【发布时间】：2020-06-01 19:45:35
【问题描述】：
我正在使用redis-semaphore gem，版本0.3.1。
由于某种原因，我有时无法释放过时的 Redis 锁。根据我的分析，如果我的 Docker 进程在创建锁后崩溃，似乎会发生这种情况。
我在下面描述了我的调试过程，想知道是否有人可以建议如何进一步调试。
假设我们想用这个名字创建一个redis锁：
name = "test"
我们在两个不同的终端窗口中插入这个变量。首先，我们运行：
def lock_for_15_secs(name)
job = Redis::Semaphore.new(name.to_sym, redis: NonBlockingRedis.new(), custom_blpop: true, :stale_client_timeout => 15)
if job.lock(-1) == "0"
puts "Locked and starting"
sleep(15)
puts "Now it's stale, try to release in another process"
sleep(15)
puts "Now trying to unlock"
unlock = job.unlock
puts unlock == false ? "Wuhuu, already unlocked" : "Hm, should have been unlocked by another process, but wasn't"
end
end
lock_for_15_secs(name)
在我们运行的第二秒：
def release_and_lock(name)
job = Redis::Semaphore.new(name.to_sym, redis: NonBlockingRedis.new(), custom_blpop: true, :stale_client_timeout => 15)
release = job.release_stale_locks!
count = job.available_count
puts "Release reponse is #{release.inspect} and available count is #{count}"
if job.lock(-1) == "0"
puts "Wuhuu, we can lock it"
job.unlock
else
puts "Hmm, we can't lock it"
end
end
release_and_lock(name)
这通常会按预期进行。 15 秒内，第二个终端无法释放锁，但运行 15 秒后，它会释放。以下是release_and_lock(name) 的输出。
在 15 秒过去之前：
irb(main):1:0> release_and_lock(name)
Release reponse is {"0"=>"1580292557.321834"} and available count is 0
Hmm, we can't lock it
=> nil
15 秒后：
irb(main):2:0> release_and_lock(name)
Release reponse is {"0"=>"1580292557.321834"} and available count is 1
Wuhuu, we can lock it
=> 1
irb(main):3:0> release_and_lock(name)
Release reponse is {} and available count is 1
Wuhuu, we can lock it
但是每当我看到一个陈旧的锁没有被释放，并且我运行release_and_lock(name) 进行诊断时，就会返回这个：
irb(main):4:0> release_and_lock(name)
Release reponse is {} and available count is 0
Hmm, we can't lock it
此时我唯一的选择是刷新 redis：
require 'non_blocking_redis'
non_blocking_redis = NonBlockingRedis.new()
non_blocking_redis.flushall
附：我的NonBlockingRedis 继承自Redis：
class Redis
class Semaphore
def initialize(name, opts = {})
@custom_opts = opts
@name = name
@resource_count = opts.delete(:resources) || 1
@stale_client_timeout = opts.delete(:stale_client_timeout)
@redis = opts.delete(:redis) || Redis.new(opts)
@use_local_time = opts.delete(:use_local_time)
@custom_blpop = opts.delete(:custom_blpop) # false=queue, true=cancel
@tokens = []
end
def lock(timeout = 0)
exists_or_create!
release_stale_locks! if check_staleness?
token_pair = @redis.blpop(available_key, timeout, @custom_blpop)
return false if token_pair.nil?
current_token = token_pair[1]
@tokens.push(current_token)
@redis.hset(grabbed_key, current_token, current_time.to_f)
if block_given?
begin
yield current_token
ensure
signal(current_token)
end
end
current_token
end
alias_method :wait, :lock
end
end
class NonBlockingRedis < Redis
def initialize(options = {})
if options.empty?
options = {
url: Rails.application.secrets.redis_url,
db: Rails.application.secrets.redis_sidekiq_db,
driver: :hiredis,
network_timeout: 5
}
end
super(options)
end
def blpop(key, timeout, custom_blpop)
if custom_blpop
if timeout == -1
result = lpop(key)
return result if result.nil?
return [key, result]
else
super(key, timeout)
end
else
super
end
end
def lock(timeout = 0)
exists_or_create!
release_stale_locks! if check_staleness?
token_pair = @redis.blpop(available_key, timeout, @custom_blpop)
return false if token_pair.nil?
current_token = token_pair[1]
@tokens.push(current_token)
@redis.hset(grabbed_key, current_token, current_time.to_f)
if block_given?
begin
yield current_token
ensure
signal(current_token)
end
end
current_token
end
alias_method :wait, :lock
end
require 'non_blocking_redis'
【问题讨论】：
-
好吧，差不多 2 年后，我面临同样的问题，你使用 bliof PR 吗？对你有用吗？
标签： ruby redis mutex semaphore