搭建Hbase步骤
1.查看linux系统最大进程数和最大文件打开数
ulimit-a
查看open files(最大文件打开数)、max user processes(最大进程数),默认为1024。
2.设置linux系统最大进程数和最大文件打开数
su
vim /etc/security/limits.conf
例如对root和hadoop用户进行配置:
root soft nproc 50000
root hard nproc 50000
root soft nofile 25535
root hard nofile 25535
hadoop soft nproc 50000
hadoop hard nproc 50000
hadoop soft nofile 25535
hadoop hard nofile 25535
3.调整linux内核参数
vim /etc/sysctl.conf
添加下述配置:
net.ipv4.ip_forward= 0
net.ipv4.conf.default.rp_filter= 1
net.ipv4.conf.default.accept_source_route= 0
kernel.core_users_pid= 1
net.ipv4.tcp_syncookies= 1
net.bridge.bridge-nf-call-ip6tables= 0
net.bridge.bridge-nf-call-iptables= 0
net.bridge.bridge-nf-call-arptables= 0
kernel.mggmnb= 65536
kernel.mggmax= 65536
kernel.shmmax= 68719476736
kernel.shmall= 268435456
net.ipv4.tcp_max_syn_backlog= 65000
net.core.netdev_max_backlog= 32768
net.core.somaxconn= 32768
fs.file-max= 65000
net.core.wmem_default= 8388608
net.core.rmem_default= 8388608
net.core.rmem_max= 16777216
net.core.wmem_max= 16777216
net.ipv4.tcp_timestamps= 1
net.ipv4.tcp_synack_retries= 2
net.ipv4.tcp_syn_retries= 2
net.ipv4.tcp_mem= 94500000 915000000 927000000
net.ipv4.tcp_max_orphans= 3276800
net.ipv4.tcp_tw_reuse= 1
net.ipv4.tcp_tw_recycle= 1
net.ipv4.tcp_keepalive_time= 1200
net.ipv4.tcp_syncookies= 1
net.ipv4.tcp_fin_timeout= 10
net.ipv4.tcp_keepalive_intvl= 15
net.ipv4.tcp_keepalive_probes= 3
net.ipv4.ip_local_port_range= 1024 65535
net.ipv4.conf.eml.send_redirects= 0
net.ipv4.conf.lo.send_redirects= 0
net.ipv4.conf.default.send_redirects= 0
net.ipv4.conf.all.send_redirects= 0
net.ipv4.icmp_echo_ignore_broadcasts= 1
net.ipv4.conf.eml.accept_source_route= 0
net.ipv4.conf.lo.accept_source_route= 0
net.ipv4.conf.default.accept_source_route= 0
net.ipv4.conf.all.accept_source_route= 0
net.ipv4.icmp_ignore_bogus_error_responses= 1
kernel.core_pattern= /tmp/core
vm.overcommit_memory= 1
执行生效:
sysctl -p
4.配置环境
(1)修改hbase-env.sh
cd ./hbase-1.2.0-cdh5.7.1/conf/
vim hbase-env.sh
具体设置如下:
# 配置Java home
export JAVA_HOME=/home/hadoop/app/jdk1.7.0_79
# 设置HBase内存堆的大小
export HBASE_HEAPSIZE=1024
# 设置HMaster最大可用内存
export HBASE_MASTER_OPTS="-Xmx512m"
# 设置HRegionServer最大可用内存
export HBASE_REGIONSERVER_OPTS="-Xmx512m"
# 设置HBase的日志目录
export HBASE_LOG_DIR=${HBASE_HOME}/logs
# 设置HBase的pid目录
export HBASE_PID_DIR=${HBASE_HOME}/pids
# 使用独立的ZooKeeper集群
export HBASE_MANAGES_ZK=false
(2)配置hbase-site.xml
vim hbase-site.xml
配置如下:
<!-- 关闭分布式日志拆分 -->
<property>
<name>hbase.master.distributed.log.splitting</name>
<value>false</value>
</property>
<!-- hbase部署至hdfs的根路径 -->
<property>
<name>hbase.rootdir</name>
<value>hdfs://educluster/hbase</value>
</property>
<!-- 开启分布式模式 -->
<property>
<name>hbase.cluster.distributed</name>
<value>true</value>
</property>
<!-- 设置HMaster的端口 -->
<property>
<name>hbase.master.port</name>
<value>60000</value>
</property>
<!-- 指定ZooKeeper集群位置 -->
<property>
<name>hbase.zookeeper.quorum</name>
<value>namenode1,namenode2,datanode</value>
</property>
<!--指定Zookeepe快照存储目录,需要与ZooKeeper集群上配置相一致 -->
<property>
<name>hbase.zookeeper.property.dataDir</name>
<value>/opt/hadoopdata/zookeeperdata</value>
</property>
<!-- hbase客户端rpc扫描一次获取的行数 -->
<property>
<name>hbase.client.scanner.caching</name>
<value>2000</value>
</property>
<!-- HRegion分裂前最大的文件大小(10G) -->
<property>
<name>hbase.hregion.max.filesize</name>
<value>10737418240</value>
</property>
<!-- 设置HMaster的http端口 -->
<property>
<name>hbase.master.info.port</name>
<value>16010</value>
</property>
<!-- 指定缓存文件存储的路径 -->
<property>
<name>hbase.tmp.dir</name>
<value>/home/hadoop/app/cdh/hbase-1.2.0-cdh5.7.1/tmp</value>
</property>
<!-- 指定ZooKeeper集群端口 -->
<property>
<name>hbase.zookeeper.property.clientPort</name>
<value>2181</value>
</property>
<!-- HRegionServer中最大的region数量 -->
<property>
<name>hbase.regionserver.reginoSplitLimit</name>
<value>2000</value>
</property>
<!-- StoreFile的个数超过这个数就开始合并 -->
<property>
<name>hbase.hstore.compactionThreshold</name>
<value>6</value>
</property>
<!-- 当某一个region的storefile个数达到该值则block写入,等待compact -->
<property>
<name>hbase.hstore.blockingStoreFiles</name>
<value>14</value>
</property>
<!-- 超过memstore大小的倍数达到该值则block所有写入请求,自我保护 -->
<property>
<name>hbase.hregion.memstore.block.multiplier</name>
<value>20</value>
</property>
<!-- service工作的sleep间隔 -->
<property>
<name>hbase.server.thread.wakefrequency</name>
<value>500</value>
</property>
<!-- ZooKeeper客户端同时访问的并发连接数 -->
<property>
<name>hbase.zookeeper.property.maxClientCnxns</name>
<value>2000</value>
</property>
<!-- 根据业务情况进行配置 -->
<property>
<name>hbase.regionserver.global.memstore.lowerLimit</name>
<value>0.3</value>
</property>
<property>
<name>hbase.regionserver.global.memstore.upperLimit</name>
<value>0.39</value>
</property>
<property>
<name>hbase.block.cache.size</name>
<value>0.4</value>
</property>
<!-- RegionServer的请求处理IO线程数 -->
<property>
<name>hbase.reginoserver.handler.count</name>
<value>300</value>
</property>
<!-- 客户端最大重试次数 -->
<property>
<name>hbase.client.retries.number</name>
<value>5</value>
</property>
<!-- 客户端重试的休眠时间 -->
<property>
<name>hbase.client.pause</name>
<value>100</value>
</property>
</configuration>
待续...