Class: BackupTool

Inherits:
Object
  • Object
show all
Defined in:
lib/backuptool.rb

Instance Method Summary collapse

Constructor Details

#initialize(cassandra, hadoop, logger) ⇒ BackupTool

Create a new BackupTool instance

  • Args :

    • cassandra -> Cassandra instance

    • hadoop -> HDFS instance

    • logger -> Logger



16
17
18
19
20
21
22
 
# File 'lib/backuptool.rb', line 16

def initialize(cassandra, hadoop, logger)
  @cassandra = cassandra
  @hadoop = hadoop
  @logger = logger

  @metadir = META_DIR
end

Instance Method Details

#buffered_download(remote, local) ⇒ Object

Download a file from HDFS, buffered way

  • Args :

    • remote -> HDFS path

    • local -> local path



148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
 
# File 'lib/backuptool.rb', line 148

def buffered_download(remote, local)
  @logger.debug("#{remote} => #{local}")

  # Create the destination directory if not exists
  path = File.dirname(local)
  FileUtils.mkdir_p(path) unless File.exist?(path)

  file = open(local, 'wb')

  offset = 0
  length = BUFFER_SIZE
  print '['
  while length == BUFFER_SIZE
    print '#'
    content = @hadoop.read(remote, offset: offset, length: BUFFER_SIZE)
    file.write(content)
    length = content.length
    offset += length
  end
  print "]\n"

  file.close
end

#delete_snapshots(node: @cassandra.node_name, date: 'ALL') ⇒ Object 



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
 
# File 'lib/backuptool.rb', line 116

def delete_snapshots(node: @cassandra.node_name, date: 'ALL')
  snapshots = search_snapshots(node: node, date: date)
  if snapshots.empty?
    raise('No snapshot found for deletion')
  else
    snapshots.each do |snapshot|
      @logger.info("Deleting snapshot #{snapshot}")
      node_snapshots = search_snapshots(node: snapshot.node)
      merged_metadata = Set.new
      node_snapshots.each do |s|
        merged_metadata += s.metadata if s != snapshot
      end
      files = snapshot.metadata - merged_metadata
      @logger.info("#{files.length} files to delete")
      files.each do |file|
        @logger.info("Deleting file #{file}")
        remote = @hadoop.base_dir + '/' + snapshot.cluster + '/' + snapshot.node + '/' + file
        @logger.debug("DELETE => #{remote}")
        @hadoop.delete(remote)
      end
      @logger.info('Deleting metadata in Hadoop')
      remote = @hadoop.base_dir + '/' + @metadir + '/' + snapshot.cluster + '/' + snapshot.node + '/cass_snap_' + snapshot.date
      @logger.debug("DELETE => #{remote}")
      @hadoop.delete(remote)
    end
  end
end

#get_snapshot_metadata(node, date) ⇒ Object 



31
32
33
34
35
36
 
# File 'lib/backuptool.rb', line 31

def get_snapshot_metadata(node, date)
  remote = @hadoop.base_dir + '/' + @metadir + '/' + @cassandra.cluster_name + '/' + node + '/cass_snap_' + date
  return @hadoop.read(remote).split("\n").to_set
rescue Exception => e
  raise("Could not read metadata : #{e.message}")
end

#get_snapshots_node(node, date) ⇒ Object 



38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
 
# File 'lib/backuptool.rb', line 38

def get_snapshots_node(node, date)
  result = []
  begin
    if date == 'ALL'
      ls = @hadoop.list("#{@hadoop.base_dir}/#{@metadir}/#{@cassandra.cluster_name}/#{node}")
      ls.each do |item|
        date = item['pathSuffix'].gsub('cass_snap_', '')
        metadata = get_snapshot_metadata(node, date)
        snapshot = CassandraSnapshot.new(@cassandra.cluster_name, node, date, metadata)
        result.push(snapshot)
      end
    else
      metadata = get_snapshot_metadata(node, date)
      snapshot = CassandraSnapshot.new(@cassandra.cluster_name, node, date, metadata)
      result.push(snapshot)
    end
  rescue Exception => e
    @logger.warn("Could not get snapshots for node #{node} : #{e.message}")
  end
  result
end

#list_snapshots(node: @cassandra.node_name) ⇒ Object 



77
78
79
80
81
 
# File 'lib/backuptool.rb', line 77

def list_snapshots(node: @cassandra.node_name)
  @logger.info('Listing available snapshots')
  snapshots = search_snapshots(node: node)
  tp(snapshots, 'cluster', 'node', 'date')
end

#new_snapshot ⇒ Object 



83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
 
# File 'lib/backuptool.rb', line 83

def new_snapshot
  @logger.info('Starting a new snapshot')
  snapshot = @cassandra.new_snapshot

  existing = search_snapshots(node: snapshot.node)
  last = if existing.empty?
           CassandraSnapshot.new(snapshot.cluster, snapshot.node, 'never')
         else
           existing[-1]
  end

  @logger.info('Uploading tables to Hadoop')
  files = snapshot.metadata - last.metadata
  @logger.info("#{files.length} files to upload")
  files.each do |file|
    @logger.info("Sending file #{file} to Hadoop")
    local = @cassandra.data_path + '/' + file
    remote = @hadoop.base_dir + '/' + snapshot.cluster + '/' + snapshot.node + '/' + file
    @logger.debug("#{local} => #{remote}")
    f = File.open(local, 'r')
    @hadoop.create(remote, f, overwrite: true)
    f.close
  end

  @logger.info('Sending metadata to Hadoop')
  remote = @hadoop.base_dir + '/' + @metadir + '/' + snapshot.cluster + '/' + snapshot.node + '/cass_snap_' + snapshot.date
  @logger.debug("metadata => #{remote}")
  @hadoop.create(remote, snapshot.metadata.to_a * "\n", overwrite: true)

  @cassandra.delete_snapshot(snapshot)
  @logger.info('Success !')
end

#restore_snapshot(node, date, destination) ⇒ Object

Restore a snapshot from HDFS

  • Args :

    • node -> node where the snapshot comes from

    • date -> snapshot date

    • destination -> local directory where to restore



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/backuptool.rb', line 177

def restore_snapshot(node, date, destination)
  # Search the snapshot matching node and date
  snapshots = search_snapshots(node: node, date: date)

  if snapshots.empty?
    raise('No snapshot found for restore')
  elsif snapshots.length > 1
    raise('More than one candidate snapshot to restore')
  else
    snapshot = snapshots[0]
    @logger.info("Restoring snapshot #{snapshot}")
    @logger.info("#{snapshot.metadata.length} files to restore")

    # For each file in metadata
    snapshot.metadata.each do |file|
      @logger.info("Restoring file #{file}")
      local = destination + '/' + file
      remote = @hadoop.base_dir + '/' + snapshot.cluster + '/' + snapshot.node + '/' + file
      # Download the file from hdfs
      buffered_download(remote, local)
    end
    @logger.info('Success !')
  end
end

#search_snapshots(node: 'ALL', date: 'ALL') ⇒ Object

Look for snapshots

  • Args :

    • node -> Cassandra node name

    • date -> HDFS instance



28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
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
 
# File 'lib/backuptool.rb', line 28

def search_snapshots(node: 'ALL', date: 'ALL')
  result = []

  def get_snapshot_metadata(node, date)
    remote = @hadoop.base_dir + '/' + @metadir + '/' + @cassandra.cluster_name + '/' + node + '/cass_snap_' + date
    return @hadoop.read(remote).split("\n").to_set
  rescue Exception => e
    raise("Could not read metadata : #{e.message}")
  end

  def get_snapshots_node(node, date)
    result = []
    begin
      if date == 'ALL'
        ls = @hadoop.list("#{@hadoop.base_dir}/#{@metadir}/#{@cassandra.cluster_name}/#{node}")
        ls.each do |item|
          date = item['pathSuffix'].gsub('cass_snap_', '')
          metadata = get_snapshot_metadata(node, date)
          snapshot = CassandraSnapshot.new(@cassandra.cluster_name, node, date, metadata)
          result.push(snapshot)
        end
      else
        metadata = get_snapshot_metadata(node, date)
        snapshot = CassandraSnapshot.new(@cassandra.cluster_name, node, date, metadata)
        result.push(snapshot)
      end
    rescue Exception => e
      @logger.warn("Could not get snapshots for node #{node} : #{e.message}")
    end
    result
  end

  if node == 'ALL'
    begin
      ls = @hadoop.list("#{@hadoop.base_dir}/#{@metadir}/#{@cassandra.cluster_name}")
      ls.each do |item|
        n = item['pathSuffix']
        result += get_snapshots_node(n, date)
      end
    rescue Exception => e
      @logger.warn("Could not get snapshots for cluster #{@cassandra.cluster_name} : #{e.message}")
    end
  else
    result = get_snapshots_node(node, date)
  end

  result.sort
end