Clear a large number of redis keys by pattern using SCAN and pipelining

clear_redis_script.rb

#!/usr/bin/env ruby

require 'redis'

# Clear a large number of keys matching a pattern using SCAN and
# pipelining to avoid killing the server.
class ClearKeys
  def initialize(pattern, url, postprocess_pattern=nil)
    @redis = Redis.new(url: url)
    @pattern = pattern
    @postprocess_pattern = postprocess_pattern
  end

  def call
    puts db_info
    puts "Clearing #{@pattern}"
    keys, time = timed { get_keys }
    puts "#{keys.size} matching keys found in #{time} sec."
    keys = postprocess(keys)
    puts "#{keys.size} matching keys after postprocessing"
    unless ENV['DRY_RUN']
      puts "deleting..."
      _, time = timed { clear(keys) }
      puts "Deleted in #{time} sec."
      puts db_info
    end
  end

  def clear(keys)
    keys.each_slice(500) do |chunk|
      @redis.pipelined do
        chunk.each do |key|
          @redis.del key
        end
      end
    end
  end

  def postprocess(keys)
    return keys if !@postprocess_pattern
    regex = Regexp.new(@postprocess_pattern)
    keys.select{ |k| regex.match k }
  end

  def db_info
    "DB stats: #{@redis.info['db0']}"
  end

  def timed(&block)
    start = Time.now
    result = block.call
    elapsed = (Time.now - start).round(2)
    return [result, elapsed]
  end

  def get_keys
    @redis.scan_each(match: @pattern, count:1000).to_a
  end
end

if ARGV[0].nil?
  puts "Syntax: #{$0} REDIS_PATTERN [HOST] [REGEX]"
else
  ClearKeys.new(ARGV[0], ARGV[1], ARGV[2]).call
end