Class: Fluent::ElasticsearchOutput

Inherits:
BufferedOutput
  • Object
show all
Includes:
ElasticsearchIndexTemplate, SetTagKeyMixin
Defined in:
lib/fluent/plugin/out_elasticsearch.rb

Direct Known Subclasses

ElasticsearchOutputDynamic

Defined Under Namespace

Classes: ConnectionFailure, TimeParser

Instance Method Summary collapse

Constructor Details

#initialize ⇒ ElasticsearchOutput

Returns a new instance of ElasticsearchOutput.



62
63
64
65
 
# File 'lib/fluent/plugin/out_elasticsearch.rb', line 62

def initialize
  super
  @time_parser = TimeParser.new(@time_key_format, @router)
end

Instance Method Details

#append_record_to_messages(op, meta, record, msgs) ⇒ Object 



205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
 
# File 'lib/fluent/plugin/out_elasticsearch.rb', line 205

def append_record_to_messages(op, meta, record, msgs)
  case op
  when "update", "upsert"
    if meta.has_key?("_id")
      msgs << { "update" => meta }
      msgs << update_body(record, op)
    end
  when "create"
    if meta.has_key?("_id")
      msgs << { "create" => meta }
      msgs << record
    end
  when "index"
    msgs << { "index" => meta }
    msgs << record
  end
end

#client ⇒ Object 



128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
 
# File 'lib/fluent/plugin/out_elasticsearch.rb', line 128

def client
  @_es ||= begin
    excon_options = { client_key: @client_key, client_cert: @client_cert, client_key_pass: @client_key_pass }
    adapter_conf = lambda {|f| f.adapter :excon, excon_options }
    transport = Elasticsearch::Transport::Transport::HTTP::Faraday.new(get_connection_options.merge(
                                                                        options: {
                                                                          reload_connections: @reload_connections,
                                                                          reload_on_failure: @reload_on_failure,
                                                                          resurrect_after: @resurrect_after,
                                                                          retry_on_failure: 5,
                                                                          transport_options: {
                                                                            request: { timeout: @request_timeout },
                                                                            ssl: { verify: @ssl_verify, ca_file: @ca_file }
                                                                          }
                                                                        }), &adapter_conf)
    es = Elasticsearch::Client.new transport: transport

    begin
      raise ConnectionFailure, "Can not reach Elasticsearch cluster (#{connection_options_description})!" unless es.ping
    rescue *es.transport.host_unreachable_exceptions => e
      raise ConnectionFailure, "Can not reach Elasticsearch cluster (#{connection_options_description})! #{e.message}"
    end

    log.info "Connection opened to Elasticsearch cluster => #{connection_options_description}"
    es
  end
end

#configure(conf) ⇒ Object 



67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
 
# File 'lib/fluent/plugin/out_elasticsearch.rb', line 67

def configure(conf)
  super
  @time_parser = TimeParser.new(@time_key_format, @router)

  if @remove_keys
    @remove_keys = @remove_keys.split(/\s*,\s*/)
  end

  if @target_index_key && @target_index_key.is_a?(String)
    @target_index_key = @target_index_key.split '.'
  end

  if @target_type_key && @target_type_key.is_a?(String)
    @target_type_key = @target_type_key.split '.'
  end

  if @remove_keys_on_update && @remove_keys_on_update.is_a?(String)
    @remove_keys_on_update = @remove_keys_on_update.split ','
  end

  if @template_name && @template_file
    template_install(@template_name, @template_file)
  end
end

#connection_options_description ⇒ Object 



189
190
191
192
193
194
195
 
# File 'lib/fluent/plugin/out_elasticsearch.rb', line 189

def connection_options_description
  get_connection_options[:hosts].map do |host_info|
    attributes = host_info.dup
    attributes[:password] = 'obfuscated' if attributes.has_key?(:password)
    attributes.inspect
  end.join(', ')
end

#flatten_record(record, prefix = []) ⇒ Object 



245
246
247
248
249
250
251
252
253
254
255
256
257
258
 
# File 'lib/fluent/plugin/out_elasticsearch.rb', line 245

def flatten_record(record, prefix=[])
  ret = {}
  if record.is_a? Hash
    record.each { |key, value|
      ret.merge! flatten_record(value, prefix + [key.to_s])
    }
  elsif record.is_a? Array
    # Don't mess with arrays, leave them unprocessed
    ret.merge!({prefix.join(@flatten_hashes_separator) => record})
  else
    return {prefix.join(@flatten_hashes_separator) => record}
  end
  ret
end

#format(tag, time, record) ⇒ Object 



197
198
199
 
# File 'lib/fluent/plugin/out_elasticsearch.rb', line 197

def format(tag, time, record)
  [tag, time, record].to_msgpack
end

#get_connection_options ⇒ Object 



156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
 
# File 'lib/fluent/plugin/out_elasticsearch.rb', line 156

def get_connection_options
  raise "`password` must be present if `user` is present" if @user && !@password

  hosts = if @hosts
    @hosts.split(',').map do |host_str|
      # Support legacy hosts format host:port,host:port,host:port...
      if host_str.match(%r{^[^:]+(\:\d+)?$})
        {
          host:   host_str.split(':')[0],
          port:   (host_str.split(':')[1] || @port).to_i,
          scheme: @scheme
        }
      else
        # New hosts format expects URLs such as http://logs.foo.com,https://john:[email protected]/elastic
        uri = URI(host_str)
        %w(user password path).inject(host: uri.host, port: uri.port, scheme: uri.scheme) do |hash, key|
          hash[key.to_sym] = uri.public_send(key) unless uri.public_send(key).nil? || uri.public_send(key) == ''
          hash
        end
      end
    end.compact
  else
    [{host: @host, port: @port, scheme: @scheme}]
  end.each do |host|
    host.merge!(user: @user, password: @password) if !host[:user] && @user
    host.merge!(path: @path) if !host[:path] && @path
  end

  {
    hosts: hosts
  }
end

#get_parent_of(record, path) ⇒ Object

returns [parent, child_key] of child described by path array in record’s tree returns [nil, child_key] if path doesnt exist in record



324
325
326
327
328
329
 
# File 'lib/fluent/plugin/out_elasticsearch.rb', line 324

def get_parent_of(record, path)
  return [nil, nil] unless path

  parent_object = path[0..-2].reduce(record) { |a, e| a.is_a?(Hash) ? a[e] : nil }
  [parent_object, path[-1]]
end

#remove_keys(record) ⇒ Object 



236
237
238
239
240
241
242
243
 
# File 'lib/fluent/plugin/out_elasticsearch.rb', line 236

def remove_keys(record)
  keys = record[@remove_keys_on_update_key] || @remove_keys_on_update || []
  record.delete(@remove_keys_on_update_key)
  return record unless keys.any?
  record = record.dup
  keys.each { |key| record.delete(key) }
  record
end

#send(data) ⇒ Object 



331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
 
# File 'lib/fluent/plugin/out_elasticsearch.rb', line 331

def send(data)
  retries = 0
  begin
    client.bulk body: data
  rescue *client.transport.host_unreachable_exceptions => e
    if retries < 2
      retries += 1
      @_es = nil
      log.warn "Could not push logs to Elasticsearch, resetting connection and trying again. #{e.message}"
      sleep 2**retries
      retry
    end
    raise ConnectionFailure, "Could not push logs to Elasticsearch after #{retries} retries. #{e.message}"
  end
end

#shutdown ⇒ Object 



201
202
203
 
# File 'lib/fluent/plugin/out_elasticsearch.rb', line 201

def shutdown
  super
end

#start ⇒ Object 



92
93
94
 
# File 'lib/fluent/plugin/out_elasticsearch.rb', line 92

def start
  super
end

#update_body(record, op) ⇒ Object 



223
224
225
226
227
228
229
230
231
232
233
234
 
# File 'lib/fluent/plugin/out_elasticsearch.rb', line 223

def update_body(record, op)
  update = remove_keys(record)
  body = { "doc" => update }
  if  op == "upsert"
    if update == record
      body["doc_as_upsert"] = true
    else
      body["upsert"] = record
    end
  end
  body
end

#write(chunk) ⇒ Object 



260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
 
# File 'lib/fluent/plugin/out_elasticsearch.rb', line 260

def write(chunk)
  bulk_message = []

  chunk.msgpack_each do |tag, time, record|
    if @flatten_hashes
      record = flatten_record(record)
    end

    next unless record.is_a? Hash
    target_index_parent, target_index_child_key = get_parent_of(record, @target_index_key)
    if target_index_parent && target_index_parent[target_index_child_key]
      target_index = target_index_parent.delete(target_index_child_key)
    elsif @logstash_format
      if record.has_key?("@timestamp")
        dt = record["@timestamp"]
        dt = @time_parser.parse(record["@timestamp"], time)
      elsif record.has_key?(@time_key)
        dt = @time_parser.parse(record[@time_key], time)
        record['@timestamp'] = record[@time_key] unless time_key_exclude_timestamp
      else
        dt = Time.at(time).to_datetime
        record.merge!({"@timestamp" => dt.to_s})
      end
      dt = dt.new_offset(0) if @utc_index
      target_index = "#{@logstash_prefix}-#{dt.strftime(@logstash_dateformat)}"
    else
      target_index = @index_name
    end

    # Change target_index to lower-case since Elasticsearch doesn't
    # allow upper-case characters in index names.
    target_index = target_index.downcase
    if @include_tag_key
      record.merge!(@tag_key => tag)
    end

    target_type_parent, target_type_child_key = get_parent_of(record, @target_type_key)
    if target_type_parent && target_type_parent[target_type_child_key]
      target_type = target_type_parent.delete(target_type_child_key)
    else
      target_type = @type_name
    end

    meta = {"_index" => target_index, "_type" => target_type}

    @meta_config_map ||= { 'id_key' => '_id', 'parent_key' => '_parent', 'routing_key' => '_routing' }
    @meta_config_map.each_pair do |config_name, meta_key|
      record_key = self.instance_variable_get("@#{config_name}")
      meta[meta_key] = record[record_key] if record_key && record[record_key]
    end

    if @remove_keys
      @remove_keys.each { |key| record.delete(key) }
    end

    append_record_to_messages(@write_operation, meta, record, bulk_message)
  end

  send(bulk_message) unless bulk_message.empty?
  bulk_message.clear
end