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

Inherits:
Chunk
  • Object
show all
Includes:
MessagePackFactory::Mixin, SystemConfig::Mixin
Defined in:
lib/fluent/plugin/buffer/file_chunk.rb

Constant Summary collapse

FILE_PERMISSION = 
0644

Instance Attribute Summary collapse

Attributes inherited from Chunk

#created_at, #metadata, #modified_at, #state, #unique_id

Class Method Summary collapse

Instance Method Summary collapse

Methods included from MessagePackFactory::Mixin

#msgpack_factory, #msgpack_packer, #msgpack_unpacker

Methods included from SystemConfig::Mixin

#system_config, #system_config_override

Methods inherited from Chunk

#append, #closed?, #queued?, #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: system_config.file_permission || FILE_PERMISSION, compress: :text) ⇒ FileChunk

Returns a new instance of FileChunk.



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

def initialize(metadata, path, mode, perm: system_config.file_permission || FILE_PERMISSION, compress: :text)
  super(metadata, compress: compress)
  @permission = perm
  @bytesize = @size = @adding_bytes = @adding_size = 0
  @meta = nil

  case mode
  when :create then create_new_chunk(path, perm)
  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

#path ⇒ Object (readonly)

Returns the value of attribute path.



41
42
43
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 41

def path
  @path
end

#permission ⇒ Object (readonly)

Returns the value of attribute permission.



41
42
43
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 41

def permission
  @permission
end

Class Method Details

.assume_chunk_state(path) ⇒ Object 



148
149
150
151
152
153
154
155
156
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 148

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 



170
171
172
173
174
175
176
177
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 170

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 



158
159
160
161
162
163
164
165
166
167
168
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 158

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



180
181
182
183
184
185
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 180

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 



89
90
91
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 89

def bytesize
  @bytesize + @adding_bytes
end

#close ⇒ Object 



118
119
120
121
122
123
124
125
126
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 118

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
 
# 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 = Time.now

  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 



242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 242

def create_new_chunk(path, perm)
  @path = self.class.generate_stage_chunk_path(path, @unique_id)
  @meta_path = @path + '.meta'
  @chunk = File.open(@path, 'wb+', perm)
  @chunk.set_encoding(Encoding::ASCII_8BIT)
  @chunk.sync = true
  @chunk.binmode
  @meta = File.open(@meta_path, 'wb', perm)
  @meta.set_encoding(Encoding::ASCII_8BIT)
  @meta.sync = true
  @meta.binmode

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

#empty? ⇒ Boolean

Returns:

  • (Boolean) 


97
98
99
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 97

def empty?
  @bytesize == 0
end

#enqueued! ⇒ Object 



101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 101

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

  file_rename(@chunk, @path, new_chunk_path, ->(new_io){ @chunk = new_io })
  @path = new_chunk_path

  file_rename(@meta, @meta_path, new_meta_path, ->(new_io){ @meta = new_io })
  @meta_path = new_meta_path

  super
end

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



225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 225

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 



303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 303

def load_existing_enqueued_chunk(path)
  @path = path
  @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)
    restore_metadata(File.open(@meta_path){|f| f.set_encoding(Encoding::ASCII_8BIT); f.binmode; f.read })
  else
    restore_metadata_partially(@chunk)
  end
  @state = :queued
end

#load_existing_staged_chunk(path) ⇒ Object 



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
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 261

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)
    @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
    restore_metadata(@meta.read)
    @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 



141
142
143
144
145
146
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 141

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 



128
129
130
131
132
133
134
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 128

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 



136
137
138
139
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 136

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

#restore_metadata(bindata) ⇒ Object 



187
188
189
190
191
192
193
194
195
196
197
198
199
200
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 187

def restore_metadata(bindata)
  data = msgpack_unpacker(symbolize_keys: true).feed(bindata).read rescue {}

  now = Time.now

  @unique_id = data[:id] || self.class.unique_id_from_path(@path) || @unique_id
  @size = data[:s] || 0
  @created_at = Time.at(data.fetch(:c, now.to_i))
  @modified_at = Time.at(data.fetch(:m, now.to_i))

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

#restore_metadata_partially(chunk) ⇒ Object 



202
203
204
205
206
207
208
209
210
211
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 202

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

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

#rollback ⇒ Object 



80
81
82
83
84
85
86
87
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 80

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 



93
94
95
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 93

def size
  @size + @adding_size
end

#write_metadata(update: true) ⇒ Object 



213
214
215
216
217
218
219
220
221
222
223
 
# File 'lib/fluent/plugin/buffer/file_chunk.rb', line 213

def write_metadata(update: true)
  data = @metadata.to_h.merge({
      id: @unique_id,
      s: (update ? @size + @adding_size : @size),
      c: @created_at.to_i,
      m: (update ? Time.now : @modified_at).to_i,
  })
  @meta.seek(0, IO::SEEK_SET)
  @meta.truncate(0)
  @meta.write(msgpack_packer.pack(data))
end