Cassandra应用实践

tar -xzvf apache-cassandra-3.11.4-bin.tar.gz

# Directory where Cassandra should store hints.
# If not set, the default directory is $CASSANDRA_HOME/data/hints.
hints_directory:/data/cassandra/hints

# Directories where Cassandra should store data on disk.  Cassandra
# will spread data evenly across them, subject to the granularity of
# the configured compaction strategy.
# If not set, the default directory is $CASSANDRA_HOME/data/data.
# data_file_directories:
#     - /var/lib/cassandra/data
data_file_directories:
    - /data1/cassandra/data
    - /data2/cassandra/data
    
# commit log.  when running on magnetic HDD, this should be a
# separate spindle than the data directories.
# If not set, the default directory is $CASSANDRA_HOME/data/commitlog.
commitlog_directory: /data/data/cassandra/commitlog

# saved caches
# If not set, the default directory is $CASSANDRA_HOME/data/saved_caches.
saved_caches_directory: /data/cassandra/saved_caches

# any class that implements the SeedProvider interface and has a
# constructor that takes a Map<String, String> of parameters will do.
seed_provider:
    # Addresses of hosts that are deemed contact points. 
    # Cassandra nodes use this list of hosts to find each other and learn
    # the topology of the ring.  You must change this if you are running
    # multiple nodes!
    - class_name: org.apache.cassandra.locator.SimpleSeedProvider
      parameters:
          # seeds is actually a comma-delimited list of addresses.
          # Ex: "<ip1>,<ip2>,<ip3>"
          - seeds: "10.10.10.1,10.10.10.2"
          
# Set listen_address OR listen_interface, not both. Interfaces must correspond
# to a single address, IP aliasing is not supported.
listen_interface: bond1

Datacenter: datacenter1
=======================
Status=Up/Down
|/ State=Normal/Leaving/Joining/Moving
--  Address         Load       Tokens       Owns    Host ID                               Rack
UN  10.10.10.1     11.7 TiB     256          ?       85ad2d5f-10af-475a-915f-f95dd705e133  rack1
UN  10.10.10.2     10.1 TiB     256          ?       568eb231-eaa4-429c-b2fa-9b3a7db36ffd  rack1
UN  10.10.10.3     10.4 TiB     256          ?       4bf77471-4a83-4217-ba5c-96ce1bbd7647  rack1

# 创建keyspace（类似mysql的database），replication_factor表示副本数，class可选SimpleStrategy和NetworkTopologyStrategy
# 如果集群分布在多个数据中心，class选择NetworkTopologyStrategy。durable_writes表示更新记录时是否使用commit log
create keyspace mykeyspace with replication={'class':'SimpleStrategy','replication_factor':3} AND durable_writes = true;
use mykeyspace;

#创建表，其中domain是partition key
CREATE TABLE t(
    domain text,
    day text,
    key text,
    value int,
    PRIMARY KEY (domain, day, key)
) WITH CLUSTERING ORDER BY (domain DESC);

# 表的增、删、改、查操作类似mysql
INSERT INTO t (domain, day, key, value) VALUES ('test.com', '2019-02-24', 'key0', 10);
SELECT * FROM t;

CREATE TABLE t(
    domain text,
    day text,
    key text,
    value int,
    PRIMARY KEY (domain, day, key)
) WITH CLUSTERING ORDER BY (domain DESC);
可以支持的查询条件
select * from t where domain = ?
select * from t where domain = ? and day = ?
select * from t where domain = ? and day > ?
如果要以domain和key作为查询条件，需要加上allow filtering
select * from t where domain = ? and key = ? allow filtering

bin/cassandra &
如果要同时增加多台机器，则增加一个-Dcassandra.consistent.rangemovement=false选项

 bin/nodetool removenode host_id
 host_id 通过bin/nodetool status查看每个节点的host_id
 如果任务一直未完成，可以执行
 bin/nodetool removenode force