xBB\xB4\xE4\xBF\xAE;\xE6\x89\x8B\xE6\x9C\xBA;                                                                           
1 row(s)

注意：CONPRESSION和SALT_BUCKETS之间需要使用逗号分隔，否则会出现语法错误