Fluentdインストールしてみた。Forwarder＆Aggregator ノード 、Elasticsearch出力

感想

abコマンドでApacheに大量アクセスをすると、td-agentプロセスがCPU100％となってしまう。
ログパースをForwarderで行っているので、これが原因なのか、Fluentdは単純tailしているので、この処理自体が重いのか、、まではまだ解明できておらず。。

本番で使うにはこの部分の検証が必要かと思いました。

環境

• CentOS7

ログ収集対象

• Apache combinedに%D(応答時間)追加

LogFormat "%h %l %u %t \"%r\" %>s %b %D \"%{Referer}i\" \"%{User-Agent}i\"" combined

• Postfix

/var/log/maillog

• Syslog

/var/log/messages

構成

Apache,Poxtrix,Syslog【Forwarderノード】 → 【Aggregatorノード】 → Elasticsearch ← Kibana

###Forwarderノード

• ログパース
• Forwarderノードのホスト名タグ付与

###Aggregatorノード

• apacheログに対しGeoIPを付与

インストール

参照
https://docs.fluentd.org/v1.0/articles/install-by-rpm

curl -L https://toolbelt.treasuredata.com/sh/install-redhat-td-agent3.sh | sh

Forwarderノード　プラグインインストール

td-agent-gem install fluent-plugin-multi-format-parser
td-agent-gem install fluent-plugin-filter_typecast

Aggregatorノード　プラグインインストール

td-agent-gem install fluent-plugin-elasticsearch
yum install epel-release
yum install geoip-devel
td-agent-gem install fluent-plugin-geoip

systemd編集

vi td-agent.service

User=root
Group=root

Forwarderノード設定

/etc/td-agent/td-agent.conf

#### Global Setting
<source>
  @type monitor_agent
  bind 0.0.0.0
  port 24220
</source>

#### Source
### Syslog
<source>
  @type tail
  tag syslog.messages
  format syslog
  path /var/log/messages
  pos_file /var/log/td-agent/syslog.messages.pos
</source>

### Apache
<source>
  @type tail
  tag apache.access
  format /^(?<host>[^ ]*) [^ ]* (?<user>[^ ]*) \[(?<time>[^\]]*)\] "(?<method>\S+)(?: +(?<path>[^ ]*) +\S*)?" (?<code>[^ ]*) (?<size>[^ ]*) (?<response_time>[^ ]*)(?: "(?<referer>[^\"]*)" "(?<agent>[^\"]*)")?$/
  time_format %d/%b/%Y:%H:%M:%S %z
  types code:integer,size:integer,response_time:float
  path /var/log/httpd/access_log
  pos_file /var/log/td-agent/apache_access.pos
  read_from_head true
</source>
<source>
  @type tail
  tag    apache.error
  format apache_error
  path   /var/log/httpd/error_log
  pos_file /var/log/td-agent/apache_error.pos
  read_from_head true
</source>

### Postfix
<source>
  @type tail
  tag postfix.maillog
  path /var/log/maillog
  pos_file /var/log/td-agent/postfix.maillog.pos
  read_from_head true
  <parse>
    @type multi_format
    <pattern>
      format /^(?<time>[^ ]* {1,2}[^ ]* [^ ]*) (?<host>[^ ]+) (?<ident>[a-zA-Z0-9_\/\.\-]*)(?:\[(?<pid>[0-9]+)\])?[^\:]*\: (?<queue_id>[0-9A-F]+): ?(to=(<(?<to>[^>]+)>)?)?,( ?(orig_to=<(?<orig_to>[^>]+)>),)? ?(relay=(?<relay>[^ ]+)), ?(delay=(?<delay>[^ ]+)), ?(delays=(?<delays>[^ ]+)), ?(dsn=(?<dsn>[^ ]+)), ?(status=(?<status>[^,]+)) \((?<status_msg>.*)\)/
      time_format %b %d %H:%M:%S
    </pattern>
    <pattern>
      format /^(?<time>[^ ]* {1,2}[^ ]* [^ ]*) (?<host>[^ ]+) (?<ident>[a-zA-Z0-9_\/\.\-]*)(?:\[(?<pid>[0-9]+)\])?[^\:]*\: (?<queue_id>[0-9A-F]+): ?(from=(<(?<from>[^>]+)>)?)? *(?<message>.*)$/
      time_format %b %d %H:%M:%S
    </pattern>
    <pattern>
      format /^(?<time>[^ ]* {1,2}[^ ]* [^ ]*) (?<host>[^ ]+) (?<ident>[a-zA-Z0-9_\/\.\-]*)(?:\[(?<pid>[0-9]+)\])?[^\:]*\: (?<queue_id>[0-9A-F]+): *(?<message>.*)$/
      time_format %b %d %H:%M:%S
    </pattern>
    <pattern>
      format /^(?<time>[^ ]* {1,2}[^ ]* [^ ]*) (?<host>[^ ]+) (?<ident>[a-zA-Z0-9_\/\.\-]*)(?:\[(?<pid>[0-9]+)\])?[^\:]*\: *(?<message>.*)$/
      time_format %b %d %H:%M:%S
    </pattern>
    <pattern>
      format none
    </pattern>
  </parse>
</source>

#### Filter
### Add MyHostname
<filter **>
  @type record_transformer
  <record>
    hostname ${hostname}
  </record>
</filter>

### Postfix
<filter postfix.maillog>
  @type typecast
  types pid:float,delay:float
</filter>

#### Output
<match **>
  @type forward
  <server>
    host 10.0.0.20
    port 24224
  </server>
  <buffer>
    @type file
    path /var/log/td-agent/buffer
    flush_interval 1s
  </buffer>
</match>

##Aggregatorノード設定
/etc/td-agent/td-agent.conf

#### Global Setting
<source>
  @type monitor_agent
  bind 0.0.0.0
  port 24220
</source>

#### Source
### Forwarder
<source>
  @type forward
  bind 0.0.0.0
  port 24224
</source>

### Add GeoIP
<filter apache.access>
  @type geoip
  geoip_lookup_keys host
  skip_adding_null_record true
  <record>
    location_properties  '{ "lat" : ${location.latitude["host"]}, "lon" : ${location.longitude["host"]} }'
    location_string      ${location.latitude["host"]},${location.longitude["host"]}
    location_array       '[${location.longitude["host"]},${location.latitude["host"]}]'
  </record>
</filter>

#### Output
### syslog
<match syslog.messages>
  @type elasticsearch
  host localhost
  port 9200
  logstash_format true
  logstash_prefix syslog.messages
  <buffer>
    @type file
    path /var/log/td-agent/buffer/syslog.messages
    flush_interval 1s
  </buffer>
</match>

### Apache
<match apache.access>
  @type elasticsearch
  host localhost
  port 9200
  logstash_format true
  logstash_prefix apache.access
  <buffer>
    @type file
    path /var/log/td-agent/buffer/apache.access
    flush_interval 1s
  </buffer>
</match>
<match apache.error>
  @type elasticsearch
  host localhost
  port 9200
  logstash_format true
  logstash_prefix apache.error
  <buffer>
    @type file
    path /var/log/td-agent/buffer/apache.error
    flush_interval 1s
  </buffer>
</match>

### Postfix
<match postfix.maillog>
  @type elasticsearch
  host localhost
  port 9200
  logstash_format true
  logstash_prefix postfix.maillog
  <buffer>
    @type file
    path /var/log/td-agent/buffer/postfix.maillog
    flush_interval 1s
  </buffer>
</match>