本文主要分为三个步骤：
1）openresty安装，openresty包含了nginx+lua；
2）filebeat安装；
3）lua脚本编写；
一：openresty安装
本次安装的版本是openresty-1.19.3.1.tar.gz，直接在你想安装的文件夹解压即可；
在安装之前防止缺少相应的依赖包：yum install pcre-devel openssl-devel gcc curl；
进入刚刚解压的文件夹，如果没有权限进如文件夹可以修改相应权限（sudo chmod 755 /usr/local/openresty -R），进入文件夹后执行下列命令：
./configure
make
sudo make install
如果没有权限请用sudo执行；
其他问题可参考下列链接：http://openresty.org/cn/installation.html
image.png
二：filebeat安装
这次安装的版本是：filebeat-6.6.0-linux-x86_64.tar.gz；
在你想安装的页面解压即可；
添加filebeat_nginx.yml,对其进行修改，从nginx中拉去日志，并将日志推到kafka，
###################### Filebeat Configuration Example #########################
# This file is an example configuration file highlighting only the most common
# options. The filebeat.reference.yml file from the same directory contains all the
# supported options with more comments. You can use it as a reference.
#
# You can find the full configuration reference here:
# [https://www.elastic.co/guide/en/beats/filebeat/index.html](https://www.elastic.co/guide/en/beats/filebeat/index.html)
# For more available modules and options, please see the filebeat.reference.yml sample
# configuration file.
#=========================== Filebeat inputs =============================
filebeat.inputs:
# Each - is an input. Most options can be set at the input level, so
# you can use different inputs for various configurations.
# Below are the input specific configurations.
- type: log
# Change to true to enable this input configuration.
enabled: false
# Paths that should be crawled and fetched. Glob based paths.
paths:
- /var/log/*.log
#- c:\programdata\elasticsearch\logs\*
# Exclude lines. A list of regular expressions to match. It drops the lines that are
# matching any regular expression from the list.
#exclude_lines: ['^DBG']
# Include lines. A list of regular expressions to match. It exports the lines that are
# matching any regular expression from the list.
#include_lines: ['^ERR', '^WARN']
# Exclude files. A list of regular expressions to match. Filebeat drops the files that
# are matching any regular expression from the list. By default, no files are dropped.
#exclude_files: ['.gz$']
# Optional additional fields. These fields can be freely picked
# to add additional information to the crawled log files for filtering
#fields:
# level: debug
# review: 1
### Multiline options
# Multiline can be used for log messages spanning multiple lines. This is common
# for Java Stack Traces or C-Line Continuation
# The regexp Pattern that has to be matched. The example pattern matches all lines starting with [
#multiline.pattern: ^\[
# Defines if the pattern set under pattern should be negated or not. Default is false.
#multiline.negate: false
# Match can be set to "after" or "before". It is used to define if lines should be append to a pattern
# that was (not) matched before or after or as long as a pattern is not matched based on negate.
# Note: After is the equivalent to previous and before is the equivalent to to next in Logstash
#multiline.match: after
#============================= Filebeat modules ===============================
filebeat.config.modules:
# Glob pattern for configuration loading
path: ${path.config}/modules.d/*.yml
# Set to true to enable config reloading
reload.enabled: false
# Period on which files under path should be checked for changes
#reload.period: 10s
#==================== Elasticsearch template setting ==========================
setup.template.settings:
index.number_of_shards: 3
#index.codec: best_compression
#_source.enabled: false
#================================ General =====================================
# The name of the shipper that publishes the network data. It can be used to group
# all the transactions sent by a single shipper in the web interface.
#name:
# The tags of the shipper are included in their own field with each
# transaction published.
#tags: ["service-X", "web-tier"]
# Optional fields that you can specify to add additional information to the
# output.
#fields:
# env: staging
#============================== Dashboards =====================================
# These settings control loading the sample dashboards to the Kibana index. Loading
# the dashboards is disabled by default and can be enabled either by setting the
# options here, or by using the `-setup` CLI flag or the `setup` command.
#setup.dashboards.enabled: false
# The URL from where to download the dashboards archive. By default this URL
# has a value which is computed based on the Beat name and version. For released
# versions, this URL points to the dashboard archive on the [artifacts.elastic.co](http://artifacts.elastic.co/)
# website.
#setup.dashboards.url:
#============================== Kibana =====================================
# Starting with Beats version 6.0.0, the dashboards are loaded via the Kibana API.
# This requires a Kibana endpoint configuration.
setup.kibana:
# Kibana Host
# Scheme and port can be left out and will be set to the default (http and 5601)
# In case you specify and additional path, the scheme is required: [http://localhost:5601/path](http://localhost:5601/path)
# IPv6 addresses should always be defined as: https://[2001:db8::1]:5601
#host: "localhost:5601"
# Kibana Space ID
# ID of the Kibana Space into which the dashboards should be loaded. By default,
# the Default Space will be used.
#[space.id](http://space.id/):
#============================= Elastic Cloud ==================================
# These settings simplify using filebeat with the Elastic Cloud ([https://cloud.elastic.co/](https://cloud.elastic.co/)).
# The [cloud.id](http://cloud.id/) setting overwrites the `output.elasticsearch.hosts` and
# `setup.kibana.host` options.
# You can find the `[cloud.id](http://cloud.id/)` in the Elastic Cloud web UI.
#[cloud.id](http://cloud.id/):
# The cloud.auth setting overwrites the `output.elasticsearch.username` and
# `output.elasticsearch.password` settings. The format is `:`.
#cloud.auth:
#================================ Outputs =====================================
# Configure what output to use when sending the data collected by the beat.
#-------------------------- Elasticsearch output ------------------------------
#output.elasticsearch:
# Array of hosts to connect to.
# hosts: ["localhost:9200"]
# Enabled ilm (beta) to use index lifecycle management instead daily indices.
#ilm.enabled: false
# Optional protocol and basic auth credentials.
#protocol: "https"
#username: "elastic"
#password: "changeme"
#----------------------------- Logstash output --------------------------------
#output.logstash:
# The Logstash hosts
#hosts: ["localhost:5044"]
# Optional SSL. By default is off.
# List of root certificates for HTTPS server verifications
#ssl.certificate_authorities: ["/etc/pki/root/ca.pem"]
# Certificate for SSL client authentication
#ssl.certificate: "/etc/pki/client/cert.pem"
# Client Certificate Key
#ssl.key: "/etc/pki/client/cert.key"
#================================ Processors =====================================
# Configure processors to enhance or manipulate events generated by the beat.
processors:
- add_host_metadata: ~
- add_cloud_metadata: ~
#================================ Logging =====================================
# Sets log level. The default log level is info.
# Available log levels are: error, warning, info, debug
#logging.level: debug
# At debug level, you can selectively enable logging only for some components.
# To enable all selectors use ["*"]. Examples of other selectors are "beat",
# "publish", "service".
#logging.selectors: ["*"]
#============================== Xpack Monitoring ===============================
# filebeat can export internal metrics to a central Elasticsearch monitoring
# cluster. This requires xpack monitoring to be enabled in Elasticsearch. The
# reporting is disabled by default.
# Set to true to enable the monitoring reporter.
#xpack.monitoring.enabled: false
# Uncomment to send the metrics to Elasticsearch. Most settings from the
# Elasticsearch output are accepted here as well. Any setting that is not set is
# automatically inherited from the Elasticsearch output configuration, so if you
# have the Elasticsearch output configured, you can simply uncomment the
# following line.
#xpack.monitoring.elasticsearch:
#=======================put log to kafka ==============
filebeat.modules:
- module: nginx
access:
enabled: true
var.paths: ["/usr/local/openresty/nginx/logs/access-map.log"]
error:
enabled: true
var.paths: ["/usr/local/openresty/nginx/logs/error.log"]
#----------------------------------Kafka output--------------------------------#
output.kafka:
version: "1.0.1"
enabled: true
hosts: ['ip:9092', 'ip8:9092', 'ip49:9092']
topic: 'topicName'
required_acks: 1 #default
compression: gzip #default
max_message_bytes: 1000000 #default
codec.format:
string: '%{[message]}'
filebeat启动命令：sudo ./filebeat -e -c filebeat_nginx.yml；
三：nginx.conf配置：
image.png
image.png
nginx输出输入：
log_format main '$remote_addr - $remote_user [$time_local] "$request" '
'$status $body_bytes_sent "$http_referer" '
'"$http_user_agent" "$http_x_forwarded_for" "$request_uri" "$request_body" "$request_body" server_name:"$server_name" "$upstream_addr" "$scheme" resp_body:"$resp_body" ';
解决中文乱码
log_escape_non_ascii off;
lua脚本编写：
lua_need_request_body on;
set $resp_body "";
body_filter_by_lua '
local resp_body = string.sub(ngx.arg[1], 1, 1000)
ngx.ctx.buffered = (ngx.ctx.buffered or "") .. resp_body
if ngx.arg[2] then
ngx.var.resp_body = ngx.ctx.buffered
end
';