HBASE-2331 [shell] count command needs a way to specify scan caching

git-svn-id: https://svn.apache.org/repos/asf/hadoop/hbase/trunk@923979 13f79535-47bb-0310-9956-ffa450edef68

CHANGES.txt

@@ -439,6 +439,8 @@ Release 0.21.0 - Unreleased
    HBASE-2313  Nit-pick about hbase-2279 shell fixup, if you do get with
                non-existant column family, throws lots of exceptions
                (Alexey Kovyrin via Stack)
+   HBASE-2331  [shell] count command needs a way to specify scan caching
+               (Alexey Kovyrin via Stack)
 
   NEW FEATURES
    HBASE-1961  HBase EC2 scripts

core/src/main/ruby/hbase.rb

@@ -31,6 +31,8 @@ module HBaseConstants
   MAXLENGTH = "MAXLENGTH"
   CACHE_BLOCKS = "CACHE_BLOCKS"
   REPLICATION_SCOPE = "REPLICATION_SCOPE"
+  INTERVAL = 'INTERVAL'
+  CACHE = 'CACHE'
 
   # Load constants from hbase java API
   def self.promote_constants(constants)

core/src/main/ruby/hbase/table.rb

@@ -63,11 +63,11 @@ module Hbase
 
     #----------------------------------------------------------------------------------------------
     # Count rows in a table
-    def count(interval = 1000)
+    def count(interval = 1000, caching_rows = 10)
       # We can safely set scanner caching with the first key only filter
       scan = Scan.new
       scan.cache_blocks = false
-      scan.caching = 10
+      scan.caching = caching_rows
       scan.setFilter(FirstKeyOnlyFilter.new)
 
       # Run the scanner

core/src/main/ruby/shell/commands/count.rb

@@ -6,17 +6,32 @@ module Shell
           Count the number of rows in a table. This operation may take a LONG
           time (Run '$HADOOP_HOME/bin/hadoop jar hbase.jar rowcount' to run a
           counting mapreduce job). Current count is shown every 1000 rows by
-          default. Count interval may be optionally specified. Examples:
+          default. Count interval may be optionally specified. Scan caching
+          is enabled on count scans by default. Default cache size is 10 rows.
+          If your rows are small in size, you may want to increase this
+          parameter. Examples:
 
           hbase> count 't1'
-          hbase> count 't1', 100000
+          hbase> count 't1', INTERVAL => 100000
+          hbase> count 't1', CACHE => 1000
+          hbase> count 't1', INTERVAL => 10, CACHE => 1000
         EOF
       end
 
-      def command(table, interval = 1000)
+      def command(table, params = {})
+        # If the second parameter is an integer, then it is the old command syntax
+        params = { 'INTERVAL' => params } if params.kind_of?(Fixnum)
+
+        # Merge params with defaults
+        params = {
+          'INTERVAL' => 1000,
+          'CACHE' => 10
+        }.merge(params)
+
+        # Call the counter method
         now = Time.now
         formatter.header
-        count = table(table).count(interval) do |cnt, row|
+        count = table(table).count(params['INTERVAL'].to_i, params['CACHE'].to_i) do |cnt, row|
           formatter.row([ "Current count: #{cnt}, row: #{row}" ])
         end
         formatter.footer(now, count)