线程池中的死锁

Question

我找不到适合 Ruby 的合适的 ThreadPool 实现，所以我编写了我的线程池实现（部分基于这里的代码： http://web.archive.org/web/20081204101031/http://snippets.dzone.com:80/posts/show/3276 ，但更改为 wait/signal 和 ThreadPool 关闭的其他实现。然而，运行一段时间后（有 100 个线程并处理大约 1300 个任务），它在第 25 行因死锁而死亡 - 它在那里等待新作业。有什么想法，为什么会发生？

require 'thread'
begin
  require 'fastthread'
rescue LoadError
  $stderr.puts "Using the ruby-core thread implementation"
end 

class ThreadPool
  class Worker
    def initialize(callback)
      @mutex = Mutex.new
      @cv = ConditionVariable.new
      @callback = callback
      @mutex.synchronize {@running = true}
      @thread = Thread.new do
        while @mutex.synchronize {@running}
          block = get_block
          if block
            block.call
            reset_block
            # Signal the ThreadPool that this worker is ready for another job
            @callback.signal
          else
            # Wait for a new job
            @mutex.synchronize {@cv.wait(@mutex)} # <=== Is this line 25?
          end
        end
      end
    end

    def name
      @thread.inspect
    end

    def get_block
      @mutex.synchronize {@block}
    end

    def set_block(block)
      @mutex.synchronize do
        raise RuntimeError, "Thread already busy." if @block
        @block = block
        # Signal the thread in this class, that there's a job to be done
        @cv.signal
      end
    end

    def reset_block
      @mutex.synchronize {@block = nil}
    end

    def busy?
      @mutex.synchronize {!@block.nil?}
    end

    def stop
      @mutex.synchronize {@running = false}
      # Signal the thread not to wait for a new job
      @cv.signal
      @thread.join
    end
  end

  attr_accessor :max_size

  def initialize(max_size = 10)
    @max_size = max_size
    @workers = []
    @mutex = Mutex.new
    @cv = ConditionVariable.new
  end

  def size
    @mutex.synchronize {@workers.size}
  end

  def busy?
    @mutex.synchronize {@workers.any? {|w| w.busy?}}
  end

  def shutdown
    @mutex.synchronize {@workers.each {|w| w.stop}}
  end
  alias :join :shutdown

  def process(block=nil,&blk)
    block = blk if block_given?
    while true
      @mutex.synchronize do
         worker = get_worker 
         if worker
           return worker.set_block(block)
         else
           # Wait for a free worker
           @cv.wait(@mutex)
         end
      end
    end
  end

  # Used by workers to report ready status
  def signal
    @cv.signal
  end

  private
  def get_worker
    free_worker || create_worker
  end

  def free_worker
    @workers.each {|w| return w unless w.busy?}; nil
  end

  def create_worker
    return nil if @workers.size >= @max_size
    worker = Worker.new(self)
    @workers << worker
    worker
  end
end

Answer 1

好的，所以实现的主要问题是：如何确保信号不丢失并避免死锁？

根据我的经验，使用条件变量和互斥体确实很难实现这一点，但使用信号量则很容易实现。碰巧 ruby​​ 实现了一个名为 Queue（或 SizedQueue）的对象来解决这个问题。这是我建议的实现：

require 'thread'
begin
  require 'fasttread'
rescue LoadError
  $stderr.puts "Using the ruby-core thread implementation"
end

class ThreadPool
  class Worker
    def initialize(thread_queue)
      @mutex = Mutex.new
      @cv = ConditionVariable.new
      @queue = thread_queue
      @running = true
      @thread = Thread.new do
        @mutex.synchronize do
          while @running
            @cv.wait(@mutex)
            block = get_block
            if block
              @mutex.unlock
              block.call
              @mutex.lock
              reset_block
            end
            @queue << self
          end
        end
      end
    end

    def name
      @thread.inspect
    end

    def get_block
      @block
    end

    def set_block(block)
      @mutex.synchronize do
        raise RuntimeError, "Thread already busy." if @block
        @block = block
        # Signal the thread in this class, that there's a job to be done
        @cv.signal
      end
    end

    def reset_block
      @block = nil
    end

    def busy?
      @mutex.synchronize { !@block.nil? }
    end

    def stop
      @mutex.synchronize do
        @running = false
        @cv.signal
      end
      @thread.join
    end
  end

  attr_accessor :max_size

  def initialize(max_size = 10)
    @max_size = max_size
    @queue = Queue.new
    @workers = []
  end

  def size
    @workers.size
  end

  def busy?
    @queue.size < @workers.size
  end

  def shutdown
    @workers.each { |w| w.stop }
    @workers = []
  end

  alias :join :shutdown

  def process(block=nil,&blk)
    block = blk if block_given?
    worker = get_worker
    worker.set_block(block)
  end

  private

  def get_worker
    if !@queue.empty? or @workers.size == @max_size
      return @queue.pop
    else
      worker = Worker.new(@queue)
      @workers << worker
      worker
    end
  end

end

这是一个简单的测试代码：

tp = ThreadPool.new 500
(1..1000).each { |i| tp.process { (2..10).inject(1) { |memo,val| sleep(0.1); memo*val }; print "Computation #{i} done. Nb of tasks: #{tp.size}\n" } }
tp.shutdown

Answer 2

您可以尝试 工作队列 gem，旨在协调生产者和工作线程池之间的工作。

Answer 3

我在这里有点偏见，但我建议用某种流程语言对此进行建模并对其进行模型检查。例如，免费提供的工具有 mCRL2 工具集（使用基于 ACP 的语言）、Mobility Workbench（pi 演算）和 Spin (PROMELA)。

否则，我建议删除对问题不重要的所有代码，并找到发生死锁的最小情况。我怀疑 100 个线程和 1300 个任务是否是导致死锁的必要条件。对于较小的情况，您可能只需添加一些调试打印即可提供足够的信息来解决问题。

Answer 4

好的，问题似乎出在您的 ThreadPool#signal 方法中。可能发生的情况是：

1 - 您的所有工作人员都很忙，您尝试处理新工作

2 - 第 90 行得到一个零工人

3 - 工作线程被释放并发出信号，但信号丢失，因为线程池没有等待它

4 - 你掉到了 95 号线上，尽管有一个空闲的工人仍在等待。

这里的错误是，即使没有人在听，你也可以向空闲的工人发出信号。这个 ThreadPool#signal 方法应该是：

def signal
     @mutex.synchronize { @cv.signal }
end

而Worker对象中的问题也是一样的。可能发生的情况是：

1 - 工人刚刚完成了一项工作

2 - 检查（第 17 行）是否有作业等待：没有

3 - 线程池发送一个新作业并发出信号......但信号丢失

4 - 工作线程等待信号，即使它被标记为忙

您应该将初始化方法设置为：

def initialize(callback)
  @mutex = Mutex.new
  @cv = ConditionVariable.new
  @callback = callback
  @mutex.synchronize {@running = true}
  @thread = Thread.new do
    @mutex.synchronize do
      while @running
        block = get_block
        if block
          @mutex.unlock
          block.call
          @mutex.lock
          reset_block
          # Signal the ThreadPool that this worker is ready for another job
          @callback.signal
        else
          # Wait for a new job
          @cv.wait(@mutex)
        end
      end
    end
  end
end

接下来，Worker#get_block 和 Worker#reset_block 方法不应再同步。这样，在测试块和等待信号之间就不能将块分配给工作人员。

Answer 5

多年来，顶级评论者的代码提供了很多帮助。这里针对 ruby​​ 2.x 进行了更新，并改进了线程识别。这是怎样的改进？当每个线程都有一个ID时，你可以用一个存储任意信息的数组组成ThreadPool。一些想法：

• 无数组：典型的线程池用法。即使使用 GIL，它也使线程编码变得非常容易，并且对于高延迟应用程序（例如大容量网络爬行）非常有用，
• 线程池和数组的大小取决于 CPU 的数量：轻松分叉进程以使用所有 CPU，
• 线程池和数组的大小取决于资源数量：例如，每个数组元素代表实例池中的一个处理器，因此，如果您有 10 个实例，每个实例有 4 个 CPU，则 TP 可以跨 40 个子进程管理工作。

对于最后两个，不要考虑执行工作的线程，而是考虑管理正在执行工作的子进程的线程池。管理任务是轻量级的，当与子流程结合时，谁关心GIL。

通过这个类，您可以用大约一百行代码编写一个基于集群的 MapReduce！这段代码非常简短，尽管要完全理解它可能有点费解。希望能帮助到你。

# Usage:
#
#   Thread.abort_on_exception = true # help localize errors while debugging
#   pool = ThreadPool.new(thread_pool_size)
#   50.times {|i|
#     pool.process { ... }
#     or
#     pool.process {|id| ... } # worker identifies itself as id
#   }
#   pool.shutdown()

class ThreadPool

  require 'thread'

  class ThreadPoolWorker

    attr_accessor :id

    def initialize(thread_queue, id)
      @id = id # worker id is exposed thru tp.process {|id| ... }
      @mutex = Mutex.new
      @cv = ConditionVariable.new
      @idle_queue = thread_queue
      @running = true
      @block = nil
      @thread = Thread.new {
        @mutex.synchronize {
          while @running
            @cv.wait(@mutex) # block until there is work to do
            if @block
              @mutex.unlock
              begin
                @block.call(@id)
              ensure
                @mutex.lock
              end
              @block = nil
            end
            @idle_queue << self
          end
        }
      }
    end

    def set_block(block)
      @mutex.synchronize {
        raise RuntimeError, "Thread is busy." if @block
        @block = block
        @cv.signal # notify thread in this class, there is work to be done
      }
    end

    def busy?
      @mutex.synchronize { ! @block.nil? }
    end

    def stop
      @mutex.synchronize {
        @running = false
        @cv.signal
      }
      @thread.join
    end

    def name
      @thread.inspect
    end
  end


  attr_accessor :max_size, :queue

  def initialize(max_size = 10)
    @process_mutex = Mutex.new
    @max_size = max_size
    @queue = Queue.new # of idle workers
    @workers = []      # array to hold workers

    # construct workers
    @max_size.times {|i| @workers << ThreadPoolWorker.new(@queue, i) }

    # queue up workers (workers in queue are idle and available to
    # work).  queue blocks if no workers are available.
    @max_size.times {|i| @queue << @workers[i] }

    sleep 1 # important to give threads a chance to initialize
  end

  def size
    @workers.size
  end

  def idle
    @queue.size
  end

  # are any threads idle

  def busy?
    # @queue.size < @workers.size
    @queue.size == 0 && @workers.size == @max_size
  end

  # block until all threads finish

  def shutdown
    @workers.each {|w| w.stop }
    @workers = []
  end

  alias :join :shutdown

  def process(block = nil, &blk)
    @process_mutex.synchronize {
      block = blk if block_given?
      worker = @queue.pop # assign to next worker; block until one is ready
      worker.set_block(block) # give code block to worker and tell it to start
    }
  end


end