|NO.Z.00012|——————————|BigDataEnd|——|Hadoop&PB级数仓.V04|——|PB数仓.v04|会员活跃度分析|agent配置&Flume配置|

一、Agent的配置

### --- 配置Flume.agent配置

[root@hadoop02 ~]# vim /data/yanqidw/conf/flume-log2hdfs1.conf
a1.sources = r1
a1.sinks = k1
a1.channels = c1

# taildir source
a1.sources.r1.type = TAILDIR
a1.sources.r1.positionFile = /data/yanqidw/conf/startlog_position.json
a1.sources.r1.filegroups = f1
a1.sources.r1.filegroups.f1 = /data/yanqidw/logs/start/.*log

# memorychannel
a1.channels.c1.type = memory
a1.channels.c1.capacity = 100000
a1.channels.c1.transactionCapacity = 2000

# hdfs sink
a1.sinks.k1.type = hdfs
a1.sinks.k1.hdfs.path = /user/data/logs/start/%Y-%m-%d/
a1.sinks.k1.hdfs.filePrefix = startlog.
a1.sinks.k1.hdfs.fileType = DataStream

# 配置文件滚动方式（文件大小32M）
a1.sinks.k1.hdfs.rollSize = 33554432
a1.sinks.k1.hdfs.rollCount = 0
a1.sinks.k1.hdfs.rollInterval = 0
a1.sinks.k1.hdfs.idleTimeout = 0
a1.sinks.k1.hdfs.minBlockReplicas = 1

# 向hdfs上刷新的event的个数
a1.sinks.k1.hdfs.batchSize = 1000

# 使用本地时间
a1.sinks.k1.hdfs.useLocalTimeStamp = true
# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1

二、Flume的优化配置

### --- 启动agent环境准备
~~~     # 查看本地文件结构

[root@hadoop02 ~]# tree /data/
/data/
└── yanqidw
    ├── conf
    │   ├── flume-log2hdfs1.conf
    │   ├── flumetest1.conf
    │   └── startlog_position.json
    ├── jars
    ├── logs
    │   ├── data
    │   │   └── start0802.log
    │   ├── event
    │   ├── source
    │   └── start
    │       └── start0802.log
    └── script

~~~     # 把该文件夹上传到hdfs服务中

[root@hadoop02 ~]# hdfs dfs -mkdir /usr/data/
[root@hadoop02 ~]# hdfs dfs  -put /data/yanqidw/* /usr/data/

### --- 启动agent

[root@hadoop02 ~]# flume-ng agent --conf-file /data/yanqidw/conf/flume-log2hdfs1.conf \
-name a1 -Dflume.root.logger=INFO,console

### --- 报错现象
~~~     向 /data/yanqidw/logs/ 目录中放入日志文件，报错：
~~~     # 缺省情况下 Flume jvm堆最大分配20m，这个值太小，需要调整。

java.lang.OutOfMemoryError: GC overhead limit exceeded

### --- 解决方案：
~~~     在 $FLUME_HOME/conf/flume-env.sh 中增加以下内容

[root@hadoop02 ~]# vim $FLUME_HOME/conf/flume-env.sh
export JAVA_OPTS="-Xms4000m -Xmx4000m -Dcom.sun.management.jmxremote"

### --- 重新启动agent
~~~     # 要想使配置文件生效，还要在命令行中指定配置文件目录

[root@hadoop02 ~]# flume-ng agent --conf /opt/yanqi/servers/flume-1.9.0/conf \
--conf-file /data/yanqidw/conf/flume-log2hdfs1.conf -name a1 \
-Dflume.root.logger=INFO,console
 
[root@hadoop02 ~]#  flume-ng agent --conf-file /data/yanqidw/conf/flume-log2hdfs1.conf \
-name a1 -Dflume.root.logger=INFO,console

~~~     # 查看hdfs日志文件

[root@hadoop02 ~]# hdfs dfs -ls /user/data/logs/start/2021-09-28/startlog..1632808271900.tmp
-rw-r--r--   5 root supergroup     256333 2021-09-28 13:51 /user/data/logs/start/2021-09-28/startlog..1632808271900.tmp

### --- 再次拷贝文件到/data/yanqidw/logs/start/目录下

[root@hadoop02 ~]# cp /data/yanqidw/logs/data/start0802.log /data/yanqidw/logs/start/start2.log
[root@hadoop02 ~]# cp /data/yanqidw/logs/data/start0802.log /data/yanqidw/logs/start/start3.log

[root@hadoop02 ~]# hdfs dfs -ls /user/data/logs/start/2021-09-28/
Found 3 items
-rw-r--r--   5 root supergroup   33691250 2021-09-28 14:05 /user/data/logs/start/2021-09-28/startlog..1632808271900
-rw-r--r--   5 root supergroup   33691476 2021-09-28 14:06 /user/data/logs/start/2021-09-28/startlog..1632808271901
-rw-r--r--   5 root supergroup      58189 2021-09-28 14:06 /user/data/logs/start/2021-09-28/startlog..1632808271902.tmp

### --- Flume内存参数设置及优化：

~~~     根据日志数据量的大小，Jvm堆一般要设置为4G或更高
~~~     -Xms -Xmx 最好设置一致，减少内存抖动带来的性能影响
~~~     存在的问题：Flume放数据时，使用本地时间；不理会日志的时间戳

---

 

 

 

 

 

 

 

 

 

---

Walter Savage Landor:strove with none,for none was worth my strife.Nature I loved and, next to Nature, Art:I warm'd both hands before the fire of life.It sinks, and I am ready to depart

                                                                                                                                                   ——W.S.Landor

---