cd /mnt/data
mkdir filebeat-es
cd filebeat-es/

# 下載filbeat 到/mnt/data/filebeat-es
# 下載地址：https://www.elastic.co/downloads/past-releases/filebeat-8-15-5
tar -zxvf filebeat-8.15.5-linux-x86_64.tar.gz -C ./?
mv filebeat-8.15.5-linux-x86_64 filebeat-es?
cd filebeat-es/?

vi filebeat.yml?

###################### 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
# 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.
# 這里定義類型是log
- type: log
  # Change to true to enable this input configuration.
  enabled: true
  # Paths that should be crawled and fetched. Glob based paths.
  # 這個(gè)地方是nginx日志的實(shí)際路徑，可以根據(jù)實(shí)際進(jìn)行修改
  paths:
    - /mnt/data/openresty/nginx/logs/access.log
    #- c:\programdata\elasticsearch\logs\*
  # 這個(gè)地方是從末尾開(kāi)始讀取寫(xiě)入ES，通常nginx的日志文件很大 耗費(fèi)CPU資源，歷史的log不再處理
  tail_files: true
  offset:
    initial: end
  # Exclude lines. A list of regular expressions to match. It drops the lines that are
  # matching any regular expression from the list.
  # exclude_lines: ['^127.0.0.1']
  # 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
  # 這個(gè)地方是給采集日志添加logtype列，通過(guò)es查詢的時(shí)候可以辨別 類似自定義標(biāo)簽，可以修改
  # 比如某個(gè)主機(jī)上安裝了兩個(gè)用途不同的openresty實(shí)例，或者多個(gè)實(shí)例組成的負(fù)載，用于辨別。
  fields:
    logtype: "mynginx01_openresty"
  #  level: debug
  #  review: 1
  fields_under_root: true
  json.enabled: true
  json.keys_under_root: true
  ### 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: ^\[
  # multiline.pattern: '^[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\s-'
  # Defines if the pattern set under pattern should be negated or not. Default is false.
  # multiline.negate: true
  # 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
#------------------------------------------------------------------------------------------
- type: log
  # Change to true to enable this input configuration.
  enabled: true
  # Paths that should be crawled and fetched. Glob based paths.
  # 這個(gè)地方是我第二個(gè)nginx日志的實(shí)際路徑，可以根據(jù)實(shí)際進(jìn)行修改或者刪除
  paths:
    - /mnt/data/openresty2/nginx/logs/access.log
    #- c:\programdata\elasticsearch\logs\*
  # 參考第一段
  tail_files: true
  offset:
    initial: end
  # Exclude lines. A list of regular expressions to match. It drops the lines that are
  # matching any regular expression from the list.
  # exclude_lines: ['^127.0.0.1']
  # 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:
     logtype: "mynginx01_openresty2"
  #  level: debug
  #  review: 1
  fields_under_root: true
  json.enabled: true
  json.keys_under_root: true
  ### 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: ^\[
  # multiline.pattern: '^[0-9]{4}/[0-9]{2}/[0-9]{2}\s[0-9]{2}:[0-9]{2}:[0-9]{2}\s'
  # Defines if the pattern set under pattern should be negated or not. Default is false.
  # multiline.negate: true
  # 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.shutdown_timeout: 5s
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.ilm.enabled: false
setup.data_streams.enabled: false
setup.template.name: "nginx_template"
setup.template.pattern: "nginx*"
setup.template.priority: 200
setup.template.settings:
index.number_of_shards: 5
  #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` 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
# 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
  # 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:
#============================= Elastic Cloud ==================================
# These settings simplify using filebeat with the Elastic Cloud (https://cloud.elastic.co/).
# The cloud.id setting overwrites the `output.elasticsearch.hosts` and
# `setup.kibana.host` options.
# You can find the `cloud.id` in the Elastic Cloud web UI.
#cloud.id:
# The cloud.auth setting overwrites the `output.elasticsearch.username` and
# `output.elasticsearch.password` settings. The format is `<user>:<pass>`.
#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: ["1.2.3.4:5678"]
  data_stream: false
  pipeline: "pipeline-nginx-plaintext"
  index: "nginx_%{+yyyyMMdd}"
  preset: balanced
  # 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 =====================================
#================================ Logging =====================================
logging.level: info
logging.to_files: true
logging.files:
  path: /mnt/data/filebeat-es
  name: filebeat.log
  keepfiles: 3
  permissions: 0644
# 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:
#================================= Migration ==================================
# This allows to enable 6.7 migration aliases
#migration.6_to_7.enabled: true

- type: log
  enabled: true
  paths:
    - /mnt/data/openresty/nginx/logs/access.log
  # --------------------------------------------------------
  # ?? 性能優(yōu)化核心配置：解決 CPU 飆升問(wèn)題
  # --------------------------------------------------------
  tail_files: true       # 啟動(dòng)時(shí)忽略文件中的舊數(shù)據(jù)，只看新產(chǎn)生的數(shù)據(jù)
  offset:
    initial: end         # 配合 tail_files，明確指定偏移量從文件末尾開(kāi)始
  # --------------------------------------------------------
  # ??? 標(biāo)簽與分類：區(qū)分不同業(yè)務(wù)來(lái)源
  # --------------------------------------------------------
  fields:
    logtype: "mynginx01_openresty" # 給該日志打上特定標(biāo)簽，用于后續(xù)生成索引名
  fields_under_root: true           # 將 logtype 字段放在根節(jié)點(diǎn)，而不是 fields.logtype
  # --------------------------------------------------------
  # ?? JSON 解析：在 Agent 端直接解析
  # --------------------------------------------------------
  json.enabled: true         # 開(kāi)啟 JSON 解析
  json.keys_under_root: true # 解析后的字段（如 status, uri）直接放在根節(jié)點(diǎn)

# ==================== Elasticsearch template setting ==========================
setup.ilm.enabled: false          # 禁用索引生命周期管理 (ILM)
setup.data_streams.enabled: false # 禁用數(shù)據(jù)流 (Data Streams)
# 定義模板
setup.template.name: "nginx_template"   # 模板名稱
setup.template.pattern: "nginx*"        # 模板匹配的索引模式
setup.template.priority: 200            # 優(yōu)先級(jí) 200 (默認(rèn)是 150)，確保你的模板覆蓋系統(tǒng)默認(rèn)模板
setup.template.settings:
  index.number_of_shards: 5             # 強(qiáng)制設(shè)置每個(gè)索引有 5 個(gè)主分片

output.elasticsearch:
  hosts: ["1.2.3.4:5678"]
  data_stream: false               # 再次確認(rèn)禁用數(shù)據(jù)流輸出
  # ?? 關(guān)鍵點(diǎn)：Ingest Pipeline
  pipeline: "pipeline-nginx-plaintext" 
  # 索引命名規(guī)則
  index: "nginx_%{+yyyyMMdd}"      # 按天生成索引，例如 nginx_20251217
  preset: balanced                 # 性能預(yù)設(shè)，平衡吞吐量和資源消耗

logging.level: info
logging.to_files: true
logging.files:
  path: /mnt/data/filebeat-es  # 日志存放路徑
  name: filebeat.log
  keepfiles: 3                 # 只保留最近 3 個(gè)文件，防止占滿磁盤
  permissions: 0644

./filebeat test config -c filebeat.yml
./filebeat test output -c filebeat.yml

?輸出說(shuō)明：
? 連接正常：輸出類似以下內(nèi)容（顯示 ES 版本、連接成功）：
elasticsearch: http://1.2.3.4:5678...
  parse url... OK
  connection...
    parse host... OK
    dns lookup... OK
    addresses: 1.2.3.4
    dial up... OK
  TLS... WARN secure connection disabled
  talk to server... OK
  version: 8.15.5 

cd ..
mv filebeat-es /usr/local/

vi /usr/lib/systemd/system/filebeat-es.service

[Unit]
Description=Filebeat sends log data to Elasticsearch
Documentation=https://www.elastic.co/docs/beats/filebeat
Wants=network-online.target
After=network-online.target
[Service]
Type=simple
User=root
Group=root
ExecStart=/usr/local/filebeat-es/filebeat -c /usr/local/filebeat-es/filebeat.yml
ExecReload=/bin/kill -HUP $MAINPID
Restart=always
RestartSec=5
LimitNOFILE=65535
[Install]
WantedBy=multi-user.target

systemctl daemon-reload 
systemctl start filebeat-es
systemctl status filebeat-es
systemctl enable filebeat-es

file_identity:
  path: ~

?/usr/local/filebeat-es/filebeat setup --index-management -c /usr/local/filebeat-es/filebeat.yml

?curl -X PUT "http://1.2.3.4:5678/_template/nginx_template" -H "Content-Type: application/json" -d '{
  "index_patterns": ["nginx_*"],
  "settings": {"index.number_of_shards":1,"index.number_of_replicas":0},
  "mappings": {"dynamic": true}
}'

?rm -rf /usr/local/filebeat-es/data/registry/filebeat/filestream/*
systemctl restart filebeat-es

?curl -X PUT "http://1.2.3.4:5678/_ingest/pipeline/pipeline-nginx-plaintext" -H "Content-Type: application/json" -d '{
  "description": "Nginx日志解析管道",
  "processors": [
    {"grok": {"field": "message", "patterns": ["%{HTTPDATE:time_local_str}"]}},
    {"date": {"field": "time_local_str", "target_field": "time_local", "formats": ["dd/MMM/yyyy:HH:mm:ss Z"]}}
  ]
}'