Class: Fluent::Plugin::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

#get_pods_and_start_watcher, #process_pod_watcher_notices, #reset_pod_watch_retry_stats, #set_up_pod_thread, #start_pod_watch

Methods included from KubernetesMetadata::Common

#match_annotations, #parse_namespace_metadata, #parse_pod_metadata, #syms_to_strs

Methods included from KubernetesMetadata::WatchNamespaces

#get_namespaces_and_start_watcher, #process_namespace_watcher_notices, #reset_namespace_watch_retry_stats, #set_up_namespace_thread, #start_namespace_watch

Methods included from KubernetesMetadata::CacheStrategy

#get_pod_metadata

Constructor Details

#initialize ⇒ KubernetesMetadataFilter

Returns a new instance of KubernetesMetadataFilter.



161
162
163
164
 
# File 'lib/fluent/plugin/filter_kubernetes_metadata.rb', line 161

def initialize
  super
  @prev_time = Time.now
end

Instance Method Details

#configure(conf) ⇒ Object 



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
255
256
257
258
259
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
 
# File 'lib/fluent/plugin/filter_kubernetes_metadata.rb', line 166

def configure(conf)
  super

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

  require 'kubeclient'
  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?
    log.debug "Kubernetes URL is not set - inspecting environ"

    env_host = ENV['KUBERNETES_SERVICE_HOST']
    env_port = ENV['KUBERNETES_SERVICE_PORT']
    if env_host.present? && env_port.present?
      if env_host =~ Resolv::IPv6::Regex
        # Brackets are needed around IPv6 addresses
        env_host = "[#{env_host}]"
      end
      @kubernetes_url = "https://#{env_host}:#{env_port}/api"
      log.debug "Kubernetes URL is now '#{@kubernetes_url}'"
    else
      log.debug "No Kubernetes URL could be found in config or environ"
    end
  end

  # Use SSL certificate and bearer token from Kubernetes service account.
  if Dir.exist?(@secret_dir)
    log.debug "Found directory with secrets: #{@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)
      log.debug "Found CA certificate: #{ca_cert}"
      @ca_file = ca_cert
    end

    if !@bearer_token_file.present? and File.exist?(pod_token)
      log.debug "Found pod token: #{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
    }

    if @ssl_partial_chain
      # taken from the ssl.rb OpenSSL::SSL::SSLContext code for DEFAULT_CERT_STORE
      require 'openssl'
      ssl_store = OpenSSL::X509::Store.new
      ssl_store.set_default_paths
      if defined? OpenSSL::X509::V_FLAG_PARTIAL_CHAIN
        flagval = OpenSSL::X509::V_FLAG_PARTIAL_CHAIN
      else
        # this version of ruby does not define OpenSSL::X509::V_FLAG_PARTIAL_CHAIN
        flagval = 0x80000
      end
      ssl_store.flags = OpenSSL::X509::V_FLAG_CRL_CHECK_ALL | flagval
      ssl_options[:cert_store] = ssl_store
    end

    auth_options = {}

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

    log.debug "Creating K8S client"
    @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
      pod_thread = Thread.new(self) { |this| this.set_up_pod_thread }
      pod_thread.abort_on_exception = true

      namespace_thread = Thread.new(self) { |this| this.set_up_namespace_thread }
      namespace_thread.abort_on_exception = true
    end
  end
  @time_fields = []
  @time_fields.push('_SOURCE_REALTIME_TIMESTAMP', '__REALTIME_TIMESTAMP') if @use_journal || @use_journal.nil?
  @time_fields.push('time') unless @use_journal
  @time_fields.push('@timestamp') if @lookup_from_k8s_field

  @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, internal_time) ⇒ Object 



322
323
324
325
326
327
328
329
330
331
332
333
334
 
# File 'lib/fluent/plugin/filter_kubernetes_metadata.rb', line 322

def create_time_from_record(record, internal_time)
  time_key = @time_fields.detect{ |ii| record.has_key?(ii) }
  time = record[time_key]
  if time.nil? || time.chop.empty?
    # `internal_time` is a Fluent::EventTime, it can't compare with Time.
    return Time.at(internal_time.to_f)
  end
  if ['_SOURCE_REALTIME_TIMESTAMP', '__REALTIME_TIMESTAMP'].include?(time_key)
    timei= time.to_i
    return Time.at(timei / 1000000, timei % 1000000)
  end
  return Time.parse(time)
end

#de_dot!(h) ⇒ Object 



389
390
391
392
393
394
395
396
397
 
# File 'lib/fluent/plugin/filter_kubernetes_metadata.rb', line 389

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 



119
120
121
122
123
124
125
126
127
128
129
130
131
 
# File 'lib/fluent/plugin/filter_kubernetes_metadata.rb', line 119

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 



133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
 
# File 'lib/fluent/plugin/filter_kubernetes_metadata.rb', line 133

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 



91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
 
# File 'lib/fluent/plugin/filter_kubernetes_metadata.rb', line 91

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 



336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
 
# File 'lib/fluent/plugin/filter_kubernetes_metadata.rb', line 336

def filter_stream(tag, es)
  return es if (es.respond_to?(:empty?) && es.empty?) || !es.is_a?(Fluent::EventStream)
  new_es = Fluent::MultiEventStream.new
  tag_match_data = tag.match(@tag_to_kubernetes_name_regexp_compiled) unless @use_journal
  tag_metadata = nil
  batch_miss_cache = {}
  es.each do |time, record|
    if tag_match_data && tag_metadata.nil?
      tag_metadata = get_metadata_for_record(tag_match_data['namespace'], tag_match_data['pod_name'], tag_match_data['container_name'],
        tag_match_data['docker_id'], create_time_from_record(record, time), batch_miss_cache)
    end
    metadata = Marshal.load(Marshal.dump(tag_metadata)) if tag_metadata
    if (@use_journal || @use_journal.nil?) &&
      (j_metadata = get_metadata_for_journal_record(record, time, batch_miss_cache))
      metadata = j_metadata
    end
    if @lookup_from_k8s_field && record.has_key?('kubernetes') && record.has_key?('docker') &&
      record['kubernetes'].respond_to?(:has_key?) && record['docker'].respond_to?(:has_key?) &&
      record['kubernetes'].has_key?('namespace_name') &&
      record['kubernetes'].has_key?('pod_name') &&
      record['kubernetes'].has_key?('container_name') &&
      record['docker'].has_key?('container_id') &&
      (k_metadata = get_metadata_for_record(record['kubernetes']['namespace_name'], record['kubernetes']['pod_name'],
        record['kubernetes']['container_name'], record['docker']['container_id'],
        create_time_from_record(record, time), batch_miss_cache))
        metadata = k_metadata
    end

    record = record.merge(metadata) if metadata
    new_es.add(time, record)
  end
  dump_stats
  new_es
end

#get_metadata_for_journal_record(record, time, batch_miss_cache) ⇒ Object 



371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
 
# File 'lib/fluent/plugin/filter_kubernetes_metadata.rb', line 371

def get_metadata_for_journal_record(record, time, batch_miss_cache)
  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|
      get_metadata_for_record(match_data['namespace'], match_data['pod_name'], match_data['container_name'],
        record['CONTAINER_ID_FULL'], create_time_from_record(record, time), batch_miss_cache)
    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
  metadata
end

#get_metadata_for_record(namespace_name, pod_name, container_name, container_id, create_time, batch_miss_cache) ⇒ Object 



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/filter_kubernetes_metadata.rb', line 299

def get_metadata_for_record(namespace_name, pod_name, container_name, container_id, create_time, batch_miss_cache)
  metadata = {
    'docker' => {'container_id' => container_id},
    'kubernetes' => {
      'container_name'  => container_name,
      'namespace_name'  => namespace_name,
      'pod_name'        => pod_name
    }
  }
  if @kubernetes_url.present?
    pod_metadata = get_pod_metadata(container_id, namespace_name, pod_name, create_time, batch_miss_cache)

    if (pod_metadata.include? 'containers') && (pod_metadata['containers'].include? container_id) && !@skip_container_metadata
      metadata['kubernetes']['container_image'] = pod_metadata['containers'][container_id]['image']
      metadata['kubernetes']['container_image_id'] = pod_metadata['containers'][container_id]['image_id']
    end

    metadata['kubernetes'].merge!(pod_metadata) if pod_metadata
    metadata['kubernetes'].delete('containers')
  end
  metadata
end