yum安装CDH5.5 hive、impala的过程详解

172.16.57.75 bd-ops-test-75 mysql-server
172.16.57.77 bd-ops-test-77 Hiveserver2 HiveMetaStore

# yum install hive hive-metastore hive-server2 hive-jdbc hive-hbase -y

# yum install hive hive-server2 hive-jdbc hive-hbase -y

# yum install mysql mysql-devel mysql-server mysql-libs -y

# 配置开启启动
# chkconfig mysqld on
# service mysqld start

# yum install mysql-connector-java
# ln -s /usr/share/java/mysql-connector-java.jar /usr/lib/hive/lib/mysql-connector-java.jar

# mysqladmin -uroot password 'bigdata'

CREATE DATABASE metastore;
USE metastore;
SOURCE /usr/lib/hive/scripts/metastore/upgrade/mysql/hive-schema-1.1.0.mysql.sql;
CREATE USER 'hive'@'localhost' IDENTIFIED BY 'hive';
GRANT ALL PRIVILEGES ON metastore.* TO 'hive'@'localhost';
GRANT ALL PRIVILEGES ON metastore.* TO 'hive'@'%';
FLUSH PRIVILEGES;

<property>
<name>javax.jdo.option.ConnectionURL</name>
<value>jdbc:mysql://172.16.57.75:3306/metastore?useUnicode=true&characterEncoding=UTF-8</value>
</property>
<property>
<name>javax.jdo.option.ConnectionDriverName</name>
<value>com.mysql.jdbc.Driver</value>
</property>

export HADOOP_MAPRED_HOME=/usr/lib/hadoop-mapreduce

# sudo -u hdfs hadoop fs -mkdir /user/hive
# sudo -u hdfs hadoop fs -chown hive /user/hive
# sudo -u hdfs hadoop fs -mkdir /user/hive/warehouse
# sudo -u hdfs hadoop fs -chmod 1777 /user/hive/warehouse
# sudo -u hdfs hadoop fs -chown hive /user/hive/warehouse

# vim /etc/hive/conf/hive-env.sh
export JAVA_HOME=/opt/programs/jdk1.7.0_67

# service hive-metastore start
# service hive-server2 start

$ hive -e'create table t(id int);'
$ hive -e'select * from t limit 2;'
$ hive -e'select id from t;'

$ beeline
beeline> !connect jdbc:hive2://localhost:10000；

# yum install hive-hbase -y

$ ADD JAR /usr/lib/hive/lib/zookeeper.jar;
$ ADD JAR /usr/lib/hive/lib/hbase.jar;
$ ADD JAR /usr/lib/hive/lib/hive-hbase-handler-<hive_version>.jar
# guava 包的版本以实际版本为准。
$ ADD JAR /usr/lib/hive/lib/guava-11.0.2.jar;

ADD JAR /usr/lib/hive/lib/zookeeper.jar;
ADD JAR /usr/lib/hive/lib/hive-hbase-handler.jar;
ADD JAR /usr/lib/hbase/lib/guava-12.0.1.jar;
ADD JAR /usr/lib/hbase/hbase-client.jar;
ADD JAR /usr/lib/hbase/hbase-common.jar;
ADD JAR /usr/lib/hbase/hbase-hadoop-compat.jar;
ADD JAR /usr/lib/hbase/hbase-hadoop2-compat.jar;
ADD JAR /usr/lib/hbase/hbase-protocol.jar;
ADD JAR /usr/lib/hbase/hbase-server.jar;

172.16.57.74 bd-ops-test-74 impala-state-store impala-catalog impala-server 
172.16.57.75 bd-ops-test-75 impala-server
172.16.57.76 bd-ops-test-76 impala-server
172.16.57.77 bd-ops-test-77 impala-server

yum install impala-state-store impala-catalog impala-server -y

yum install impala-server -y

# find / -name impala
/var/run/impala
/var/lib/alternatives/impala
/var/log/impala
/usr/lib/impala
/etc/alternatives/impala
/etc/default/impala
/etc/impala
/etc/default/impala

IMPALA_CATALOG_SERVICE_HOST=bd-ops-test-74
IMPALA_STATE_STORE_HOST=bd-ops-test-74
IMPALA_STATE_STORE_PORT=24000
IMPALA_BACKEND_PORT=22000
IMPALA_LOG_DIR=/var/log/impala
IMPALA_CATALOG_ARGS=" -log_dir=${IMPALA_LOG_DIR} -sentry_config=/etc/impala/conf/sentry-site.xml"
IMPALA_STATE_STORE_ARGS=" -log_dir=${IMPALA_LOG_DIR} -state_store_port=${IMPALA_STATE_STORE_PORT}"
IMPALA_SERVER_ARGS=" \
-log_dir=${IMPALA_LOG_DIR} \
-use_local_tz_for_unix_timestamp_conversions=true \
-convert_legacy_hive_parquet_utc_timestamps=true \
-catalog_service_host=${IMPALA_CATALOG_SERVICE_HOST} \
-state_store_port=${IMPALA_STATE_STORE_PORT} \
-use_statestore \
-state_store_host=${IMPALA_STATE_STORE_HOST} \
-be_port=${IMPALA_BACKEND_PORT} \
-server_name=server1\
-sentry_config=/etc/impala/conf/sentry-site.xml"
ENABLE_CORE_DUMPS=false
# LIBHDFS_OPTS=-Djava.library.path=/usr/lib/impala/lib
# MYSQL_CONNECTOR_JAR=/usr/share/java/mysql-connector-java.jar
# IMPALA_BIN=/usr/lib/impala/sbin
# IMPALA_HOME=/usr/lib/impala
# HIVE_HOME=/usr/lib/hive
# HBASE_HOME=/usr/lib/hbase
# IMPALA_CONF_DIR=/etc/impala/conf
# HADOOP_CONF_DIR=/etc/impala/conf
# HIVE_CONF_DIR=/etc/impala/conf
# HBASE_CONF_DIR=/etc/impala/conf

<property>
<name>dfs.client.read.shortcircuit</name>
<value>true</value>
</property>
<property>
<name>dfs.domain.socket.path</name>
<value>/var/run/hadoop-hdfs/dn._PORT</value>
</property>
<property>
<name>dfs.datanode.hdfs-blocks-metadata.enabled</name>
<value>true</value>
</property>

# mkdir -p /var/run/hadoop-hdfs

sudo -u hdfs hadoop fs -mkdir /user/impala
sudo -u hdfs hadoop fs -chown impala /user/impala

# groups impala
impala : impala hadoop hdfs hive

# service impala-state-store start
# service impala-catalog start

#impala-shell 
Starting Impala Shell without Kerberos authentication
Connected to bd-dev-hadoop-70:21000
Server version: impalad version 2.3.0-cdh5.5.1 RELEASE (build 73bf5bc5afbb47aa7eab06cfbf6023ba8cb74f3c)
***********************************************************************************
Welcome to the Impala shell. Copyright (c) 2015 Cloudera, Inc. All rights reserved.
(Impala Shell v2.3.0-cdh5.5.1 (73bf5bc) built on Wed Dec 2 10:39:33 PST 2015)
After running a query, type SUMMARY to see a summary of where time was spent.
***********************************************************************************
[bd-dev-hadoop-70:21000] > invalidate metadata;

#impala-shell -h
Usage: impala_shell.py [options]
Options:
-h, --help show this help message and exit
-i IMPALAD, --impalad=IMPALAD
<host:port> of impalad to connect to
[default: bd-dev-hadoop-70:21000]
-q QUERY, --query=QUERY
Execute a query without the shell [default: none]
-f QUERY_FILE, --query_file=QUERY_FILE
Execute the queries in the query file, delimited by ;
[default: none]
-k, --kerberos Connect to a kerberized impalad [default: False]
-o OUTPUT_FILE, --output_file=OUTPUT_FILE
If set, query results are written to the given file.
Results from multiple semicolon-terminated queries
will be appended to the same file [default: none]
-B, --delimited Output rows in delimited mode [default: False]
--print_header Print column names in delimited mode when pretty-
printed. [default: False]
--output_delimiter=OUTPUT_DELIMITER
Field delimiter to use for output in delimited mode
[default: \t]
-s KERBEROS_SERVICE_NAME, --kerberos_service_name=KERBEROS_SERVICE_NAME
Service name of a kerberized impalad [default: impala]
-V, --verbose Verbose output [default: True]
-p, --show_profiles Always display query profiles after execution
[default: False]
--quiet Disable verbose output [default: False]
-v, --version Print version information [default: False]
-c, --ignore_query_failure
Continue on query failure [default: False]
-r, --refresh_after_connect
Refresh Impala catalog after connecting
[default: False]
-d DEFAULT_DB, --database=DEFAULT_DB
Issues a use database command on startup
[default: none]
-l, --ldap Use LDAP to authenticate with Impala. Impala must be
configured to allow LDAP authentication.
[default: False]
-u USER, --user=USER User to authenticate with. [default: root]
--ssl Connect to Impala via SSL-secured connection
[default: False]
--ca_cert=CA_CERT Full path to certificate file used to authenticate
Impala's SSL certificate. May either be a copy of
Impala's certificate (for self-signed certs) or the
certificate of a trusted third-party CA. If not set,
but SSL is enabled, the shell will NOT verify Impala's
server certificate [default: none]
--config_file=CONFIG_FILE
Specify the configuration file to load options. File
must have case-sensitive '[impala]' header. Specifying
this option within a config file will have no effect.
Only specify this as a option in the commandline.
[default: /root/.impalarc]
--live_summary Print a query summary every 1s while the query is
running. [default: False]
--live_progress Print a query progress every 1s while the query is
running. [default: False]
--auth_creds_ok_in_clear
If set, LDAP authentication may be used with an
insecure connection to Impala. WARNING: Authentication
credentials will therefore be sent unencrypted, and
may be vulnerable to attack. [default: none]

impala-shell -i '172.16.57.74:21000' -r -q "select * from test" -B --output_delimiter="\t" -o result.txt