cassback 0.1.6 → 0.1.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 7ea67ebf7ce61ab5f9fe0606ab9cf15031029ca8
-  data.tar.gz: 38ad08644367525cd7e399ca5f4199fcce777aca
+  metadata.gz: 1b107b26f3da7063045152d59e04f0e4b393eacd
+  data.tar.gz: f234d6292937383a03d69bf32b70c20997d8e693
 SHA512:
-  metadata.gz: 6e1f3ff9809b7d038dd9357b1be6d4b832e3aefa877798573bb154b2d4191ae6f048d569f7972d720b422567230239fcb5c79ad48fdf563d256f81170def9a93
-  data.tar.gz: d97a160971c5467cc531f510eb7777a16e25bd34f6d00599d383138555c61cd96d50b9194f9b219600eeeba8ce5b037088c7ecebca1882aa2d039a30445b6a5d
+  metadata.gz: cce6bf488cd7e741525f59cce0347e107a972365312d12f0772f6aebd75cfbc2fdaf20d95f3fddb39405877054bb11da488be1080877adb5ebe6fd40a67beecc
+  data.tar.gz: aff6febf30585a2fb0e3fccb9d368dd558df4970989f1673ef5fe3f26c1fceed77d282a4e81b3a3540c500884b645295388c74cf86ac5d77e39f757d6d3f2dcf

data/README.md

@@ -78,6 +78,9 @@ can retry the file download/upload of data. This is configurable via the followi
 If you want to check more about Hadoop's checksum algorithm that ensures data integrity you can check the
 following link : https://www.safaribooksonline.com/library/view/hadoop-the-definitive/9781449328917/ch04.html
 
+Also there is the **hadoop.readTimeout** property which has been set by default to 300s, but it can be configured to
+another value if necessary (if HDFS cluster is responding too slow sometimes).
+
 ## Cleanup policy
 
 Usually backups of databases take a lot of space. Even if we have optimized the code so the backups are done incrementally

data/bin/cassback

@@ -57,6 +57,7 @@ options = {
     'directory'     => 'cassandra',
     'retryTimes'    => 5,
     'retryInterval' => 1,
+    'readTimeout'   => 300
   },
   'restore'   => {
     'destination' => 'cassandra',
@@ -162,7 +163,7 @@ begin
   # Create the Hadoop object
   hadoop = Hadoop.new(host: options['hadoop']['hostname'], port: options['hadoop']['port'],
   base_dir: options['hadoop']['directory'], retry_times: options['hadoop']['retryTimes'],
-  retry_interval: options['hadoop']['retryInterval'])
+  retry_interval: options['hadoop']['retryInterval'], read_timeout: options['hadoop']['readTimeout'])
 
   #  Create the Cassandra object
   cassandra = Cassandra.new(options['cassandra']['config'], logger)

data/conf/local.yml

@@ -1,3 +1,4 @@
+#Configuration file that can be used as an example.
 cassandra:
 #  config: "/etc/cassandra/conf/cassandra.yaml"
   config: "/Users/b.niculescu/Tools/apache-cassandra-2.0.16/conf/cassandra.yaml"
@@ -10,6 +11,7 @@ hadoop:
   directory: "/tmp/b.niculescu/cassandra"
   retryTimes : 3
   retryInterval : 1
+  readTimeout: 300
 
 restore:
   destination: "cassback_restore"

data/lib/cassback/version.rb

@@ -1,9 +1,3 @@
 module Cassback
-  # This represents the version that been currently deployed to rubygems.org
-  # For deploying a new version do the following :
-  # 1) Increment the version here
-  # 2) Build the gem using command : gem build cassback.gemspec
-  # 3) Push the gem using command : gem push cassback-<version>.gem
-  # 4) Commit the version change into source control system.
-  VERSION = '0.1.6'.freeze
+  VERSION = '0.1.7'.freeze
 end

data/lib/hadoop.rb

@@ -6,13 +6,13 @@ WebHDFS::ClientV1::REDIRECTED_OPERATIONS.delete('OPEN')
 class Hadoop < WebHDFS::Client
   attr_reader :base_dir
 
-  def initialize(host: 'localhost', port: 14_000, base_dir: '/', retry_times: 5, retry_interval: 1)
+  def initialize(host: 'localhost', port: 14_000, base_dir: '/', retry_times: 5, retry_interval: 1, read_timeout: 300)
     super(host = host, port = port)
     @kerberos = true
     @base_dir = base_dir
     @retry_known_errors = true
     @retry_times = retry_times
     @retry_interval = retry_interval
-    @read_timeout = 300
+    @read_timeout = read_timeout
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: cassback
 version: !ruby/object:Gem::Version
-  version: 0.1.6
+  version: 0.1.7
 platform: ruby
 authors:
 - Vincent Van Hollebeke