Class: Fluent::Plugin::Buffer::FileChunk

Inherits:
Chunk
  • Object
show all
Defined in:
lib/fluent/plugin/buffer/file_chunk.rb

Defined Under Namespace

Classes: FileChunkError

Constant Summary collapse

BUFFER_HEADER = 
"\xc1\x00".force_encoding(Encoding::ASCII_8BIT).freeze

Instance Attribute Summary collapse

Attributes inherited from Chunk

#metadata, #state, #unique_id

Class Method Summary collapse

Instance Method Summary collapse

Methods inherited from Chunk

#append, #closed?, #created_at, #modified_at, #queued?, #raw_create_at, #raw_modified_at, #staged!, #staged?, #unstaged!, #unstaged?, #writable?, #write_to

Methods included from UniqueId::Mixin

#dump_unique_id_hex, #generate_unique_id

Constructor Details

#initialize(metadata, path, mode, perm: nil, compress: :text, decompression_size_limit: Compressable::DEFAULT_DECOMPRESSION_SIZE_LIMIT) ⇒ FileChunk

Returns a new instance of FileChunk.



42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 42

def initialize(metadata, path, mode, perm: nil, compress: :text, decompression_size_limit: Compressable::DEFAULT_DECOMPRESSION_SIZE_LIMIT)
  super(metadata, compress: compress, decompression_size_limit: decompression_size_limit)
  perm ||= Fluent::DEFAULT_FILE_PERMISSION
  @permission = perm.is_a?(String) ? perm.to_i(8) : perm
  @bytesize = @size = @adding_bytes = @adding_size = 0
  @meta = nil

  case mode
  when :create then create_new_chunk(path, @permission)
  when :staged then load_existing_staged_chunk(path)
  when :queued then load_existing_enqueued_chunk(path)
  else
    raise ArgumentError, "Invalid file chunk mode: #{mode}"
  end
end

Instance Attribute Details

#meta_path ⇒ Object (readonly)

state: b/q - ‘b’(on stage, compatible with v0.12), ‘q’(enqueued) path_prefix: path prefix string, ended with ‘.’ path_suffix: path suffix string, like ‘.log’ (or any other user specified)



40
41
42
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 40

def meta_path
  @meta_path
end

#path ⇒ Object (readonly)

state: b/q - ‘b’(on stage, compatible with v0.12), ‘q’(enqueued) path_prefix: path prefix string, ended with ‘.’ path_suffix: path suffix string, like ‘.log’ (or any other user specified)



40
41
42
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 40

def path
  @path
end

#permission ⇒ Object (readonly)

state: b/q - ‘b’(on stage, compatible with v0.12), ‘q’(enqueued) path_prefix: path prefix string, ended with ‘.’ path_suffix: path suffix string, like ‘.log’ (or any other user specified)



40
41
42
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 40

def permission
  @permission
end

Class Method Details

.assume_chunk_state(path) ⇒ Object 



176
177
178
179
180
181
182
183
184
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 176

def self.assume_chunk_state(path)
  if /\.(b|q)([0-9a-f]+)\.[^\/]*\Z/n =~ path # //n switch means explicit 'ASCII-8BIT' pattern
    $1 == 'b' ? :staged : :queued
  else
    # files which matches to glob of buffer file pattern
    # it includes files which are created by out_file
    :unknown
  end
end

.generate_queued_chunk_path(path, unique_id) ⇒ Object 



198
199
200
201
202
203
204
205
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 198

def self.generate_queued_chunk_path(path, unique_id)
  chunk_id = Fluent::UniqueId.hex(unique_id)
  if path.index(".b#{chunk_id}.")
    path.sub(".b#{chunk_id}.", ".q#{chunk_id}.")
  else # for unexpected cases (ex: users rename files while opened by fluentd)
    path + ".q#{chunk_id}.chunk"
  end
end

.generate_stage_chunk_path(path, unique_id) ⇒ Object 



186
187
188
189
190
191
192
193
194
195
196
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 186

def self.generate_stage_chunk_path(path, unique_id)
  pos = path.index('.*.')
  raise "BUG: buffer chunk path on stage MUST have '.*.'" unless pos

  prefix = path[0...pos]
  suffix = path[(pos+3)..-1]

  chunk_id = Fluent::UniqueId.hex(unique_id)
  state = 'b'
  "#{prefix}.#{state}#{chunk_id}.#{suffix}"
end

.unique_id_from_path(path) ⇒ Object

used only for queued v0.12 buffer path or broken files



208
209
210
211
212
213
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 208

def self.unique_id_from_path(path)
  if /\.(b|q)([0-9a-f]+)\.[^\/]*\Z/n =~ path # //n switch means explicit 'ASCII-8BIT' pattern
    return $2.scan(/../).map{|x| x.to_i(16) }.pack('C*')
  end
  nil
end

Instance Method Details

#bytesize ⇒ Object 



90
91
92
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 90

def bytesize
  @bytesize + @adding_bytes
end

#close ⇒ Object 



146
147
148
149
150
151
152
153
154
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 146

def close
  super
  size = @chunk.size
  @chunk.close
  @meta.close if @meta # meta may be missing if chunk is queued at first
  if size == 0
    File.unlink(@path, @meta_path)
  end
end

#commit ⇒ Object 



68
69
70
71
72
73
74
75
76
77
78
79
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 68

def commit
  write_metadata # this should be at first: of course, this operation may fail

  @commit_position = @chunk.pos
  @size += @adding_size
  @bytesize += @adding_bytes
  @adding_bytes = @adding_size = 0
  @modified_at = Fluent::Clock.real_now
  @modified_at_object = nil

  true
end

#concat(bulk, bulk_size) ⇒ Object 



58
59
60
61
62
63
64
65
66
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 58

def concat(bulk, bulk_size)
  raise "BUG: concatenating to unwritable chunk, now '#{self.state}'" unless self.writable?

  bulk.force_encoding(Encoding::ASCII_8BIT)
  @chunk.write bulk
  @adding_bytes += bulk.bytesize
  @adding_size += bulk_size
  true
end

#create_new_chunk(path, perm) ⇒ Object 



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
321
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 282

def create_new_chunk(path, perm)
  @path = self.class.generate_stage_chunk_path(path, @unique_id)
  @meta_path = @path + '.meta'
  begin
    @chunk = File.open(@path, 'wb+', perm)
    @chunk.set_encoding(Encoding::ASCII_8BIT)
    @chunk.sync = true
    @chunk.binmode
  rescue => e
    # Here assumes "Too many open files" like recoverable error so raising BufferOverflowError.
    # If other cases are possible, we will change error handling with proper classes.
    raise BufferOverflowError, "can't create buffer file for #{path}. Stop creating buffer files: error = #{e}"
  end
  begin
    @meta = File.open(@meta_path, 'wb', perm)
    @meta.set_encoding(Encoding::ASCII_8BIT)
    @meta.sync = true
    @meta.binmode
    write_metadata(update: false)
  rescue => e
    # This case is easier than enqueued!. Just removing pre-create buffer file
    @chunk.close rescue nil
    File.unlink(@path) rescue nil

    if @meta
      # ensure to unlink when #write_metadata fails
      @meta.close rescue nil
      File.unlink(@meta_path) rescue nil
    end

    # Same as @chunk case. See above
    raise BufferOverflowError, "can't create buffer metadata for #{path}. Stop creating buffer files: error = #{e}"
  end

  @state = :unstaged
  @bytesize = 0
  @commit_position = @chunk.pos # must be 0
  @adding_bytes = 0
  @adding_size = 0
end

#empty? ⇒ Boolean

Returns:

  • (Boolean) 


98
99
100
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 98

def empty?
  @bytesize == 0
end

#enqueued! ⇒ Object 



102
103
104
105
106
107
108
109
110
111
112
113
114
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
142
143
144
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 102

def enqueued!
  return unless self.staged?

  new_chunk_path = self.class.generate_queued_chunk_path(@path, @unique_id)
  new_meta_path = new_chunk_path + '.meta'

  write_metadata(update: false) # re-write metadata w/ finalized records

  begin
    file_rename(@chunk, @path, new_chunk_path, ->(new_io) { @chunk = new_io })
  rescue => e
    begin
      file_rename(@chunk, new_chunk_path, @path, ->(new_io) { @chunk = new_io }) if File.exist?(new_chunk_path)
    rescue => re
      # In this point, restore buffer state is hard because previous `file_rename` failed by resource problem.
      # Retry is one possible approach but it may cause livelock under limited resources or high load environment.
      # So we ignore such errors for now and log better message instead.
      # "Too many open files" should be fixed by proper buffer configuration and system setting.
      raise "can't enqueue buffer file and failed to restore. This may causes inconsistent state: path = #{@path}, error = '#{e}', retry error = '#{re}'"
    else
      raise "can't enqueue buffer file: path = #{@path}, error = '#{e}'"
    end
  end

  begin
    file_rename(@meta, @meta_path, new_meta_path, ->(new_io) { @meta = new_io })
  rescue => e
    begin
      file_rename(@chunk, new_chunk_path, @path, ->(new_io) { @chunk = new_io }) if File.exist?(new_chunk_path)
      file_rename(@meta, new_meta_path, @meta_path, ->(new_io) { @meta = new_io }) if File.exist?(new_meta_path)
    rescue => re
      # See above
      raise "can't enqueue buffer metadata and failed to restore. This may causes inconsistent state: path = #{@meta_path}, error = '#{e}', retry error = '#{re}'"
    else
      raise "can't enqueue buffer metadata: path = #{@meta_path}, error = '#{e}'"
    end
  end

  @path = new_chunk_path
  @meta_path = new_meta_path

  super
end

#file_rename(file, old_path, new_path, callback = nil) ⇒ Object 



265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 265

def file_rename(file, old_path, new_path, callback=nil)
  pos = file.pos
  if Fluent.windows?
    file.close
    File.rename(old_path, new_path)
    file = File.open(new_path, 'rb', @permission)
  else
    File.rename(old_path, new_path)
    file.reopen(new_path, 'rb')
  end
  file.set_encoding(Encoding::ASCII_8BIT)
  file.sync = true
  file.binmode
  file.pos = pos
  callback.call(file) if callback
end

#load_existing_enqueued_chunk(path) ⇒ Object

Raises:



373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 373

def load_existing_enqueued_chunk(path)
  @path = path
  raise FileChunkError, "enqueued file chunk is empty" if File.size(@path).zero?

  @chunk = File.open(@path, 'rb')
  @chunk.set_encoding(Encoding::ASCII_8BIT)
  @chunk.binmode
  @chunk.seek(0, IO::SEEK_SET)
  @bytesize = @chunk.size
  @commit_position = @chunk.size

  @meta_path = @path + '.meta'
  if File.readable?(@meta_path)
    begin
      restore_metadata(File.open(@meta_path){|f| f.set_encoding(Encoding::ASCII_8BIT); f.binmode; f.read })
    rescue => e
      @chunk.close
      raise FileChunkError, "enqueued meta file is broken. #{e.message}"
    end
  else
    restore_metadata_partially(@chunk)
  end
  @state = :queued
end

#load_existing_staged_chunk(path) ⇒ Object 



323
324
325
326
327
328
329
330
331
332
333
334
335
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
370
371
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 323

def load_existing_staged_chunk(path)
  @path = path
  @meta_path = @path + '.meta'

  @meta = nil
  # staging buffer chunk without metadata is classic buffer chunk file
  # and it should be enqueued immediately
  if File.exist?(@meta_path)
    raise FileChunkError, "staged file chunk is empty" if File.size(@path).zero?

    @chunk = File.open(@path, 'rb+')
    @chunk.set_encoding(Encoding::ASCII_8BIT)
    @chunk.sync = true
    @chunk.seek(0, IO::SEEK_END)
    @chunk.binmode

    @meta = File.open(@meta_path, 'rb+')
    @meta.set_encoding(Encoding::ASCII_8BIT)
    @meta.sync = true
    @meta.binmode
    begin
      restore_metadata(@meta.read)
    rescue => e
      @chunk.close
      @meta.close
      raise FileChunkError, "staged meta file is broken. #{e.message}"
    end
    @meta.seek(0, IO::SEEK_SET)

    @state = :staged
    @bytesize = @chunk.size
    @commit_position = @chunk.pos
    @adding_bytes = 0
    @adding_size = 0
  else
    # classic buffer chunk - read only chunk
    @chunk = File.open(@path, 'rb')
    @chunk.set_encoding(Encoding::ASCII_8BIT)
    @chunk.binmode
    @chunk.seek(0, IO::SEEK_SET)
    @state = :queued
    @bytesize = @chunk.size

    restore_metadata_partially(@chunk)

    @commit_position = @chunk.size
    @unique_id = self.class.unique_id_from_path(@path) || @unique_id
  end
end

#open(**kwargs, &block) ⇒ Object 



169
170
171
172
173
174
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 169

def open(**kwargs, &block)
  @chunk.seek(0, IO::SEEK_SET)
  val = yield @chunk
  @chunk.seek(0, IO::SEEK_END) if self.staged?
  val
end

#purge ⇒ Object 



156
157
158
159
160
161
162
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 156

def purge
  super
  @chunk.close
  @meta.close if @meta
  @bytesize = @size = @adding_bytes = @adding_size = 0
  File.unlink(@path, @meta_path)
end

#read(**kwargs) ⇒ Object 



164
165
166
167
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 164

def read(**kwargs)
  @chunk.seek(0, IO::SEEK_SET)
  @chunk.read
end

#restore_metadata(bindata) ⇒ Object

Raises:



215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 215

def restore_metadata(bindata)
  data = restore_metadata_with_new_format(bindata)

  unless data
    # old type of restore
    data = Fluent::MessagePackFactory.msgpack_unpacker(symbolize_keys: true).feed(bindata).read rescue {}
  end
  raise FileChunkError, "invalid meta data" if data.nil? || !data.is_a?(Hash)
  raise FileChunkError, "invalid unique_id" unless data[:id]
  raise FileChunkError, "invalid created_at" unless data[:c].to_i > 0
  raise FileChunkError, "invalid modified_at" unless data[:m].to_i > 0

  now = Fluent::Clock.real_now

  @unique_id = data[:id]
  @size = data[:s] || 0
  @created_at = data[:c]
  @modified_at = data[:m]

  @metadata.timekey = data[:timekey]
  @metadata.tag = data[:tag]
  @metadata.variables = data[:variables]
  @metadata.seq = data[:seq] || 0
end

#restore_metadata_partially(chunk) ⇒ Object 



240
241
242
243
244
245
246
247
248
249
250
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 240

def restore_metadata_partially(chunk)
  @unique_id = self.class.unique_id_from_path(chunk.path) || @unique_id
  @size = 0
  @created_at = chunk.ctime.to_i # birthtime isn't supported on Windows (and Travis?)
  @modified_at = chunk.mtime.to_i

  @metadata.timekey = nil
  @metadata.tag = nil
  @metadata.variables = nil
  @metadata.seq = 0
end

#rollback ⇒ Object 



81
82
83
84
85
86
87
88
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 81

def rollback
  if @chunk.pos != @commit_position
    @chunk.seek(@commit_position, IO::SEEK_SET)
    @chunk.truncate(@commit_position)
  end
  @adding_bytes = @adding_size = 0
  true
end

#size ⇒ Object 



94
95
96
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 94

def size
  @size + @adding_size
end

#write_metadata(update: true) ⇒ Object 



252
253
254
255
256
257
258
259
260
261
262
263
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 252

def write_metadata(update: true)
  data = @metadata.to_h.merge({
      id: @unique_id,
      s: (update ? @size + @adding_size : @size),
      c: @created_at,
      m: (update ? Fluent::Clock.real_now : @modified_at),
  })
  bin = Fluent::MessagePackFactory.thread_local_msgpack_packer.pack(data).full_pack
  size = [bin.bytesize].pack('N')
  @meta.seek(0, IO::SEEK_SET)
  @meta.write(BUFFER_HEADER + size + bin)
end