Logstash 经过过滤器

Question

我正在尝试使用 ELK 堆栈中的 elapsed.rb 过滤器，但似乎无法弄清楚。我对 grok 不是很熟悉，我相信那是我的问题所在。有人可以帮忙吗？

示例日志文件：

{
    "application_name": "Application.exe",
    "machine_name": "Machine1",
    "user_name": "testuser",
    "entry_date": "2015-03-12T18:12:23.5187552Z",
    "chef_environment_name": "chefenvironment1",
    "chef_logging_cookbook_version": "0.1.9",
    "logging_level": "INFO",
    "performance": {
        "process_name": "account_search",
        "process_id": "Machine1|1|635617555435187552",
        "event_type": "enter"
    },
    "thread_name": "1",
    "logger_name": "TestLogger",
    "@version": "1",
    "@timestamp": "2015-03-12T18:18:48.918Z",
    "type": "rabbit",
    "log_from": "rabbit"
}

{
    "application_name": "Application.exe",
    "machine_name": "Machine1",
    "user_name": "testuser",
    "entry_date": "2015-03-12T18:12:23.7527462Z",
    "chef_environment_name": "chefenvironment1",
    "chef_logging_cookbook_version": "0.1.9",
    "logging_level": "INFO",
    "performance": {
        "process_name": "account_search",
        "process_id": "Machine1|1|635617555435187552",
        "event_type": "exit"
    },
    "thread_name": "1",
    "logger_name": "TestLogger",
    "@version": "1",
    "@timestamp": "2015-03-12T18:18:48.920Z",
    "type": "rabbit",
    "log_from": "rabbit"
}

示例 .conf 文件

input {
  rabbitmq {
    host => "SERVERNAME"
    add_field => ["log_from", "rabbit"]
    type => "rabbit"
    user => "testuser"
    password => "testuser"
    durable => "true"
    exchange => "Logging"
    queue => "testqueue"
    codec => "json"
    exclusive => "false"
    passive => "true"
  }
}


filter {

   grok {
     match => ["message", "%{TIMESTAMP_ISO8601} START id: (?<process_id>.*)"]
     add_tag => [ "taskStarted" ]
   }

   grok {
     match => ["message", "%{TIMESTAMP_ISO8601} END id: (?<process_id>.*)"]
     add_tag => [ "taskTerminated"]
   }

   elapsed {
    start_tag => "taskStarted"
    end_tag => "taskTerminated"
    unique_id_field => "process_id"
    timeout => 10000
    new_event_on_match => false
  }
}

output {
  file {
    codec => json { charset => "UTF-8" }
    path => "test.log"
  }
}

Answer 1

您不需要使用 grok 过滤器，因为您的输入已经是 json 格式。你需要做这样的事情：

if [performance][event_type] == "enter" {
  mutate { add_tag => ["taskStarted"] }
} else if [performance][event_type] == "exit" {
  mutate { add_tag => ["taskTerminated"] }
}
elapsed {
  start_tag => "taskStarted"
  end_tag => "taskTerminated"
  unique_id_field => "performance.process_id"
  timeout => 10000
  new_event_on_match => false
}

我对此持否定态度 unique_id_field -- 我认为它应该有效，但如果无效，您可以将其更改为仅 process_id 和 add_field => { "process_id" => "%{[performance][process_id]}" }

Logstash 经过过滤器

Logstash elapsed filter

elasticsearch

logstash

groc