Flume采集数据到hdfs:
1、启动HDFS
start-dfs.sh
2、启动YARN
start-yarn.sh
3、将flume上传到hdp-1的apps中,解压
tar -zxvf flume-1.6.0
4、配置文件
vi /etc/profile
export FLUME_HOME=/root/apps/flume-1.6.0
export PATH=$FLUME_HOME/bin:$PATH
soure /etc/profile
4、在flume-1.6.0/conf新建文本dome.loggeer.properties
# Name the components on this agent
a1.sources = r1
a1.sinks = k1
a1.channels = c1
# Describe/configure the source
a1.sources.r1.type = spooldir
# 根据需要修改监控日志目录: nginx为:/usr/local/nginx/logs
a1.sources.r1.spoolDir = /usr/local/nginx/logs
a1.sources.r1.fileHeader = true
a1.sources.r1.interceptors = i1
a1.sources.r1.interceptors.i1.type = timestamp
# Describe the sink
a1.sinks.k1.type = hdfs
# 收集到hdfs的地址
a1.sinks.k1.hdfs.path = hdfs://hdp-1:9000/output/flume
a1.sinks.k1.hdfs.writeFormat = Text
a1.sinks.k1.hdfs.fileType = DataStream
a1.sinks.k1.hdfs.rollInterval = 10
a1.sinks.k1.hdfs.rollSize = 0
a1.sinks.k1.hdfs.rollCount = 0
a1.sinks.k1.hdfs.filePrefix = %Y-%m-%d-%H-%M-%S
a1.sinks.k1.hdfs.useLocalTimeStamp = true
# Use a channel which buffers events in file
a1.channels.c1.type = file
a1.channels.c1.checkpointDir = /home/hadoop/flume/checkpoint
a1.channels.c1.dataDirs = /home/hadoop/flume/data
# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1
5、根目录中新建flume包: flume下makeflume.sh
[root@hdp-1 flume]#cd flume
[root@hdp-1 flume]# ll
总用量 4
-rwxr-xr-x. 1 root root 58 10月 10 11:52 makeflume.sh
makeflume.sh存储数据脚本:
while ture
do
echo 'date' >> access.flume
slpee 0.1
done
6、启动flume
$FLUME_HOME/bin/flume-ng agent \-c conf \-n a1 \-f $FLUME_HOME/conf/dome.logger.properties \-Dflume.root.logger=DEBUG,console
7、查看日志是否被收集
cd /usr/local/nginx/logs/
8、查看HDFS响应的目录
hadoop fs -ls /
nginx安装配置及运用
1、将web项目(作用:产生日志)重新编译(compile)成功后,打成jar包(package),上传到hdp-1,并运行jar包,
cd apps/
java -jar demo-0.0.1-SNAPSHOT.jar
2、安装make
yum -y install gcc automake autoconf libtool make
安装g++
yum install gcc gcc-c++
安装openssl
yum -y install openssl openssl-devel
安装PCRE库到apps
运行安装pcre-8.39
./configure
make
make install
安装zlib库到apps
运行安装zlib-1.2.11
./configure
make
make install
安装nginx到apps,与上同理,运行安装
3、启动nginx
cd /usr/local/nginx/sbin
./nginx
在浏览器中输入你的节点的ip地址,查看是否启动成功
停止
./nginx -s stop
./nginx -s quit
./nginx -s quit:此方式停止步骤是待nginx进程处理任务完毕进行停止。
./nginx -s stop:此方式相当于先查出nginx进程id再使用kill命令强制杀掉进程。
重新加载
./nginx -s reload
4、修改配置文件
vi /apps/nginx-1.1.10/conf/nginx.conf
#user nobody;
worker_processes 1;
#error_log logs/error.log;
#error_log logs/error.log notice;
#error_log logs/error.log info;
#pid logs/nginx.pid;
events {
worker_connections 1024;
}
http {
include mime.types;
default_type application/octet-stream;
#将main放出
log_format main '$remote_addr - $remote_user [$time_local] "$request" '
'$status $body_bytes_sent "$http_referer" '
'"$http_user_agent" "$http_x_forwarded_for"';
#access_log logs/access.log main;
sendfile on;
#tcp_nopush on;
#keepalive_timeout 0;
keepalive_timeout 65;
#gzip on;
upstream frame-tomcat{
server 127.0.0.1:1997;#修改
}
server {
listen 80;
server_name hdp-1;#修改
#charset koi8-r;
#access_log logs/host.access.log main;
location / {
root html;
index index.html index.htm;
}
#error_page 404 /404.html;
# redirect server error pages to the static page /50x.html
#
error_page 500 502 503 504 /50x.html;
location = /50x.html {
root html;
}
}
server {
listen 80;
server_name localhost;
#charset koi8-r;
access_log logs/log.frame.access.log main;
location / {
# root html;
# index index.html index.htm;
proxy_pass http://frame-tomcat;
}
error_page 500 502 503 504 /50x.html;
location = /50x.html {
root html;
}
# proxy the PHP scripts to Apache listening on 127.0.0.1:80
#
#location ~ \.php$ {
# proxy_pass http://127.0.0.1;#修改
#}
# pass the PHP scripts to FastCGI server listening on 127.0.0.1:9000
#
#location ~ \.php$ {
# root html;
# fastcgi_pass 127.0.0.1:9000;
# fastcgi_index index.php;
# fastcgi_param SCRIPT_FILENAME /scripts$fastcgi_script_name;
# include fastcgi_params;
#}
# deny access to .htaccess files, if Apache's document root
# concurs with nginx's one
#
#location ~ /\.ht {
# deny all;
#}
}
# another virtual host using mix of IP-, name-, and port-based configuration
#
#server {
# listen 8000;
# listen somename:8080;
# server_name somename alias another.alias;
# location / {
# root html;
# index index.html index.htm;
# }
#}
# HTTPS server
#
#server {
# listen 443;
# server_name localhost;
# ssl on;
# ssl_certificate cert.pem;
# ssl_certificate_key cert.key;
# ssl_session_timeout 5m;
# ssl_protocols SSLv2 SSLv3 TLSv1;
# ssl_ciphers HIGH:!aNULL:!MD5;
# ssl_prefer_server_ciphers on;
# location / {
# root html;
# index index.html index.htm;
# }
#}
}
在hdp-4上也启动运行jar包,安装nginx,浏览器搜索两个地址就会访问到同一个网页,nginx起的作用是转发作用,一个是tomcat服务器,一个是nginx服务器