SpringCloud—搭建ELK日志采集与分析系统

mkdir /usr/local/java

vi /etc/profile

JAVA_HOME=/usr/local/java/jdk1.8.0_64
PATH=$JAVA_HOME/bin:$PATH
CLASSPATH=$JAVA_HOME/jre/lib/ext:$JAVA_HOME/lib/tools.jar
export PATH JAVA_HOME CLASSPATH

source /etc/profile

yum install java-1.8.0-openjdk* -y

tar -zxvf elasticsearch-8.0.0-linux-x86_64.tar.gz

mv elasticsearch-8.0.0 elasticsearch

# 创建用户组
groupadd elasticsearch
# 创建用户并添加至用户组
useradd elasticsearch -g elasticsearch
# 更改elasticsearch密码，设置一个自己需要的密码，这里设置为和用户名一样：El12345678
passwd elasticsearch 

mkdir -p /data/elasticsearch/data
mkdir -p /data/elasticsearch/log
chown -R elasticsearch:elasticsearch /data/elasticsearch*operation.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.
  #prospector.scanner.exclude_files: ['.gz$']
  # Optional additional fields. These fields can be freely picked
  # to add additional information to the crawled log files for filtering
  fields:
    topic: operation_log
  #  level: debug
  #  review: 1
# filestream is an input for collecting log messages from files.
- type: filestream
  # Change to true to enable this input configuration.
  enabled: true
  # Paths that should be crawled and fetched. Glob based paths.
  paths:
    - /data/gitegg/log*debug.log
    #- c:\programdata\elasticsearch\logs\*
  # Exclude lines. A list of regular expressions to match. It drops the lines that are
  # matching any regular expression from the list.
  #exclude_lines: ['^DBG']
  # Include lines. A list of regular expressions to match. It exports the lines that are
  # matching any regular expression from the list.
  #include_lines: ['^ERR', '^WARN']
  # Exclude files. A list of regular expressions to match. Filebeat drops the files that
  # are matching any regular expression from the list. By default, no files are dropped.
  #prospector.scanner.exclude_files: ['.gz$']
  # Optional additional fields. These fields can be freely picked
  # to add additional information to the crawled log files for filtering
  fields:
    topic: debugger_log
  #  level: debug
  #  review: 1
# filestream is an input for collecting log messages from files.
- type: filestream
  # Change to true to enable this input configuration.
  enabled: true
  # Paths that should be crawled and fetched. Glob based paths.
  paths:
    - /usr/local/nginx/logs/access.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.
  #prospector.scanner.exclude_files: ['.gz$']
  # Optional additional fields. These fields can be freely picked
  # to add additional information to the crawled log files for filtering
  fields:
    topic: nginx_log
  #  level: debug
  #  review: 1
# ============================== 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.number_of_replicas: 1
  #index.codec: best_compression
  #_source.enabled: false
# 允许自动生成index模板
setup.template.enabled: true
# # 生成index模板时字段配置文件
setup.template.fields: fields.yml
# # 如果存在模块则覆盖
setup.template.overwrite: true
# # 生成index模板的名称
setup.template.name: "gitegg_log" 
# # 生成index模板匹配的index格式 
setup.template.pattern: "filebeat-*" 
#索引生命周期管理ilm功能默认开启，开启的情况下索引名称只能为filebeat-*， 通过setup.ilm.enabled: false进行关闭；
setup.ilm.pattern: "{now/d}"
setup.ilm.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: true
# 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: "172.16.20.220:5601"
  # Optional protocol and basic auth credentials.
  #protocol: "https"
  username: "elastic"
  password: "123456"
  # Optional HTTP path
  #path: ""
  # Optional Kibana space ID.
  #space.id: ""
  # Custom HTTP headers to add to each request
  #headers:
  #  X-My-Header: Contents of the header
  # Use SSL settings for HTTPS.
  #ssl.enabled: true
# =============================== 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 `:`.
#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"]
  # Protocol - either `http` (default) or `https`.
  #protocol: "https"
  # Authentication credentials - either API key or username/password.
  #api_key: "id:api_key"
  #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"
# -------------------------------- Kafka Output --------------------------------
output.kafka:
  # Boolean flag to enable or disable the output module.
  enabled: true
  # The list of Kafka broker addresses from which to fetch the cluster metadata.
  # The cluster metadata contain the actual Kafka brokers events are published
  # to.
  hosts: ["172.16.20.220:9092","172.16.20.221:9092","172.16.20.222:9092"]
  # The Kafka topic used for produced events. The setting can be a format string
  # using any event field. To set the topic from document type use `%{[type]}`.
  topic: '%{[fields.topic]}'
  # The Kafka event key setting. Use format string to create a unique event key.
  # By default no event key will be generated.
  #key: ''
  # The Kafka event partitioning strategy. Default hashing strategy is `hash`
  # using the `output.kafka.key` setting or randomly distributes events if
  # `output.kafka.key` is not configured.
  partition.hash:
    # If enabled, events will only be published to partitions with reachable
    # leaders. Default is false.
    reachable_only: true
    # Configure alternative event field names used to compute the hash value.
    # If empty `output.kafka.key` setting will be used.
    # Default value is empty list.
    #hash: []
  # Authentication details. Password is required if username is set.
  #username: ''
  #password: ''
  # SASL authentication mechanism used. Can be one of PLAIN, SCRAM-SHA-256 or SCRAM-SHA-512.
  # Defaults to PLAIN when `username` and `password` are configured.
  #sasl.mechanism: ''
  # Kafka version Filebeat is assumed to run against. Defaults to the "1.0.0".
  #version: '1.0.0'
  # Configure JSON encoding
  #codec.json:
    # Pretty-print JSON event
    #pretty: false
    # Configure escaping HTML symbols in strings.
    #escape_html: false
  # Metadata update configuration. Metadata contains leader information
  # used to decide which broker to use when publishing.
  #metadata:
    # Max metadata request retry attempts when cluster is in middle of leader
    # election. Defaults to 3 retries.
    #retry.max: 3
    # Wait time between retries during leader elections. Default is 250ms.
    #retry.backoff: 250ms
    # Refresh metadata interval. Defaults to every 10 minutes.
    #refresh_frequency: 10m
    # Strategy for fetching the topics metadata from the broker. Default is false.
    #full: false
  # The number of concurrent load-balanced Kafka output workers.
  #worker: 1
  # The number of times to retry publishing an event after a publishing failure.
  # After the specified number of retries, events are typically dropped.
  # Some Beats, such as Filebeat, ignore the max_retries setting and retry until
  # all events are published.  Set max_retries to a value less than 0 to retry
  # until all events are published. The default is 3.
  #max_retries: 3
  # The number of seconds to wait before trying to republish to Kafka
  # after a network error. After waiting backoff.init seconds, the Beat
  # tries to republish. If the attempt fails, the backoff timer is increased
  # exponentially up to backoff.max. After a successful publish, the backoff
  # timer is reset. The default is 1s.
  #backoff.init: 1s
  # The maximum number of seconds to wait before attempting to republish to
  # Kafka after a network error. The default is 60s.
  #backoff.max: 60s
  # The maximum number of events to bulk in a single Kafka request. The default
  # is 2048.
  #bulk_max_size: 2048
  # Duration to wait before sending bulk Kafka request. 0 is no delay. The default
  # is 0.
  #bulk_flush_frequency: 0s
  # The number of seconds to wait for responses from the Kafka brokers before
  # timing out. The default is 30s.
  #timeout: 30s
  # The maximum duration a broker will wait for number of required ACKs. The
  # default is 10s.
  #broker_timeout: 10s
  # The number of messages buffered for each Kafka broker. The default is 256.
  #channel_buffer_size: 256
  # The keep-alive period for an active network connection. If 0s, keep-alives
  # are disabled. The default is 0 seconds.
  #keep_alive: 0
  # Sets the output compression codec. Must be one of none, snappy and gzip. The
  # default is gzip.
  compression: gzip
  # Set the compression level. Currently only gzip provides a compression level
  # between 0 and 9. The default value is chosen by the compression algorithm.
  #compression_level: 4
  # The maximum permitted size of JSON-encoded messages. Bigger messages will be
  # dropped. The default value is 1000000 (bytes). This value should be equal to
  # or less than the broker's message.max.bytes.
  max_message_bytes: 1000000
  # The ACK reliability level required from broker. 0=no response, 1=wait for
  # local commit, -1=wait for all replicas to commit. The default is 1.  Note:
  # If set to 0, no ACKs are returned by Kafka. Messages might be lost silently
  # on error.
  required_acks: 1
  # The configurable ClientID used for logging, debugging, and auditing
  # purposes.  The default is "beats".
  #client_id: beats
  # Use SSL settings for HTTPS.
  #ssl.enabled: true
  # Controls the verification of certificates. Valid values are:
  # * full, which verifies that the provided certificate is signed by a trusted
  # authority (CA) and also verifies that the server's hostname (or IP address)
  # matches the names identified within the certificate.
  # * strict, which verifies that the provided certificate is signed by a trusted
  # authority (CA) and also verifies that the server's hostname (or IP address)
  # matches the names identified within the certificate. If the Subject Alternative
  # Name is empty, it returns an error.
  # * certificate, which verifies that the provided certificate is signed by a
  # trusted authority (CA), but does not perform any hostname verification.
  #  * none, which performs no verification of the server's certificate. This
  # mode disables many of the security benefits of SSL/TLS and should only be used
  # after very careful consideration. It is primarily intended as a temporary
  # diagnostic mechanism when attempting to resolve TLS errors; its use in
  # production environments is strongly discouraged.
  # The default value is full.
  #ssl.verification_mode: full
  # List of supported/valid TLS versions. By default all TLS versions from 1.1
  # up to 1.3 are enabled.
  #ssl.supported_protocols: [TLSv1.1, TLSv1.2, TLSv1.3]
  # 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"
  # Optional passphrase for decrypting the certificate key.
  #ssl.key_passphrase: ''
  # Configure cipher suites to be used for SSL connections
  #ssl.cipher_suites: []
  # Configure curve types for ECDHE-based cipher suites
  #ssl.curve_types: []
  # Configure what types of renegotiation are supported. Valid options are
  # never, once, and freely. Default is never.
  #ssl.renegotiation: never
  # Configure a pin that can be used to do extra validation of the verified certificate chain,
  # this allow you to ensure that a specific certificate is used to validate the chain of trust.
  #
  # The pin is a base64 encoded string of the SHA-256 fingerprint.
  #ssl.ca_sha256: ""
  # A root CA HEX encoded fingerprint. During the SSL handshake if the
  # fingerprint matches the root CA certificate, it will be added to
  # the provided list of root CAs (`certificate_authorities`), if the
  # list is empty or not defined, the matching certificate will be the
  # only one in the list. Then the normal SSL validation happens.
  #ssl.ca_trusted_fingerprint: ""
  # Enable Kerberos support. Kerberos is automatically enabled if any Kerberos setting is set.
  #kerberos.enabled: true
  # Authentication type to use with Kerberos. Available options: keytab, password.
  #kerberos.auth_type: password
  # Path to the keytab file. It is used when auth_type is set to keytab.
  #kerberos.keytab: /etc/security/keytabs/kafka.keytab
  # Path to the Kerberos configuration.
  #kerberos.config_path: /etc/krb5.conf
  # The service name. Service principal name is contructed from
  # service_name/hostname@realm.
  #kerberos.service_name: kafka
  # Name of the Kerberos user.
  #kerberos.username: elastic
  # Password of the Kerberos user. It is used when auth_type is set to password.
  #kerberos.password: changeme
  # Kerberos realm.
  #kerberos.realm: ELASTIC
  # Enables Kerberos FAST authentication. This may
  # conflict with certain Active Directory configurations.
  #kerberos.enable_krb5_fast: false
# ================================= Processors =================================
processors:
  - add_host_metadata:
      when.not.contains.tags: forwarded
  - add_cloud_metadata: ~
  - add_docker_metadata: ~
  - add_kubernetes_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",
# "publisher", "service".
#logging.selectors: ["*"]
# ============================= X-Pack 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.
#monitoring.enabled: false
# Sets the UUID of the Elasticsearch cluster under which monitoring data for this
# Filebeat instance will appear in the Stack Monitoring UI. If output.elasticsearch
# is enabled, the UUID is derived from the Elasticsearch cluster referenced by output.elasticsearch.
#monitoring.cluster_uuid:
# Uncomment to send the metrics to Elasticsearch. Most settings from the
# Elasticsearch output are accepted here as well.
# Note that the settings should point to your Elasticsearch *monitoring* cluster.
# Any setting that is not set is automatically inherited from the Elasticsearch
# output configuration, so if you have the Elasticsearch output configured such
# that it is pointing to your Elasticsearch monitoring cluster, you can simply
# uncomment the following line.
#monitoring.elasticsearch:
# ============================== Instrumentation ===============================
# Instrumentation support for the filebeat.
#instrumentation:
    # Set to true to enable instrumentation of filebeat.
    #enabled: false
    # Environment in which filebeat is running on (eg: staging, production, etc.)
    #environment: ""
    # APM Server hosts to report instrumentation results to.
    #hosts:
    #  - http://localhost:8200
    # API Key for the APM Server(s).
    # If api_key is set then secret_token will be ignored.
    #api_key:
    # Secret token for the APM Server(s).
    #secret_token:
# ================================= Migration ==================================
# This allows to enable 6.7 migration aliases
#migration.6_to_7.enabled: true

./filebeat -e -c filebeat.yml

nohup ./filebeat -e -c filebeat.yml >/dev/null 2>&1 &

ps -ef |grep filebeat
kill -9 进程号

./kafka-console-consumer.sh --bootstrap-server 172.16.20.221:9092 --topic api_log
./kafka-console-consumer.sh --bootstrap-server 172.16.20.222:9092 --topic operation_log

echo "api log1111" > /data/gitegg/log/gitegg-service-system/api.log
echo "operation log1111" > /data/gitegg/log/gitegg-service-system/operation.log

echo "api log8888888888888888888888" > /data/gitegg/log/gitegg-service-system/api.log
echo "operation loggggggggggggggggggg" > /data/gitegg/log/gitegg-service-system/operation.log