Cassandra开发入门文档第四部分(集合类型、元组类型、时间序列、计数列)

Cassandra 提供了三种集合类型,分别是Set,List,Map
Set: 非重复集,存储了一组类型相同的不重复元素,当被查询时会返回排好序的结果,但是内部构成是无序的值,应该是在查询时对结果进行了排序。
List: 列表,查询时会按照元素在list中的index顺序来返回结果,可以存储多个重复的值。
Map:哈希Key-Value键值对,提供了名字到值的映射

-- 开始工作:
bin/cqlsh localhost
-- 查看所有的键空间:
DESCRIBE keyspaces
-- 使用创建的键空间:
USE myks;
-- 查看已有表:
describe tables;
-- 查看表结构:
describe table user_status_updates;

 

Set

-- 修改表结构,增加一个列,用于存储评星用户记录

ALTER TABLE "user_status_updates"
ADD "starred_by_users" text;

-- 查询出一个空记录
SELECT "starred_by_users"
FROM "user_status_updates"
WHERE "username" = 'alice'
AND "id" = 76e7a4d0-e796-11e3-90ce-5f98e903bf02;

-- 修改记录,增加评星用户
UPDATE "user_status_updates"
SET "starred_by_users" = '["bob"]'
WHERE "username" = 'alice'
AND "id" = 76e7a4d0-e796-11e3-90ce-5f98e903bf02;

-- 事实上,可以直接定义列的类型为集合列,而不是定义为Text类型
ALTER TABLE "user_status_updates"
DROP "starred_by_users";
-- 注意一下:SET<text>类型
ALTER TABLE "user_status_updates"
ADD "starred_by_userss" SET<text>;

-- 修改记录方法1,增加评星用户,这次是集合,使用{}来存储多条数据
UPDATE "user_status_updates"
SET "starred_by_userss" = {'bob'}
WHERE "username" = 'alice'
AND "id" = 76e7a4d0-e796-11e3-90ce-5f98e903bf02;

-- 修改记录方法2,用+
UPDATE "user_status_updates"
SET "starred_by_userss" = "starred_by_userss" + {'carol'}
WHERE "username" = 'alice'
AND "id" = 76e7a4d0-e796-11e3-90ce-5f98e903bf02;

UPDATE "user_status_updates"
SET "starred_by_userss" = "starred_by_userss" + {'dave'}
WHERE "username" = 'alice'
AND "id" = 76e7a4d0-e796-11e3-90ce-5f98e903bf02;

-- 修改记录方法2,用-
UPDATE "user_status_updates"
SET "starred_by_userss" = "starred_by_users" - {'dave'}
WHERE "username" = 'alice'
AND "id" = 76e7a4d0-e796-11e3-90ce-5f98e903bf02;

UPDATE "user_status_updates"
SET "starred_by_userss" = "starred_by_userss" + {'carol'}
WHERE "username" = 'alice'
AND "id" = 76e7a4d0-e796-11e3-90ce-5f98e903bf02;

-- 多加几个为了测试排序
UPDATE "user_status_updates"
SET "starred_by_userss" = "starred_by_userss" + {'alice'}
WHERE "username" = 'alice'
AND "id" = 76e7a4d0-e796-11e3-90ce-5f98e903bf02;

SELECT "starred_by_userss"
FROM "user_status_updates"
WHERE "username" = 'alice'
AND "id" = 76e7a4d0-e796-11e3-90ce-5f98e903bf02;

 

查询结果发现,是经过了排序:
starred_by_userss
-----------------------------------
{'alice', 'bob', 'carol', 'dave'}

集合列表List

和上面的差不多,区别是允许重复,并且没有排序。

ALTER TABLE "user_status_updates"
ADD "shared_by" LIST<text>;

UPDATE "user_status_updates"
SET "shared_by" = ['bob']
WHERE "username" = 'alice'
AND "id" = 76e7a4d0-e796-11e3-90ce-5f98e903bf02;

UPDATE "user_status_updates"
SET "shared_by" = "shared_by" + ['carol']
WHERE "username" = 'alice'
AND "id" = 76e7a4d0-e796-11e3-90ce-5f98e903bf02;

UPDATE "user_status_updates"
SET "shared_by" = ['dave'] + "shared_by"
WHERE "username" = 'alice'
AND "id" = 76e7a4d0-e796-11e3-90ce-5f98e903bf02;

UPDATE "user_status_updates"
SET "shared_by"[1] = 'robert'
WHERE "username" = 'alice'
AND "id" = 76e7a4d0-e796-11e3-90ce-5f98e903bf02;

UPDATE "user_status_updates"
SET "shared_by"[3] = 'maurice'
WHERE "username" = 'alice'
AND "id" = 76e7a4d0-e796-11e3-90ce-5f98e903bf02;

UPDATE "user_status_updates"
SET "shared_by" = "shared_by" - ['carol']
WHERE "username" = 'alice'
AND "id" = 76e7a4d0-e796-11e3-90ce-5f98e903bf02;


--删除记录的方法是按照index顺序下标进行删除
DELETE "shared_by"[0]
FROM "user_status_updates"
WHERE "username" = 'alice'
AND "id" = 76e7a4d0-e796-11e3-90ce-5f98e903bf02;

UPDATE "user_status_updates"
SET "shared_by" = "shared_by" + ['arol']
WHERE "username" = 'alice'
AND "id" = 76e7a4d0-e796-11e3-90ce-5f98e903bf02;

-- 查询
SELECT "shared_by"
FROM "user_status_updates"
WHERE "username" = 'alice'
AND "id" = 76e7a4d0-e796-11e3-90ce-5f98e903bf02;

 

查询结果发现,没有排序:
shared_by
----------------------------
['dave', 'robert', 'arol']

Map

存储键值对,键是唯一和无序的。

ALTER TABLE "users"
ADD social_identities MAP<text,bigint>;

UPDATE "users"
SET "social_identities" = {'twitter': 353637}
WHERE "username" = 'alice';

UPDATE "users"
SET "social_identities"['instagram'] = 9839025,
"social_identities"['yo'] = 25
WHERE "username" = 'alice';

UPDATE "users"
SET "social_identities"['twitter'] = 2725634
WHERE "username" = 'alice';

DELETE "social_identities"['instagram']
FROM "users"
WHERE "username" = 'alice';


INSERT INTO "users" (
"username", "email", "encrypted_password",
"social_identities", "version"
) VALUES (
'ivan',
'ivan@gmail.com',
0x48acb738ece5780f37b626a0cb64928b,
{'twitter': 875958, 'instagram': 109550},
NOW()
);

 

使用TTL

UPDATE users USING TTL <computed_ttl>
SET todo['2012-10-1'] = 'find water' WHERE user_id = 'frodo';
INSERT INTO users
(user_name, password)
VALUES ('cbrown', 'ch@ngem4a') USING TTL 86400;

在设定的computed_ttl数值秒后,数据会自动删除。

使用集合类型要注意:
1.集合的每一项最大是64K。
2.保持集合内的数据不要太大,免得Cassandra 查询延时过长,只因Cassandra 查询时会读出整个集合内的数据,集合在内部不会进行分页,集合的目的是存储小量数据。
3.不要向集合插入大于64K的数据,否则只有查询到前64K数据,其它部分会丢失。

正确的查询姿势

如果查询条件where跟随集合列的时候会报错,是因为没有建立索引
InvalidRequest: Error from server: code=2200 [Invalid query] message="Cannot execute this query as it might involve data filtering and thus may have unpredictable performance. If you want to execute this query despite the performance unpredictability, use ALLOW FILTERING"

-- 正确的查询姿势,先创建索引
CREATE INDEX ON "user_status_updates" ("starred_by_userss");

SELECT * FROM "user_status_updates"
WHERE "starred_by_userss" CONTAINS 'alice';

-- map类型也是

CREATE INDEX ON "users" (KEYS("social_identities"));

SELECT "username", "social_identities"
FROM users
WHERE "social_identities" CONTAINS KEY 'twitter';

SELECT "shared_by"[2]
FROM "user_status_updates"
WHERE "username" = 'alice'
AND "id" = 76e7a4d0-e796-11e3-90ce-5f98e903bf02;

SELECT "social_identities"['twitter']
FROM "users"
WHERE "username" = 'alice';

SELECT * FROM "user_status_updates"
WHERE "username" = 'alice'
ORDER BY "id" ASC
LIMIT 2;


DROP INDEX user_social_identities_idx;
ALTER TABLE "users" DROP social_identities;

ALTER TABLE "users" ADD social_identities set<text>;

 

元组和自定义类型


-- 元组

ALTER
TABLE "users" ADD "education" frozen <tuple<text, int>>; ALTER TABLE "users" DROP "education"; ALTER TABLE "users" ADD "education" tuple<text, int>; UPDATE "users" SET "education" = ('Big Data University', 2019) WHERE "username" = 'alice'; UPDATE "users" SET "education" = ('Cassandra College', null, null) WHERE "username" = 'bob'; UPDATE "users" SET "education" = ('BDU') WHERE "username" = 'alice'; UPDATE "users" SET "education" = ('Big Data University', 2003) WHERE "username" = 'alice'; CREATE INDEX ON "users" ("education"); SELECT "username", "education" FROM users; SELECT "username", "education" FROM users WHERE "education" = ('Big Data University', 2003); -- 自定义类型 CREATE TYPE "education_information" ( "school_name" text, "graduation_year" int ); ALTER TABLE "users" DROP "education"; ALTER TABLE "users" ADD "education" frozen <"education_information">; UPDATE "users" SET "education" = { "school_name": 'Big Data University', "graduation_year": 2003 } WHERE "username" = 'alice'; CREATE INDEX ON "users" ("education"); SELECT "username", "education" FROM "users" WHERE "education" = { "school_name": 'Big Data University', "graduation_year": 2003 }; SELECT "username", "education"."school_name" FROM "users" WHERE "username" = 'alice'; ALTER TABLE "users" ADD "telephone_numbers" map<text, set<text>>; ALTER TABLE "users" ADD "telephone_numbers" map<text, frozen<set<text>>>; UPDATE "users" SET "telephone_numbers"['home'] = {'123456789', '123789456'} WHERE "username" = 'alice'; UPDATE "users" SET "telephone_numbers"['office'] = {'123654789', '123987456'} WHERE "username" = 'alice'; ALTER TABLE "users" ADD "education_history" set<frozen<"education_information">>; UPDATE "users" SET "education_history" = {{ "school_name": 'Big Data University', "graduation_year": 2003 },{ "school_name": 'Cassandra College', "graduation_year": 2005 }} WHERE "username" = 'alice';

 

时间序列数据库


目前业界时间序列数据库可以分成两类,基于现有的数据库或者专门为时间序列数据写的数据库。
有很多时间序列数据库是基于 Cassandra 的, KairosDB 是其中比较早的一个。 InfluxDB 是专用于时间序列的数据库。
另外还有十几种时间序列数据库,都是基于Cassandra,见https://xephonhq.github.io/awesome-time-series-database/?language=All&backend=Cassandra

一个简单的时间序列数据结构

CREATE TABLE IF NOT EXISTS naive.metrics (
metric_name text, metric_timestamp timestamp, value int,
PRIMARY KEY (metric_name, metric_timestamp))
INSERT INTO naive.metrics (metric_name, metric_timestamp, value) VALUES (cpu, 2017/03/17:13:24:00:20, 10.2) 
INSERT INTO naive.metrics (metric_name, metric_timestamp, value) VALUES (mem, 2017/03/17:13:24:00:20, 80.3)

上图显示了使用 Cassandra 存储时间序列数据时 naive 的表结构, Cluster Key 存储时间戳,列的值存储实际的数值。 它 naive 之处在于序列和 Cassandra 的物理行是一一对应的。 当单一序列的数据点超过 Cassandra 的限制(20亿)时就会崩溃。
一个更加成熟的表结构是把一个时间序列按时间范围分区,(KairosDB 按照 3 周来划分,但是可以根据数据量进行不定长的划分)。 为了存储分区的信息,需要一张额外的表。 同时在 naive 里序列的名称只是一个简单的字符串,如果需要按照多种条件进行筛选的话,需要存储更多的键值对,并且对于这些键值对需要建立索引以提高查询速度。

更复杂的例子:

一个双分区列的例子,("status_update_username", "status_update_id")是联合分区列,observed_at是簇分区列,也是时间序列,类型为timeuuid

CREATE TABLE "status_update_views" (

"status_update_username" text,
"status_update_id" timeuuid,
"observed_at" timeuuid,
"client_type" text,
PRIMARY KEY (
("status_update_username", "status_update_id"),
"observed_at"
)
);

-- 插入数据
INSERT INTO "status_update_views" (
"status_update_username", "status_update_id",
"observed_at", "client_type"
) VALUES (
'alice', 76e7a4d0-e796-11e3-90ce-5f98e903bf02,
85a53d10-4cc3-11e4-a7ff-5f98e903bf02,
'web'
);
-- 查询
SELECT "observed_at", "client_type"
FROM "status_update_views"
WHERE "status_update_username" = 'alice'
AND "status_update_id" = 76e7a4d0-e796-11e3-90ce-5f98e903bf02
AND "observed_at" >= MINTIMEUUID('2014-10-05 00:00:00+0000')
AND "observed_at" < MINTIMEUUID('2014-10-06 00:00:00+0000');
-- 查询计数
SELECT COUNT(1)
FROM "status_update_views"
WHERE "status_update_username" = 'alice'
AND "status_update_id" = 76e7a4d0-e796-11e3-90ce-5f98e903bf02
AND "observed_at" >= MINTIMEUUID('2014-10-05 00:00:00+0000')
AND "observed_at" < MINTIMEUUID('2014-10-06 00:00:00+0000');

 

计数表counter

有一些计数类型的应用,比如某个页面被点击了多少次,或9月的每一天,状态更新了多少次。一般地说,我们希望将每日总体视图计数存储在一个结构中,该结构允许我们在给定的时间范围内轻松检索计数。我们不需要存储关于每个视图事件的离散信息;只需知道每天发生了多少视图就足够了。Cassandra非常擅长做这个。


我个人认为这种高性能、低存储空间的计数应用交给Redis会更好,Cassandra有比较多的局限(http://rockthecode.io/blog/highly-available-counters-using-cassandra/),Cassandra还是做它擅长的列存储、时间序列就好了。

-- 注意,counter类型
-- year是分区列,date为簇列

CREATE TABLE "daily_status_update_views" (
"year" int,
"date" timestamp,
"total_views" counter,
"web_views" counter,
"mobile_views" counter,
"api_views" counter,
PRIMARY KEY (("year"), "date")
);

SELECT "date", "total_views"
FROM "daily_status_update_views"
WHERE "year" = 2014
AND "date" >= '2014-09-01'
AND "date" < '2014-09-30';

UPDATE "daily_status_update_views"
SET "total_views" = "total_views" + 1,
"web_views" = "web_views" + 1
WHERE "year" = 2014
AND "date" = '2014-10-05 00:00:00+0000';

SELECT * FROM "daily_status_update_views";

-- 在尝试添加的时候会报错,原因是counter表只允许update,不准insert
-- InvalidRequest: Error from server: code=2200 [Invalid query] message="INSERT statements are not allowed on counter tables, use UPDATE instead"

INSERT INTO "daily_status_update_views"
("year", "date", "total_views")
VALUES (2014, '2014-02-01 00:00:00+0000', 500);

-- 正确的姿势
UPDATE "daily_status_update_views"
SET "total_views" = "total_views" + 500
WHERE "year" = 2014
AND "date" = '2014-02-01 00:00:00+0000';

DELETE FROM "daily_status_update_views"
WHERE "year" = 2014
AND "date" = '2014-02-01 00:00:00+0000';

UPDATE "daily_status_update_views"
SET "total_views" = "total_views" + 100
WHERE "year" = 2014
AND "date" = '2014-02-01 00:00:00+0000';

-- 在尝试修改表定义的时候会报错,只能增加counter类型的列
-- ConfigurationException: Cannot add a non counter column (last_view_time) in a counter column family

ALTER TABLE "daily_status_update_views"
ADD "last_view_time" timestamp;

 

用户定义函数

比较简单,不多说了。感觉应用的地方不多。

CREATE OR REPLACE FUNCTION selectCity(location text) 
CALLED ON NULL INPUT 
RETURNS text 
LANGUAGE java 
AS ' 
if (location == null)
return null;
else
return location.split(",")[0];
';

SELECT username, selectCity(location) FROM "users";

CREATE OR REPLACE FUNCTION selectCity(location text) 
RETURNS NULL ON NULL INPUT 
RETURNS text 
LANGUAGE java 
AS ' 
return location.split(",")[0];
';

INSERT INTO "status_update_views" ("status_update_username", "status_update_id", "observed_at", "client_type") VALUES ('alice', 76e7a4d0-e796-11e3-90ce-5f98e903bf02, NOW(), 'web');
INSERT INTO "status_update_views" ("status_update_username", "status_update_id", "observed_at", "client_type") VALUES ('alice', 76e7a4d0-e796-11e3-90ce-5f98e903bf02, NOW(), 'web');
INSERT INTO "status_update_views" ("status_update_username", "status_update_id", "observed_at", "client_type") VALUES ('alice', 76e7a4d0-e796-11e3-90ce-5f98e903bf02, NOW(), 'mobile');
INSERT INTO "status_update_views" ("status_update_username", "status_update_id", "observed_at", "client_type") VALUES ('alice', 76e7a4d0-e796-11e3-90ce-5f98e903bf02, NOW(), 'mobile');
INSERT INTO "status_update_views" ("status_update_username", "status_update_id", "observed_at", "client_type") VALUES ('alice', 76e7a4d0-e796-11e3-90ce-5f98e903bf02, NOW(), 'api');


CREATE OR REPLACE FUNCTION state_group_and_count (state map<text, int>, client_type text)
CALLED ON NULL INPUT
RETURNS map<text, int>
LANGUAGE java AS '
Integer count = (Integer) state.get(client_type); 
if (count == null) 
count = 1; 
else 
count++; 
state.put(client_type, count); 
return state; 
';

CREATE OR REPLACE AGGREGATE group_and_count (text) 
SFUNC state_group_and_count
STYPE map<text, int> 
INITCOND {};

 

SELECT status_update_username, status_update_id, group_and_count(client_type) 
FROM status_update_views 
WHERE status_update_username='alice' AND status_update_id=76e7a4d0-e796-11e3-90ce-5f98e903bf02;


SELECT status_update_username, status_update_id, group_and_count(client_type) 
FROM status_update_views 
WHERE status_update_username='alice' AND status_update_id=76e7a4d0-e796-11e3-90ce-5f98e903bf02 
AND "observed_at" >= MINTIMEUUID('2016-12-21 00:00:00+0000') 
AND "observed_at" < MINTIMEUUID('2016-12-22 00:00:00+0000');

 

posted @ 2019-11-26 10:12  昕友软件开发  阅读(1068)  评论(0编辑  收藏  举报
欢迎访问我的开源项目:xyIM企业即时通讯