Class: Fluent::KubernetesMetadataFilter

Inherits:
Filter
  • Object
show all
Includes:
KubernetesMetadata::CacheStrategy, KubernetesMetadata::Common, KubernetesMetadata::WatchNamespaces, KubernetesMetadata::WatchPods
Defined in:
lib/fluent/plugin/filter_kubernetes_metadata.rb

Constant Summary collapse

K8_POD_CA_CERT = 
'ca.crt'
K8_POD_TOKEN = 
'token'

Instance Method Summary collapse

Methods included from KubernetesMetadata::WatchPods

#start_pod_watch

Methods included from KubernetesMetadata::Common

#match_annotations, #parse_namespace_metadata, #parse_pod_metadata, #syms_to_strs

Methods included from KubernetesMetadata::WatchNamespaces

#start_namespace_watch

Methods included from KubernetesMetadata::CacheStrategy

#get_pod_metadata

Constructor Details

#initialize ⇒ KubernetesMetadataFilter

Returns a new instance of KubernetesMetadataFilter.



143
144
145
146
 
# File 'lib/fluent/plugin/filter_kubernetes_metadata.rb', line 143

def initialize
  super
  @prev_time = Time.now
end

Instance Method Details

#configure(conf) ⇒ Object 



148
149
150
151
152
153
154
155
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
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
 
# File 'lib/fluent/plugin/filter_kubernetes_metadata.rb', line 148

def configure(conf)
  super

  def log.trace?
    level == Fluent::Log::LEVEL_TRACE
  end

  require 'kubeclient'
  require 'active_support/core_ext/object/blank'
  require 'lru_redux'
  @stats = KubernetesMetadata::Stats.new

  if @de_dot && (@de_dot_separator =~ /\./).present?
    raise Fluent::ConfigError, "Invalid de_dot_separator: cannot be or contain '.'"
  end

  if @cache_ttl < 0
    log.info "Setting the cache TTL to :none because it was <= 0"
    @cache_ttl = :none
  end

  # Caches pod/namespace UID tuples for a given container UID.
  @id_cache = LruRedux::TTL::ThreadSafeCache.new(@cache_size, @cache_ttl)

  # Use the container UID as the key to fetch a hash containing pod metadata
  @cache = LruRedux::TTL::ThreadSafeCache.new(@cache_size, @cache_ttl)

  # Use the namespace UID as the key to fetch a hash containing namespace metadata
  @namespace_cache = LruRedux::TTL::ThreadSafeCache.new(@cache_size, @cache_ttl)

  @tag_to_kubernetes_name_regexp_compiled = Regexp.compile(@tag_to_kubernetes_name_regexp)
  @container_name_to_kubernetes_regexp_compiled = Regexp.compile(@container_name_to_kubernetes_regexp)

  # Use Kubernetes default service account if we're in a pod.
  if @kubernetes_url.nil?
    env_host = ENV['KUBERNETES_SERVICE_HOST']
    env_port = ENV['KUBERNETES_SERVICE_PORT']
    if env_host.present? && env_port.present?
      @kubernetes_url = "https://#{env_host}:#{env_port}/api"
    end
  end

  # Use SSL certificate and bearer token from Kubernetes service account.
  if Dir.exist?(@secret_dir)
    ca_cert = File.join(@secret_dir, K8_POD_CA_CERT)
    pod_token = File.join(@secret_dir, K8_POD_TOKEN)

    if !@ca_file.present? and File.exist?(ca_cert)
      @ca_file = ca_cert
    end

    if !@bearer_token_file.present? and File.exist?(pod_token)
      @bearer_token_file = pod_token
    end
  end

  if @kubernetes_url.present?

    ssl_options = {
        client_cert: @client_cert.present? ? OpenSSL::X509::Certificate.new(File.read(@client_cert)) : nil,
        client_key:  @client_key.present? ? OpenSSL::PKey::RSA.new(File.read(@client_key)) : nil,
        ca_file:     @ca_file,
        verify_ssl:  @verify_ssl ? OpenSSL::SSL::VERIFY_PEER : OpenSSL::SSL::VERIFY_NONE
    }

    auth_options = {}

    if @bearer_token_file.present?
      bearer_token = File.read(@bearer_token_file)
      auth_options[:bearer_token] = bearer_token
    end

    @client = Kubeclient::Client.new @kubernetes_url, @apiVersion,
                                     ssl_options: ssl_options,
                                     auth_options: auth_options

    begin
      @client.api_valid?
    rescue KubeException => kube_error
      raise Fluent::ConfigError, "Invalid Kubernetes API #{@apiVersion} endpoint #{@kubernetes_url}: #{kube_error.message}"
    end

    if @watch
      thread = Thread.new(self) { |this| this.start_pod_watch }
      thread.abort_on_exception = true
      namespace_thread = Thread.new(self) { |this| this.start_namespace_watch }
      namespace_thread.abort_on_exception = true
    end
  end
  if @use_journal
    log.debug "Will stream from the journal"
    self.class.class_eval { alias_method :filter_stream, :filter_stream_from_journal }
  else
    log.debug "Will stream from the files"
    self.class.class_eval { alias_method :filter_stream, :filter_stream_from_files }
  end

  @annotations_regexps = []
  @annotation_match.each do |regexp|
    begin
      @annotations_regexps << Regexp.compile(regexp)
    rescue RegexpError => e
      log.error "Error: invalid regular expression in annotation_match: #{e}"
    end
  end

end

#create_time_from_record(record) ⇒ Object 



271
272
273
274
275
276
277
278
 
# File 'lib/fluent/plugin/filter_kubernetes_metadata.rb', line 271

def create_time_from_record(record)
    time = if @use_journal
       record['_SOURCE_REALTIME_TIMESTAMP'].nil? ? record['_SOURCE_REALTIME_TIMESTAMP'] : record['__REALTIME_TIMESTAMP']
    else
      record['time']
    end
    (time.nil? || time.chop.empty?) ? Time.now : Time.parse(time)
end

#de_dot!(h) ⇒ Object 



344
345
346
347
348
349
350
351
352
 
# File 'lib/fluent/plugin/filter_kubernetes_metadata.rb', line 344

def de_dot!(h)
  h.keys.each do |ref|
    if h[ref] && ref =~ /\./
      v = h.delete(ref)
      newref = ref.to_s.gsub('.', @de_dot_separator)
      h[newref] = v
    end
  end
end

#dump_stats ⇒ Object 



101
102
103
104
105
106
107
108
109
110
111
112
113
 
# File 'lib/fluent/plugin/filter_kubernetes_metadata.rb', line 101

def dump_stats
  @curr_time = Time.now
  return if @curr_time.to_i - @prev_time.to_i < @stats_interval
  @prev_time = @curr_time
  @stats.set(:pod_cache_size, @cache.count)
  @stats.set(:namespace_cache_size, @namespace_cache.count) if @namespace_cache
  log.info(@stats)
  if log.level == Fluent::Log::LEVEL_TRACE
    log.trace("       id cache: #{@id_cache.to_a}")
    log.trace("      pod cache: #{@cache.to_a}")
    log.trace("namespace cache: #{@namespace_cache.to_a}")
  end
end

#fetch_namespace_metadata(namespace_name) ⇒ Object 



115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
 
# File 'lib/fluent/plugin/filter_kubernetes_metadata.rb', line 115

def fetch_namespace_metadata(namespace_name)
  log.trace("fetching namespace metadata: #{namespace_name}") if log.trace?
  begin
    metadata = @client.get_namespace(namespace_name)
    unless metadata
        log.trace("no metadata returned for: #{namespace_name}") if log.trace?
        @stats.bump(:namespace_cache_api_nil_not_found)
    else
      begin
        log.trace("raw metadata for #{namespace_name}: #{metadata}") if log.trace?
        metadata = parse_namespace_metadata(metadata)
        @stats.bump(:namespace_cache_api_updates)
        log.trace("parsed metadata for #{namespace_name}: #{metadata}") if log.trace?
         @namespace_cache[metadata['namespace_id']] = metadata
        return metadata
      rescue Exception => e
        log.debug(e)
        @stats.bump(:namespace_cache_api_nil_bad_resp_payload)
        log.trace("returning empty metadata for #{namespace_name} due to error '#{e}'") if log.trace?
      end
    end
  rescue Exception => kube_error
    @stats.bump(:namespace_cache_api_nil_error)
    log.debug "Exception '#{kube_error}' encountered fetching namespace metadata from Kubernetes API #{@apiVersion} endpoint #{@kubernetes_url}"
  end
  {}
end

#fetch_pod_metadata(namespace_name, pod_name) ⇒ Object 



73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
 
# File 'lib/fluent/plugin/filter_kubernetes_metadata.rb', line 73

def fetch_pod_metadata(namespace_name, pod_name)
  log.trace("fetching pod metadata: #{namespace_name}/#{pod_name}") if log.trace?
  begin
    metadata = @client.get_pod(pod_name, namespace_name)
    unless metadata
      log.trace("no metadata returned for: #{namespace_name}/#{pod_name}") if log.trace?
      @stats.bump(:pod_cache_api_nil_not_found)
    else
      begin
        log.trace("raw metadata for #{namespace_name}/#{pod_name}: #{metadata}") if log.trace?
        metadata = parse_pod_metadata(metadata)
        @stats.bump(:pod_cache_api_updates)
        log.trace("parsed metadata for #{namespace_name}/#{pod_name}: #{metadata}") if log.trace?
        @cache[metadata['pod_id']] = metadata
        return metadata
      rescue Exception=>e
        log.debug(e)
        @stats.bump(:pod_cache_api_nil_bad_resp_payload)
        log.trace("returning empty metadata for #{namespace_name}/#{pod_name} due to error '#{e}'") if log.trace?
      end
    end
  rescue Exception=>e
    @stats.bump(:pod_cache_api_nil_error)
    log.debug "Exception '#{e}' encountered fetching pod metadata from Kubernetes API #{@apiVersion} endpoint #{@kubernetes_url}"
  end
  {}
end

#filter_stream(tag, es) ⇒ Object 



280
281
282
 
# File 'lib/fluent/plugin/filter_kubernetes_metadata.rb', line 280

def filter_stream(tag, es)
  es
end

#filter_stream_from_files(tag, es) ⇒ Object 



284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
 
# File 'lib/fluent/plugin/filter_kubernetes_metadata.rb', line 284

def filter_stream_from_files(tag, es)
  return es if (es.respond_to?(:empty?) && es.empty?) || !es.is_a?(Fluent::EventStream)
  new_es = MultiEventStream.new

  match_data = tag.match(@tag_to_kubernetes_name_regexp_compiled)
  batch_miss_cache = {}
  if match_data
    container_id = match_data['docker_id']
    metadata = {
      'docker' => {
        'container_id' => container_id
      },
      'kubernetes' => get_metadata_for_record(match_data, container_id, create_time_from_record(es.first[1]), batch_miss_cache)
    }
  end

  es.each do |time, record|
    record = record.merge(Marshal.load(Marshal.dump(metadata))) if metadata
    new_es.add(time, record)
  end
  dump_stats
  new_es
end

#filter_stream_from_journal(tag, es) ⇒ Object 



308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
 
# File 'lib/fluent/plugin/filter_kubernetes_metadata.rb', line 308

def filter_stream_from_journal(tag, es)
  return es if (es.respond_to?(:empty?) && es.empty?) || !es.is_a?(Fluent::EventStream)
  new_es = MultiEventStream.new
  batch_miss_cache = {}
  es.each do |time, record|
    metadata = nil
    if record.has_key?('CONTAINER_NAME') && record.has_key?('CONTAINER_ID_FULL')
      metadata = record['CONTAINER_NAME'].match(@container_name_to_kubernetes_regexp_compiled) do |match_data|
       container_id = record['CONTAINER_ID_FULL']
        metadata = {
          'docker' => {
            'container_id' => container_id
          },
          'kubernetes' => get_metadata_for_record(match_data, container_id, create_time_from_record(record), batch_miss_cache)
        }

        metadata
      end
      unless metadata
        log.debug "Error: could not match CONTAINER_NAME from record #{record}"
        @stats.bump(:container_name_match_failed)
      end
    elsif record.has_key?('CONTAINER_NAME') && record['CONTAINER_NAME'].start_with?('k8s_')
      log.debug "Error: no container name and id in record #{record}"
      @stats.bump(:container_name_id_missing)
    end

    record = record.merge(metadata) if metadata

    new_es.add(time, record)
  end

  dump_stats
  new_es
end

#get_metadata_for_record(match_data, cache_key, create_time, batch_miss_cache) ⇒ Object 



256
257
258
259
260
261
262
263
264
265
266
267
268
269
 
# File 'lib/fluent/plugin/filter_kubernetes_metadata.rb', line 256

def get_metadata_for_record(match_data, cache_key, create_time, batch_miss_cache)
  namespace_name = match_data['namespace']
  pod_name = match_data['pod_name']
  metadata = {
    'container_name' => match_data['container_name'],
    'namespace_name' => namespace_name,
    'pod_name'       => pod_name
  }
  if @kubernetes_url.present?
    pod_metadata = get_pod_metadata(cache_key, namespace_name, pod_name, create_time, batch_miss_cache)
    metadata.merge!(pod_metadata) if pod_metadata
  end
  metadata
end