Class: Flydata::Command::Sync

Inherits:
Base
  • Object
show all
Includes:
Helpers
Defined in:
lib/flydata/command/sync.rb

Defined Under Namespace

Classes: SyncDataEntryError

Constant Summary collapse

INSERT_PROGRESS_INTERVAL = 
1000
SERVER_DATA_PROCESSING_TIMEOUT =

seconds

3600
STATUS_PARSING =

for dump.pos file

'PARSING'
STATUS_WAITING = 
'WAITING'
STATUS_COMPLETE = 
'COMPLETE'

Constants included from Helpers

Helpers::UNIT_PREFIX

Instance Attribute Summary collapse

Attributes inherited from Base

#opts

Class Method Summary collapse

Instance Method Summary collapse

Methods included from Helpers

as_size, development?, env_mode, env_suffix, flydata_api_host_file, flydata_conf_file, flydata_version, format_menu_list, retry_on, to_command_class, usage_text

Methods inherited from Base

#ask_input_table_name, #ask_yes_no, #choose_one, #flydata, #initialize, #newline, #register_crontab, #retrieve_data_entries, #separator, #show_purpose_name

Methods included from Flydata::CommandLoggable

#before_logging, #log_error_stderr, #log_info_stdout, #log_warn_stderr

Constructor Details

This class inherits a constructor from Flydata::Command::Base

Instance Attribute Details

#ddl_tables ⇒ Object (readonly)

true if full initial sync



34
35
36
 
# File 'lib/flydata/command/sync.rb', line 34

def ddl_tables
  @ddl_tables
end

#full_initial_sync ⇒ Object (readonly)

true if full initial sync



34
35
36
 
# File 'lib/flydata/command/sync.rb', line 34

def full_initial_sync
  @full_initial_sync
end

#full_tables ⇒ Object (readonly)

true if full initial sync



34
35
36
 
# File 'lib/flydata/command/sync.rb', line 34

def full_tables
  @full_tables
end

#input_tables ⇒ Object (readonly)

true if full initial sync



34
35
36
 
# File 'lib/flydata/command/sync.rb', line 34

def input_tables
  @input_tables
end

#new_tables ⇒ Object (readonly)

true if full initial sync



34
35
36
 
# File 'lib/flydata/command/sync.rb', line 34

def new_tables
  @new_tables
end

Class Method Details

.slop ⇒ Object

Command: flydata sync

- Arguments



48
49
50
51
52
53
54
55
56
57
58
59
 
# File 'lib/flydata/command/sync.rb', line 48

def self.slop
  Slop.new do
    on 'c', 'skip-cleanup', 'Skip server cleanup'
    on 'f', 'skip-flush', 'Skip server flush'
    on 'y', 'yes', 'Skip command prompt assuming yes to all questions.  Use this for batch operation.'
    on 'd', 'dump-file', 'Dump mysqldump into a file. Use this for debugging after making sure the free space.' # dummy for compatibility
    on 's', 'dump-stream', 'Dump mysqldump stream instead of saving dump file. It might cause timeout error if db size is larger than 10GB.'
    on 'n', 'no-flydata-start', 'Don\'t start the flydata agent after initial sync.'
    #TODO : This option is temp! Should remove soon.
    on 'ff', 'Skip checking query queue and flush'
  end
end

.slop_fix_binlogpos ⇒ Object

Command: flydata sync:fix_binlogpos

- Arguments



242
243
244
245
246
 
# File 'lib/flydata/command/sync.rb', line 242

def self.slop_fix_binlogpos
  Slop.new do
    on 'f', 'force', 'update sent binlog position file forcibly'
  end
end

.slop_flush ⇒ Object

Command: flydata sync:flush

- Arguments



111
112
113
114
115
116
 
# File 'lib/flydata/command/sync.rb', line 111

def self.slop_flush
  Slop.new do
    on 'f', 'skip-flush', 'Skip server flush'
    on 'y', 'yes', 'Skip command prompt assuming yes to all questions.  Use this for batch operation.'
  end
end

.slop_generate_table_ddl ⇒ Object

Command: flydata sync:generate_table_ddl

- Arguments



217
218
219
220
221
222
223
224
 
# File 'lib/flydata/command/sync.rb', line 217

def self.slop_generate_table_ddl
  Slop.new do
    on 'c', 'ctl-only', 'Only generate FlyData Control definitions'
    on 'y', 'yes', 'Skip command prompt assuming yes to all questions.  Use this for batch operation.'
    on 's', 'skip-primary-key-check', 'Skip primary key check when generating DDL'
    on 'all-tables', 'Generate all table schema'
  end
end

.slop_reset ⇒ Object

Command: flydata sync:reset

- Arguments



137
138
139
140
141
142
 
# File 'lib/flydata/command/sync.rb', line 137

def self.slop_reset
  Slop.new do
    on 'c', 'client', 'Resets client only.'
    on 'y', 'yes', 'Skip command prompt assuming yes to all questions.  Use this for batch operation.'
  end
end

Instance Method Details

#fix_binlogpos ⇒ Object

Command: flydata sync:fix_binlogpos Set binlog path

- Entry method



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
 
# File 'lib/flydata/command/sync.rb', line 251

def fix_binlogpos
  de = data_entry
  sync_fm = create_sync_file_manager(de)

  if File.exists?(sync_fm.sent_binlog_path) && !opts.force?
    log_info_stdout("Skip creating sent binlogpos because sent position file is exist already. (#{sync_fm.sent_binlog_path})")
    return
  end

  if Flydata::Command::Sender.new.process_exist?
    log_warn_stderr("flydata is running. flydata process needs to be stopped with 'flydata stop'.")
    return
  end

  binlog_info = sync_fm.load_binlog
  if binlog_info.nil?
    log_info_stdout("Skip creating sent binlogpos because binlog position file is empty or invalid. (#{sync_fm.sent_binlog_path})")
    return
  end

  say("Updating binlog position files...")
  log_info("Updating binlog position files... Original binlog_info:#{binlog_info}")

  # Update binlog.sent.pos file
  #   -1 is because the position in binlog.pos is the next event's position.
  #   on the other hand the position in sent position indicates already processed.
  binlog_info[:pos] -= 1
  log_info("Updating sent position file. #{binlog_info} -> #{sync_fm.sent_binlog_path}")
  sync_fm.save_sent_binlog(binlog_info)

  # Update binlog.pos file to start from head of the current binlog file
  new_binlog_info = binlog_info.dup.tap{|h| h[:pos] = 4}  # 4 is the first position of binlog file.
  log_info("Updating original position file. #{new_binlog_info} -> #{sync_fm.binlog_path}")
  sync_fm.save_binlog(new_binlog_info)
  log_info_stdout("Done!")
end

#flush(*tables) ⇒ Object

Command: flydata sync:flush

- Entry method



120
121
122
123
124
125
126
127
128
129
130
131
132
133
 
# File 'lib/flydata/command/sync.rb', line 120

def flush(*tables)
  begin
    flush_buffer_and_stop(tables)
  rescue ServerDataProcessingTimeout => e
    ee = ServerDataProcessingTimeout.new("Delayed Data Processing")
    ee.description = <<EOS
  Data processing is taking more than expected.  Please contact [email protected] to check the system status.

EOS
    ee.set_backtrace e.backtrace
    raise ee
  end
  log_info_stdout("Buffers have been flushed and the sender process has been stopped.")
end

#generate_table_ddl(*tables) ⇒ Object

Command: flydata sync:generate_table_ddl

- Entry method



228
229
230
231
232
233
234
235
236
237
238
 
# File 'lib/flydata/command/sync.rb', line 228

def generate_table_ddl(*tables)
  # Compatibility check
  de = data_entry
  dp = flydata.data_port.get
  Flydata::MysqlCompatibilityCheck.new(dp, de['mysql_data_entry_preference']).check

  # Set instance variables
  set_current_tables(tables)

  do_generate_table_ddl(de)
end

#reset(*tables) ⇒ Object

Command: flydata sync:reset

- Entry method



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
191
192
193
194
195
196
197
198
199
200
 
# File 'lib/flydata/command/sync.rb', line 146

def reset(*tables)
  show_purpose_name
  # Flush client buffer
  msg = tables.empty? ? '' : " for these tables : #{tables.join(" ")}"
  return unless ask_yes_no("This resets the current sync#{msg}.  Are you sure?")
  sender = Flydata::Command::Sender.new
  sender.flush_client_buffer # TODO We should rather delete buffer files
  sender.stop

  # Set instance variables
  de = data_entry
  set_current_tables(tables)

  begin
    wait_for_server_buffer(timeout: SERVER_DATA_PROCESSING_TIMEOUT, tables: target_tables_for_api)
  rescue ServerDataProcessingTimeout => e
    ee = ServerDataProcessingTimeout.new("Delayed Data Processing")
    ee.description = <<EOS
  Data processing is taking more than expected.  Please contact [email protected] to check the system status.
  Once checked, you can continue sync reset with the following command

    flydata sync:reset #{tables.empty? ? '' : tables.join(" ")}

EOS
    ee.set_backtrace e.backtrace
    raise ee
  end

  # Cleanup tables on server
  cleanup_sync_server(de, @input_tables) unless opts.client?

  # Delete local files
  sync_fm = create_sync_file_manager(de)
  delete_files = [
    sync_fm.dump_file_path,
    sync_fm.dump_pos_path,
    sync_fm.mysql_table_marshal_dump_path,
    sync_fm.sync_info_file,
    sync_fm.table_position_file_paths(*@input_tables),
    sync_fm.table_binlog_pos_paths(*@input_tables),
    sync_fm.table_binlog_pos_init_paths(*@input_tables),
    sync_fm.table_rev_file_paths(*@input_tables),
    sync_fm.table_ddl_file_paths(*@input_tables)
  ]
  new_tables_after_reset = @new_tables + @input_tables
  if @input_tables.empty? or @full_tables.empty? or @full_tables.all?{|ft| new_tables_after_reset.include?(ft)}
    delete_files << sync_fm.binlog_path
    delete_files << sync_fm.sent_binlog_path
  end
  delete_files.flatten.each do |path|
    FileUtils.rm(path) if File.exists?(path)
  end
  sync_fm.close
  log_info_stdout("Reset completed successfully.")
end

#run(*tables) ⇒ Object

Command: flydata sync

- Entry method



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
90
91
92
93
94
95
 
# File 'lib/flydata/command/sync.rb', line 63

def run(*tables)
  # Process check
  sender = Flydata::Command::Sender.new
  if (sender.process_exist?)
    if tables.empty?
      # full sync
      log_warn_stderr("FlyData Agent is already running.  If you'd like to restart FlyData Sync from scratch, run 'flydata sync:reset' first.")
    else
      # per-table sync
      log_warn_stderr("Flydata Agent is already running.  If you'd like to Sync the table(s), run 'flydata sync:flush' first.")
    end
    exit 1
  end

  # Setup instance variables
  set_current_tables(tables)

  # Start initial sync with check
  handle_mysql_sync

  # Start continuous sync by starting fluentd process
  unless opts.no_flydata_start?
    log_info_stdout("Starting FlyData Agent...")
    Flydata::Command::Sender.new.start(quiet: true)
    log_info_stdout("  -> Done")
  end

  # Show message
  dashboard_url = "#{flydata.flydata_api_host}/dashboard"
  redshift_console_url = "#{flydata.flydata_api_host}/redshift_clusters/query/new"
  last_message = ALL_DONE_MESSAGE_TEMPLATE % [redshift_console_url, dashboard_url]
  log_info_stdout(last_message)
end

#skip ⇒ Object

Depricated Command: flydata sync:skip skip initial sync



204
205
206
207
208
209
210
211
212
213
 
# File 'lib/flydata/command/sync.rb', line 204

def skip
  de = data_entry
  sync_fm = create_sync_file_manager(de)
  binlog_path = sync_fm.binlog_path
  sync_fm.close
  `touch #{binlog_path}`
  log_info_stdout("Created an empty binlog position file.")
  log_info_stdout("-> #{binlog_path}")
  log_info_stdout("Run 'flydata start' to start continuous sync.")
end

#try_mysql_sync ⇒ Object

Public method

- Called from Sender#start/restart



99
100
101
102
103
104
105
106
107
 
# File 'lib/flydata/command/sync.rb', line 99

def try_mysql_sync
  # Setup instance variables
  set_current_tables

  # Start initial sync
  handle_mysql_sync
rescue SyncDataEntryError
  return
end