Class: DataDrain::GlueRunner

Inherits:
Object
  • Object
show all
Extended by:
Observability
Defined in:
lib/data_drain/glue_runner.rb

Overview

Orquestador para AWS Glue. Permite disparar y monitorear Jobs en AWS para delegar el movimiento masivo de datos (ej. tablas de 1TB).

Class Attribute Summary collapse

Class Method Summary collapse

Class Attribute Details

.client ⇒ Boolean

Dispara un Job de Glue y espera a que termine exitosamente.

Parameters:

  • job_name (String) —

    Nombre del Job en la consola de AWS.

  • arguments (Hash) —

    Argumentos de ejecución (deben empezar con –).

  • polling_interval (Integer) —

    Segundos de espera entre cada chequeo de estado.

  • max_wait_seconds (Integer, nil) —

    Timeout máximo en segundos. nil = sin límite (comportamiento anterior).

Returns:

  • (Boolean) —

    true si el Job terminó exitosamente (SUCCEEDED).

Raises:

  • (DataDrain::Error) —

    si max_wait_seconds excede antes de SUCCEEDED.

  • (RuntimeError) —

    si el Job falla o se detiene.



22
23
24
 
# File 'lib/data_drain/glue_runner.rb', line 22

def self.client
  @client ||= Aws::Glue::Client.new(region: DataDrain.configuration.aws_region)
end

Class Method Details

.create_job(job_name, role_arn:, script_location: nil, script_path: nil, script_bucket: nil, script_folder: "scripts", script_filename: nil, command_name: "glueetl", default_arguments: {}, description: nil, worker_type: nil, number_of_workers: nil, timeout: 2880, max_retries: 0, allocated_capacity: nil, glue_version: nil) ⇒ Object 



43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
 
# File 'lib/data_drain/glue_runner.rb', line 43

def self.create_job(job_name, role_arn:, script_location: nil, script_path: nil,
                    script_bucket: nil, script_folder: "scripts", script_filename: nil,
                    command_name: "glueetl", default_arguments: {}, description: nil,
                    worker_type: nil, number_of_workers: nil, timeout: 2880,
                    max_retries: 0, allocated_capacity: nil, glue_version: nil)
  @logger = DataDrain.configuration.logger
  DataDrain::Validations.validate_glue_name!(:job_name, job_name)

  final_script_location = resolve_script_location(
    script_location: script_location,
    script_path: script_path,
    script_bucket: script_bucket,
    script_folder: script_folder,
    script_filename: script_filename
  )

  opts = {
    name: job_name,
    role: role_arn,
    command: {
      name: command_name,
      python_version: "3",
      script_location: final_script_location
    }
  }
  opts[:default_arguments] = default_arguments unless default_arguments.empty?
  opts[:description] = description if description
  opts[:timeout] = timeout if timeout
  opts[:max_retries] = max_retries if max_retries
  opts[:allocated_capacity] = allocated_capacity if allocated_capacity
  opts[:worker_type] = worker_type if worker_type
  opts[:number_of_workers] = number_of_workers if number_of_workers
  opts[:glue_version] = glue_version if glue_version

  client.create_job(**opts)
  safe_log(:info, "glue_runner.job_create", {
             job: job_name,
             glue_version: glue_version,
             worker_type: worker_type,
             number_of_workers: number_of_workers
           })
  get_job(job_name)
rescue Aws::Glue::Errors::ServiceError => e
  safe_log(:error, "glue_runner.job_create_error",
           { job: job_name }.merge(exception_metadata(e)))
  raise
end

.delete_job(job_name) ⇒ Object 



124
125
126
127
128
129
130
131
132
133
134
135
136
137
 
# File 'lib/data_drain/glue_runner.rb', line 124

def self.delete_job(job_name)
  @logger = DataDrain.configuration.logger
  DataDrain::Validations.validate_glue_name!(:job_name, job_name)
  client.delete_job(job_name: job_name)
  safe_log(:info, "glue_runner.job_delete", { job: job_name })
  true
rescue Aws::Glue::Errors::EntityNotFoundException
  safe_log(:info, "glue_runner.job_delete_skipped", { job: job_name, reason: "not_found" })
  false
rescue Aws::Glue::Errors::ServiceError => e
  safe_log(:error, "glue_runner.job_delete_error",
           { job: job_name }.merge(exception_metadata(e)))
  raise
end

.ensure_job(job_name, role_arn:, script_location: nil, script_path: nil, script_bucket: nil, script_folder: "scripts", script_filename: nil, command_name: "glueetl", default_arguments: {}, description: nil, worker_type: nil, number_of_workers: nil, timeout: 2880, max_retries: 0, allocated_capacity: nil, glue_version: nil) ⇒ Object 



139
140
141
142
143
144
145
146
147
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
 
# File 'lib/data_drain/glue_runner.rb', line 139

def self.ensure_job(job_name, role_arn:, script_location: nil, script_path: nil,
                    script_bucket: nil, script_folder: "scripts", script_filename: nil,
                    command_name: "glueetl", default_arguments: {}, description: nil,
                    worker_type: nil, number_of_workers: nil, timeout: 2880,
                    max_retries: 0, allocated_capacity: nil, glue_version: nil)
  @logger = DataDrain.configuration.logger

  final_script_location = resolve_script_location(
    script_location: script_location,
    script_path: script_path,
    script_bucket: script_bucket,
    script_folder: script_folder,
    script_filename: script_filename
  )

  if job_exists?(job_name)
    current = get_job(job_name)
    desired = {
      role: role_arn,
      command_name: command_name,
      script_location: final_script_location,
      default_arguments: default_arguments,
      description: description,
      worker_type: worker_type,
      number_of_workers: number_of_workers,
      timeout: timeout,
      max_retries: max_retries,
      glue_version: glue_version
    }
    changed = changed_fields(desired, current)
    if changed.empty?
      safe_log(:info, "glue_runner.job_unchanged", { job: job_name })
      current
    else
      safe_log(:info, "glue_runner.job_exists", { job: job_name })
      update_job(job_name, role_arn: role_arn, command_name: command_name,
                           script_location: final_script_location, default_arguments: default_arguments,
                           description: description, worker_type: worker_type,
                           number_of_workers: number_of_workers, timeout: timeout,
                           max_retries: max_retries, allocated_capacity: allocated_capacity,
                           glue_version: glue_version)
    end
  else
    safe_log(:info, "glue_runner.job_created", { job: job_name })
    create_job(job_name, role_arn: role_arn, script_location: final_script_location,
                         command_name: command_name, default_arguments: default_arguments,
                         description: description, worker_type: worker_type,
                         number_of_workers: number_of_workers, timeout: timeout,
                         max_retries: max_retries, allocated_capacity: allocated_capacity,
                         glue_version: glue_version)
  end
end

.get_job(job_name) ⇒ Object 



38
39
40
41
 
# File 'lib/data_drain/glue_runner.rb', line 38

def self.get_job(job_name)
  DataDrain::Validations.validate_glue_name!(:job_name, job_name)
  client.get_job(job_name: job_name).job
end

.job_exists?(job_name) ⇒ Boolean

Returns:

  • (Boolean) 


30
31
32
33
34
35
36
 
# File 'lib/data_drain/glue_runner.rb', line 30

def self.job_exists?(job_name)
  DataDrain::Validations.validate_glue_name!(:job_name, job_name)
  get_job(job_name)
  true
rescue Aws::Glue::Errors::EntityNotFoundException
  false
end

.run_and_wait(job_name, arguments = {}, polling_interval: 30, max_wait_seconds: nil) ⇒ Object 



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
298
299
300
301
302
303
 
# File 'lib/data_drain/glue_runner.rb', line 258

def self.run_and_wait(job_name, arguments = {}, polling_interval: 30, max_wait_seconds: nil)
  config = DataDrain.configuration
  config.validate!
  start_time = Process.clock_gettime(Process::CLOCK_MONOTONIC)

  @logger = config.logger

  safe_log(:info, "glue_runner.start", { job: job_name })
  resp = client.start_job_run(job_name: job_name, arguments: arguments)
  run_id = resp.job_run_id

  loop do
    if max_wait_seconds &&
       (Process.clock_gettime(Process::CLOCK_MONOTONIC) - start_time) > max_wait_seconds
      safe_log(:error, "glue_runner.timeout", {
                 job: job_name,
                 run_id: run_id,
                 max_wait_seconds: max_wait_seconds
               })
      raise DataDrain::Error,
            "Glue Job #{job_name} (Run ID: #{run_id}) excedió max_wait_seconds=#{max_wait_seconds}"
    end

    run_info = client.get_job_run(job_name: job_name, run_id: run_id).job_run
    status = run_info.job_run_state

    case status
    when "SUCCEEDED"
      duration = Process.clock_gettime(Process::CLOCK_MONOTONIC) - start_time
      safe_log(:info, "glue_runner.complete", { job: job_name, run_id: run_id, duration_s: duration.round(2) })
      return true
    when "FAILED", "STOPPED", "TIMEOUT"
      duration = Process.clock_gettime(Process::CLOCK_MONOTONIC) - start_time
      error_metadata = { job: job_name, run_id: run_id, status: status, duration_s: duration.round(2) }

      error_metadata[:error_message] = run_info.error_message.gsub("\"", "'")[0, 200] if run_info.error_message

      safe_log(:error, "glue_runner.failed", error_metadata)
      raise "Glue Job #{job_name} (Run ID: #{run_id}) falló con estado #{status}."
    else
      safe_log(:info, "glue_runner.polling",
               { job: job_name, run_id: run_id, status: status, next_check_in_s: polling_interval })
      sleep polling_interval
    end
  end
end

.update_job(job_name, role_arn: nil, command_name: nil, script_location: nil, default_arguments: nil, description: nil, worker_type: nil, number_of_workers: nil, timeout: nil, max_retries: nil, allocated_capacity: nil, glue_version: nil) ⇒ 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
118
119
120
121
122
 
# File 'lib/data_drain/glue_runner.rb', line 91

def self.update_job(job_name, role_arn: nil, command_name: nil, script_location: nil,
                    default_arguments: nil, description: nil, worker_type: nil,
                    number_of_workers: nil, timeout: nil, max_retries: nil, allocated_capacity: nil,
                    glue_version: nil)
  @logger = DataDrain.configuration.logger
  DataDrain::Validations.validate_glue_name!(:job_name, job_name)
  job_update = {}
  job_update[:role] = role_arn if role_arn
  if command_name && script_location
    job_update[:command] =
      { name: command_name, python_version: "3", script_location: script_location }
  end
  job_update[:default_arguments] = default_arguments if default_arguments
  job_update[:description] = description if description
  job_update[:timeout] = timeout if timeout
  job_update[:max_retries] = max_retries if max_retries
  job_update[:allocated_capacity] = allocated_capacity if allocated_capacity
  job_update[:worker_type] = worker_type if worker_type
  job_update[:number_of_workers] = number_of_workers if number_of_workers
  job_update[:glue_version] = glue_version if glue_version

  client.update_job(job_name: job_name, job_update: job_update)
  safe_log(:info, "glue_runner.job_update", {
             job: job_name,
             changed_fields: job_update.keys.map(&:to_s)
           })
  get_job(job_name)
rescue Aws::Glue::Errors::ServiceError => e
  safe_log(:error, "glue_runner.job_update_error",
           { job: job_name }.merge(exception_metadata(e)))
  raise
end

.upload_script(local_path:, bucket:, folder: "scripts", filename: nil) ⇒ Object 



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
 
# File 'lib/data_drain/glue_runner.rb', line 225

def self.upload_script(local_path:, bucket:, folder: "scripts", filename: nil)
  @logger = DataDrain.configuration.logger

  unless File.exist?(local_path)
    raise DataDrain::ConfigurationError,
          "Script local '#{local_path}' no existe"
  end

  actual_filename = filename || File.basename(local_path)
  s3_key = "#{folder.chomp("/")}/#{actual_filename}"
  bytes = File.size(local_path)

  adapter = DataDrain::Storage.adapter
  unless adapter.is_a?(DataDrain::Storage::S3)
    raise DataDrain::ConfigurationError,
          "upload_script requiere storage_mode = :s3, actual: #{DataDrain.configuration.storage_mode}"
  end

  s3_path = adapter.upload_file(local_path, bucket, s3_key, content_type: "text/x-python")

  safe_log(:info, "glue_runner.script_uploaded", {
             local_path: local_path,
             s3_path: s3_path,
             bytes: bytes
           })

  s3_path
rescue Aws::S3::Errors::ServiceError => e
  safe_log(:error, "glue_runner.script_upload_error",
           { local_path: local_path, bucket: bucket }.merge(exception_metadata(e)))
  raise
end