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, host='localhost', postprocess_pattern=nil)
    @redis = Redis.new(host: host)
    @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

Example usage:

# clear redis keys matching redis-globbed pattern `*:ovc:*` that
# also have a number at the end.  Perform dry run first.
#
$ DRY_RUN=true ./clear_redis_script.rb *:ovc:* localhost ':\d+$'
DB stats: keys=329,expires=329,avg_ttl=936664199
Clearing *:ovc:*
5 matching keys found in 0.0 sec.
2 matching keys after postprocessing

# perform actual wipe
#
$ ./clear_redis_script.rb *:ovc:* localhost ':\d+$'
DB stats: keys=329,expires=329,avg_ttl=936552482
Clearing *:ovc:*
5 matching keys found in 0.0 sec.
2 matching keys after postprocessing
deleting...
Deleted in 0.0 sec.
DB stats: keys=327,expires=327,avg_ttl=936517877


# delete all keys matching a globbed pattern without
# extra postprocessing
#
$ ./clear_redis_script.rb *:src2:* localhost
DB stats: keys=327,expires=327,avg_ttl=936517870
Clearing *:src2:*
327 matching keys found in 0.0 sec.
327 matching keys after postprocessing
deleting...
Deleted in 0.01 sec.
DB stats:

want to know one thing, will it work faster than "delete_matched" and can it process multiple requests at same time?

Pretty sure this predates delete_matched's SCAN-based implementation (rails/rails#32610). As far as I can tell that is similar or better.