solid_queue 1.2.4 → 1.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 5450063206508cf94195d16dfe5be8db7609b4b959a9e2e36ca7cc102b90e04b
-  data.tar.gz: 6b10b7ddc67fdff01b31a78e486a4ea4f351277e7f851071406237300177d614
+  metadata.gz: ae346e5b4e8249ab21441c1b45118745124d1d7d78b5b43c08cf6b333e0ec665
+  data.tar.gz: fc4b4a6131ff3cb5799f1325f9b0523606152bf8e331bf7122af4463c543e2b5
 SHA512:
-  metadata.gz: 71a4c19d255e551e3a44aa1cdc508c5cb8dee3d66ae27c5b67a7fe2aaa31f958226e2a947bba773738274f717e5f635e412da1c471a03608657fc3deead4a961
-  data.tar.gz: 602c99609a6b65d3edbd29c8b8c26e9eed040830a115f207c0cebe139da80c6e43ccd2c1d583f4920fc0550c546747055f7da2fa73d858b9d20b4c7e37e674a9
+  metadata.gz: 2282d35fe14f5dfa424f1016dd8e00b2f3613e7023cb48cf99b82de5e2079de0154e7102fef72867060cdf4f1e7c9aa125cbed43c229ead9c200342c74e41099
+  data.tar.gz: cab19aa7d9d4a22fc3c068ebe00d2bbd1c288c023a37ef24b461bc8d84d9c3e100337ffcd53bf634d17e712e42937175e59cc6b2041e81661e91edfa9fb94282

data/README.md

@@ -14,8 +14,9 @@ Solid Queue can be used with SQL databases such as MySQL, PostgreSQL, or SQLite,
   - [Dashboard UI Setup](#dashboard-ui-setup)
   - [Incremental adoption](#incremental-adoption)
   - [High performance requirements](#high-performance-requirements)
+- [Workers, dispatchers, and scheduler](#workers-dispatchers-and-scheduler)
+  - [Fork vs. async mode](#fork-vs-async-mode)
 - [Configuration](#configuration)
-  - [Workers, dispatchers, and scheduler](#workers-dispatchers-and-scheduler)
   - [Queue order and priorities](#queue-order-and-priorities)
   - [Queues specification and performance](#queues-specification-and-performance)
   - [Threads, processes, and signals](#threads-processes-and-signals)
@@ -92,10 +93,10 @@ development:
 + primary:
     <<: *default
     database: storage/development.sqlite3
-+  queue:
-+    <<: *default
-+    database: storage/development_queue.sqlite3
-+    migrations_paths: db/queue_migrate
++ queue:
++   <<: *default
++   database: storage/development_queue.sqlite3
++   migrations_paths: db/queue_migrate
 ```
 
 Next, add the following to `development.rb`
@@ -127,7 +128,7 @@ In `config/cable.yml`
 ```diff
 development:
 -  adapter: async
-+ adapter: solid_cable
++  adapter: solid_cable
 +  connects_to:
 +    database:
 +      writing: cable
@@ -177,11 +178,9 @@ end
 
 ### High performance requirements
 
-Solid Queue was designed for the highest throughput when used with MySQL 8+ or PostgreSQL 9.5+, as they support `FOR UPDATE SKIP LOCKED`. You can use it with older versions, but in that case, you might run into lock waits if you run multiple workers for the same queue. You can also use it with SQLite on smaller applications.
-
-## Configuration
+Solid Queue was designed for the highest throughput when used with MySQL 8+, MariaDB 10.6+, or PostgreSQL 9.5+, as they support `FOR UPDATE SKIP LOCKED`. You can use it with older versions, but in that case, you might run into lock waits if you run multiple workers for the same queue. You can also use it with SQLite on smaller applications.
 
-### Workers, dispatchers, and scheduler
+## Workers, dispatchers, and scheduler
 
 We have several types of actors in Solid Queue:
 
@@ -190,7 +189,19 @@ We have several types of actors in Solid Queue:
 - The _scheduler_ manages [recurring tasks](#recurring-tasks), enqueuing jobs for them when they're due.
 - The _supervisor_ runs workers and dispatchers according to the configuration, controls their heartbeats, and stops and starts them when needed.
 
-Solid Queue's supervisor will fork a separate process for each supervised worker/dispatcher/scheduler.
+### Fork vs. async mode
+
+By default, Solid Queue runs in `fork` mode. This means the supervisor will fork a separate process for each supervised worker/dispatcher/scheduler. This provides the best isolation and performance, but can have additional memory usage and might not work with some Ruby implementations. As an alternative, you can run all workers, dispatchers and schedulers in the same process as the supervisor, in different threads, with an `async` mode. You can choose this mode by running `bin/jobs` as:
+
+```
+bin/jobs --mode async
+```
+
+Or you can also set the environment variable `SOLID_QUEUE_SUPERVISOR_MODE` to `async`. If you use the `async` mode, the `processes` option in the configuration described below will be ignored.
+
+**The recommended and default mode is `fork`. Only use `async` if you know what you're doing and have strong reasons to**
+
+## Configuration
 
 By default, Solid Queue will try to find your configuration under `config/queue.yml`, but you can set a different path using the environment variable `SOLID_QUEUE_CONFIG` or by using the `-c/--config_file` option with `bin/jobs`, like this:
 
@@ -254,7 +265,7 @@ Here's an overview of the different options:
 
 - `threads`: this is the max size of the thread pool that each worker will have to run jobs. Each worker will fetch this number of jobs from their queue(s), at most and will post them to the thread pool to be run. By default, this is `3`. Only workers have this setting.
 It is recommended to set this value less than or equal to the queue database's connection pool size minus 2, as each worker thread uses one connection, and two additional connections are reserved for polling and heartbeat.
-- `processes`: this is the number of worker processes that will be forked by the supervisor with the settings given. By default, this is `1`, just a single process. This setting is useful if you want to dedicate more than one CPU core to a queue or queues with the same configuration. Only workers have this setting.
+- `processes`: this is the number of worker processes that will be forked by the supervisor with the settings given. By default, this is `1`, just a single process. This setting is useful if you want to dedicate more than one CPU core to a queue or queues with the same configuration. Only workers have this setting. **Note**: this option will be ignored if [running in `async` mode](#fork-vs-async-mode).
 - `concurrency_maintenance`: whether the dispatcher will perform the concurrency maintenance work. This is `true` by default, and it's useful if you don't use any [concurrency controls](#concurrency-controls) and want to disable it or if you run multiple dispatchers and want some of them to just dispatch jobs without doing anything else.
 
 
@@ -334,7 +345,7 @@ queues: back*
 
 Workers in Solid Queue use a thread pool to run work in multiple threads, configurable via the `threads` parameter above. Besides this, parallelism can be achieved via multiple processes on one machine (configurable via different workers or the `processes` parameter above) or by horizontal scaling.
 
-The supervisor is in charge of managing these processes, and it responds to the following signals:
+The supervisor is in charge of managing these processes, and it responds to the following signals when running in its own process via `bin/jobs` or with [the Puma plugin](#puma-plugin) with the default `fork` mode:
 - `TERM`, `INT`: starts graceful termination. The supervisor will send a `TERM` signal to its supervised processes, and it'll wait up to `SolidQueue.shutdown_timeout` time until they're done. If any supervised processes are still around by then, it'll send a `QUIT` signal to them to indicate they must exit.
 - `QUIT`: starts immediate termination. The supervisor will send a `QUIT` signal to its supervised processes, causing them to exit immediately.
 
@@ -366,7 +377,7 @@ There are several settings that control how Solid Queue works that you can set a
 
   **This is not used for errors raised within a job execution**. Errors happening in jobs are handled by Active Job's `retry_on` or `discard_on`, and ultimately will result in [failed jobs](#failed-jobs-and-retries). This is for errors happening within Solid Queue itself.
 
-- `use_skip_locked`: whether to use `FOR UPDATE SKIP LOCKED` when performing locking reads. This will be automatically detected in the future, and for now, you only need to set this to `false` if your database doesn't support it. For MySQL, that'd be versions < 8, and for PostgreSQL, versions < 9.5. If you use SQLite, this has no effect, as writes are sequential.
+- `use_skip_locked`: whether to use `FOR UPDATE SKIP LOCKED` when performing locking reads. This will be automatically detected in the future, and for now, you only need to set this to `false` if your database doesn't support it. For MySQL, that'd be versions < 8; for MariaDB, versions < 10.6; and for PostgreSQL, versions < 9.5. If you use SQLite, this has no effect, as writes are sequential.
 - `process_heartbeat_interval`: the heartbeat interval that all processes will follow—defaults to 60 seconds.
 - `process_alive_threshold`: how long to wait until a process is considered dead after its last heartbeat—defaults to 5 minutes.
 - `shutdown_timeout`: time the supervisor will wait since it sent the `TERM` signal to its supervised processes before sending a `QUIT` version to them requesting immediate termination—defaults to 5 seconds.
@@ -519,11 +530,11 @@ DeliverAnnouncementToContactJob.set(wait: 30.minutes).perform_later(contact)
 
 The 3 jobs will go into the scheduled queue and will wait there until they're due. Then, 10 minutes after, the first two jobs will be enqueued and the second one most likely will be blocked because the first one will be running first. Then, assuming the jobs are fast and finish in a few seconds, when the third job is due, it'll be enqueued normally.
 
-Normally scheduled jobs are enqueued in batches, but with concurrency controls, jobs need to be enqueued one by one. This has an impact on performance, similarly to the impact of concurrency controls in bulk enqueuing. Read below for more details. I'd generally advise against mixing concurrency controls with waiting/scheduling in the future.
+Normally scheduled jobs are enqueued in batches, but with concurrency controls, jobs need to be enqueued one by one. This has an impact on performance, similarly to the impact of concurrency controls in bulk enqueuing. Read below for more details. We generally advise against mixing concurrency controls with waiting/scheduling in the future.
 
 ### Performance considerations
 
-Concurrency controls introduce significant overhead (blocked executions need to be created and promoted to ready, semaphores need to be created and updated) so you should consider carefully whether you need them. For throttling purposes, where you plan to have `limit` significantly larger than 1, I'd encourage relying on a limited number of workers per queue instead. For example:
+Concurrency controls introduce significant overhead (blocked executions need to be created and promoted to ready, semaphores need to be created and updated) so you should consider carefully whether you need them. For throttling purposes, where you plan to have `limit` significantly larger than 1, we encourage relying on a limited number of workers per queue instead. For example:
 
 ```ruby
 class ThrottledJob < ApplicationJob
@@ -603,6 +614,22 @@ that you set in production only. This is what Rails 8's default Puma config look
 
 **Note**: phased restarts are not supported currently because the plugin requires [app preloading](https://github.com/puma/puma?tab=readme-ov-file#cluster-mode) to work.
 
+### Running as a fork or asynchronously
+
+By default, the Puma plugin will fork additional processes for each worker and dispatcher so that they run in different processes. This provides the best isolation and performance, but can have additional memory usage.
+
+Alternatively, workers and dispatchers can be run within the same Puma process(s). To do so just configure the plugin as:
+
+```ruby
+plugin :solid_queue
+solid_queue_mode :async
+```
+
+Note that in this case, the `processes` configuration option will be ignored. See also [Fork vs. async mode](#fork-vs-async-mode).
+
+**The recommended and default mode is `fork`. Only use `async` if you know what you're doing and have strong reasons to**
+
+
 ## Jobs and transactional integrity
 :warning: Having your jobs in the same ACID-compliant database as your application data enables a powerful yet sharp tool: taking advantage of transactional integrity to ensure some action in your app is not committed unless your job is also committed and vice versa, and ensuring that your job won't be enqueued until the transaction within which you're enqueuing it is committed. This can be very powerful and useful, but it can also backfire if you base some of your logic on this behaviour, and in the future, you move to another active job backend, or if you simply move Solid Queue to its own database, and suddenly the behaviour changes under you. Because this can be quite tricky and many people shouldn't need to worry about it, by default Solid Queue is configured in a different database as the main app.
 

data/lib/puma/plugin/solid_queue.rb

@@ -1,5 +1,13 @@
 require "puma/plugin"
 
+module Puma
+  class DSL
+    def solid_queue_mode(mode = :fork)
+      @options[:solid_queue_mode] = mode.to_sym
+    end
+  end
+end
+
 Puma::Plugin.create do
   attr_reader :puma_pid, :solid_queue_pid, :log_writer, :solid_queue_supervisor
 
@@ -7,35 +15,73 @@ Puma::Plugin.create do
     @log_writer = launcher.log_writer
     @puma_pid = $$
 
-    in_background do
-      monitor_solid_queue
+    if launcher.options[:solid_queue_mode] == :async
+      start_async(launcher)
+    else
+      start_forked(launcher)
     end
+  end
 
-    if Gem::Version.new(Puma::Const::VERSION) < Gem::Version.new("7")
-      launcher.events.on_booted do
-        @solid_queue_pid = fork do
-          Thread.new { monitor_puma }
-          SolidQueue::Supervisor.start
+  private
+    def start_forked(launcher)
+      in_background do
+        monitor_solid_queue
+      end
+
+      if Gem::Version.new(Puma::Const::VERSION) < Gem::Version.new("7")
+        launcher.events.on_booted do
+          @solid_queue_pid = fork do
+            Thread.new { monitor_puma }
+            SolidQueue::Supervisor.start(mode: :fork)
+          end
         end
+
+        launcher.events.on_stopped { stop_solid_queue_fork }
+        launcher.events.on_restart { stop_solid_queue_fork }
+      else
+        launcher.events.after_booted do
+          @solid_queue_pid = fork do
+            Thread.new { monitor_puma }
+            start_solid_queue(mode: :fork)
+          end
+        end
+
+        launcher.events.after_stopped { stop_solid_queue_fork }
+        launcher.events.before_restart { stop_solid_queue_fork }
       end
+    end
 
-      launcher.events.on_stopped { stop_solid_queue }
-      launcher.events.on_restart { stop_solid_queue }
-    else
-      launcher.events.after_booted do
-        @solid_queue_pid = fork do
-          Thread.new { monitor_puma }
-          SolidQueue::Supervisor.start
+    def start_async(launcher)
+      if Gem::Version.new(Puma::Const::VERSION) < Gem::Version.new("7")
+        launcher.events.on_booted do
+          start_solid_queue(mode: :async, standalone: false)
+        end
+
+        launcher.events.on_stopped { solid_queue_supervisor&.stop }
+
+        launcher.events.on_restart do
+          solid_queue_supervisor&.stop
+          start_solid_queue(mode: :async, standalone: false)
+        end
+      else
+        launcher.events.after_booted do
+          start_solid_queue(mode: :async, standalone: false)
+        end
+
+        launcher.events.after_stopped { solid_queue_supervisor&.stop }
+
+        launcher.events.before_restart do
+          solid_queue_supervisor&.stop
+          start_solid_queue(mode: :async, standalone: false)
         end
       end
+    end
 
-      launcher.events.after_stopped { stop_solid_queue }
-      launcher.events.before_restart { stop_solid_queue }
+    def start_solid_queue(**options)
+      @solid_queue_supervisor = SolidQueue::Supervisor.start(**options)
     end
-  end
 
-  private
-    def stop_solid_queue
+    def stop_solid_queue_fork
       Process.waitpid(solid_queue_pid, Process::WNOHANG)
       log "Stopping Solid Queue..."
       Process.kill(:INT, solid_queue_pid) if solid_queue_pid
@@ -48,7 +94,7 @@ Puma::Plugin.create do
     end
 
     def monitor_solid_queue
-      monitor(:solid_queue_dead?, "Detected Solid Queue has gone away, stopping Puma...")
+      monitor(:solid_queue_fork_dead?, "Detected Solid Queue has gone away, stopping Puma...")
     end
 
     def monitor(process_dead, message)
@@ -62,7 +108,7 @@ Puma::Plugin.create do
       end
     end
 
-    def solid_queue_dead?
+    def solid_queue_fork_dead?
       if solid_queue_started?
         Process.waitpid(solid_queue_pid, Process::WNOHANG)
       end

data/lib/solid_queue/app_executor.rb

@@ -17,5 +17,15 @@ module SolidQueue
         SolidQueue.on_thread_error.call(error)
       end
     end
+
+    def create_thread(&block)
+      Thread.new do
+        Thread.current.name = name
+        block.call
+      rescue Exception => exception
+        handle_thread_error(exception)
+        raise
+      end
+    end
   end
 end

data/lib/solid_queue/async_supervisor.rb

@@ -0,0 +1,50 @@
+# frozen_string_literal: true
+
+module SolidQueue
+  class AsyncSupervisor < Supervisor
+    after_shutdown :terminate_gracefully, unless: :standalone?
+
+    def stop
+      super
+      @thread&.join
+    end
+
+    private
+      def supervise
+        if standalone? then super
+        else
+          @thread = create_thread { super }
+        end
+      end
+
+      def check_and_replace_terminated_processes
+        terminated_threads = process_instances.select { |thread_id, instance| !instance.alive? }
+        terminated_threads.each { |thread_id, instance| replace_thread(thread_id, instance) }
+      end
+
+      def replace_thread(thread_id, instance)
+        SolidQueue.instrument(:replace_thread, supervisor_pid: ::Process.pid) do |payload|
+          payload[:thread] = instance
+
+          error = Processes::ThreadTerminatedError.new(terminated_instance.name)
+          release_claimed_jobs_by(terminated_instance, with_error: error)
+
+          start_process(configured_processes.delete(thread_id))
+        end
+      end
+
+      def perform_graceful_termination
+        process_instances.values.each(&:stop)
+
+        Timer.wait_until(SolidQueue.shutdown_timeout, -> { all_processes_terminated? })
+      end
+
+      def perform_immediate_termination
+        exit!
+      end
+
+      def all_processes_terminated?
+        process_instances.values.none?(&:alive?)
+      end
+  end
+end

data/lib/solid_queue/cli.rb

@@ -8,6 +8,10 @@ module SolidQueue
       desc: "Path to config file (default: #{Configuration::DEFAULT_CONFIG_FILE_PATH}).",
       banner: "SOLID_QUEUE_CONFIG"
 
+    class_option :mode, type: :string, default: "fork", enum: %w[ fork async ],
+      desc: "Whether to fork processes for workers and dispatchers (fork) or to run these in the same process as the supervisor (async) (default: fork).",
+      banner: "SOLID_QUEUE_SUPERVISOR_MODE"
+
     class_option :recurring_schedule_file, type: :string,
       desc: "Path to recurring schedule definition (default: #{Configuration::DEFAULT_RECURRING_SCHEDULE_FILE_PATH}).",
       banner: "SOLID_QUEUE_RECURRING_SCHEDULE"

data/lib/solid_queue/configuration.rb

@@ -56,6 +56,14 @@ module SolidQueue
       end
     end
 
+    def mode
+      @options[:mode].to_s.inquiry
+    end
+
+    def standalone?
+      mode.fork? || @options[:standalone]
+    end
+
     private
       attr_reader :options
 
@@ -84,6 +92,8 @@ module SolidQueue
 
       def default_options
         {
+          mode: ENV["SOLID_QUEUE_SUPERVISOR_MODE"] || :fork,
+          standalone: true,
           config_file: Rails.root.join(ENV["SOLID_QUEUE_CONFIG"] || DEFAULT_CONFIG_FILE_PATH),
           recurring_schedule_file: Rails.root.join(ENV["SOLID_QUEUE_RECURRING_SCHEDULE"] || DEFAULT_RECURRING_SCHEDULE_FILE_PATH),
           only_work: false,
@@ -110,7 +120,12 @@ module SolidQueue
 
       def workers
         workers_options.flat_map do |worker_options|
-          processes = worker_options.fetch(:processes, WORKER_DEFAULTS[:processes])
+          processes = if mode.fork?
+            worker_options.fetch(:processes, WORKER_DEFAULTS[:processes])
+          else
+            1
+          end
+
           processes.times.map { Process.new(:worker, worker_options.with_defaults(WORKER_DEFAULTS)) }
         end
       end

data/lib/solid_queue/dispatcher.rb

@@ -3,6 +3,7 @@
 module SolidQueue
   class Dispatcher < Processes::Poller
     include LifecycleHooks
+
     attr_reader :batch_size
 
     after_boot :run_start_hooks

data/lib/solid_queue/fork_supervisor.rb

@@ -0,0 +1,68 @@
+# frozen_string_literal: true
+
+module SolidQueue
+  class ForkSupervisor < Supervisor
+    private
+
+    def perform_graceful_termination
+      term_forks
+
+      Timer.wait_until(SolidQueue.shutdown_timeout, -> { all_processes_terminated? }) do
+        reap_terminated_forks
+      end
+    end
+
+    def perform_immediate_termination
+      quit_forks
+    end
+
+    def term_forks
+      signal_processes(process_instances.keys, :TERM)
+    end
+
+    def quit_forks
+      signal_processes(process_instances.keys, :QUIT)
+    end
+
+    def check_and_replace_terminated_processes
+      loop do
+        pid, status = ::Process.waitpid2(-1, ::Process::WNOHANG)
+        break unless pid
+
+        replace_fork(pid, status)
+      end
+    end
+
+    def reap_terminated_forks
+      loop do
+        pid, status = ::Process.waitpid2(-1, ::Process::WNOHANG)
+        break unless pid
+
+        if (terminated_fork = process_instances.delete(pid)) && !status.exited? || status.exitstatus > 0
+          error = Processes::ProcessExitError.new(status)
+          release_claimed_jobs_by(terminated_fork, with_error: error)
+        end
+
+        configured_processes.delete(pid)
+      end
+    rescue SystemCallError
+      # All children already reaped
+    end
+
+    def replace_fork(pid, status)
+      SolidQueue.instrument(:replace_fork, supervisor_pid: ::Process.pid, pid: pid, status: status) do |payload|
+        if terminated_fork = process_instances.delete(pid)
+          payload[:fork] = terminated_fork
+          error = Processes::ProcessExitError.new(status)
+          release_claimed_jobs_by(terminated_fork, with_error: error)
+
+          start_process(configured_processes.delete(pid))
+        end
+      end
+    end
+
+    def all_processes_terminated?
+      process_instances.empty?
+    end
+  end
+end

data/lib/solid_queue/processes/runnable.rb

@@ -7,20 +7,26 @@ module SolidQueue::Processes
     attr_writer :mode
 
     def start
-      boot
-
-      if running_async?
-        @thread = create_thread { run }
-      else
+      run_in_mode do
+        boot
         run
       end
     end
 
     def stop
       super
-
       wake_up
-      @thread&.join
+
+      # When not supervised, block until the thread terminates for backward
+      # compatibility with code that expects stop to be synchronous.
+      # When supervised, the supervisor controls the shutdown timeout.
+      unless supervised?
+        @thread&.join
+      end
+    end
+
+    def alive?
+      !running_async? || @thread&.alive?
     end
 
     private
@@ -30,6 +36,18 @@ module SolidQueue::Processes
         (@mode || DEFAULT_MODE).to_s.inquiry
       end
 
+      def run_in_mode(&block)
+        case
+        when running_as_fork?
+          fork(&block)
+        when running_async?
+          @thread = create_thread(&block)
+          @thread.object_id
+        else
+          block.call
+        end
+      end
+
       def boot
         SolidQueue.instrument(:start_process, process: self) do
           run_callbacks(:boot) do
@@ -74,16 +92,5 @@ module SolidQueue::Processes
       def running_as_fork?
         mode.fork?
       end
-
-
-      def create_thread(&block)
-        Thread.new do
-          Thread.current.name = name
-          block.call
-        rescue Exception => exception
-          handle_thread_error(exception)
-          raise
-        end
-      end
   end
 end

data/lib/solid_queue/processes/thread_terminated_error.rb

@@ -0,0 +1,11 @@
+# frozen_string_literal: true
+
+module SolidQueue
+  module Processes
+    class ThreadTerminatedError < RuntimeError
+      def initialize(name)
+        super("Thread #{name} terminated unexpectedly")
+      end
+    end
+  end
+end

data/lib/solid_queue/supervisor/maintenance.rb

@@ -32,5 +32,16 @@ module SolidQueue
           ClaimedExecution.orphaned.fail_all_with(Processes::ProcessMissingError.new)
         end
       end
+
+      # When a supervised process crashes or exits we need to mark all the
+      # executions it had claimed as failed so that they can be retried
+      # by some other worker.
+      def release_claimed_jobs_by(terminated_process, with_error:)
+        wrap_in_app_executor do
+          if registered_process = SolidQueue::Process.find_by(name: terminated_process.name)
+            registered_process.fail_all_claimed_executions_with(with_error)
+          end
+        end
+      end
   end
 end

data/lib/solid_queue/supervisor/signals.rb

@@ -6,8 +6,8 @@ module SolidQueue
       extend ActiveSupport::Concern
 
       included do
-        before_boot :register_signal_handlers
-        after_shutdown :restore_default_signal_handlers
+        before_boot :register_signal_handlers, if: :standalone?
+        after_shutdown :restore_default_signal_handlers, if: :standalone?
       end
 
       private

data/lib/solid_queue/supervisor.rb

@@ -13,17 +13,21 @@ module SolidQueue
         configuration = Configuration.new(**options)
 
         if configuration.valid?
-          new(configuration).tap(&:start)
+          klass = configuration.mode.fork? ? ForkSupervisor : AsyncSupervisor
+          klass.new(configuration).tap(&:start)
         else
           abort configuration.errors.full_messages.join("\n") + "\nExiting..."
         end
       end
     end
 
+    delegate :mode, :standalone?, to: :configuration
+
     def initialize(configuration)
       @configuration = configuration
-      @forks = {}
+
       @configured_processes = {}
+      @process_instances = {}
 
       super
     end
@@ -43,8 +47,12 @@ module SolidQueue
       run_stop_hooks
     end
 
+    def kind
+      "Supervisor(#{mode})"
+    end
+
     private
-      attr_reader :configuration, :forks, :configured_processes
+      attr_reader :configuration, :configured_processes, :process_instances
 
       def boot
         SolidQueue.instrument(:start_process, process: self) do
@@ -62,11 +70,13 @@ module SolidQueue
         loop do
           break if stopped?
 
-          set_procline
-          process_signal_queue
+          if standalone?
+            set_procline
+            process_signal_queue
+          end
 
           unless stopped?
-            reap_and_replace_terminated_forks
+            check_and_replace_terminated_processes
             interruptible_sleep(1.second)
           end
         end
@@ -77,30 +87,23 @@ module SolidQueue
       def start_process(configured_process)
         process_instance = configured_process.instantiate.tap do |instance|
           instance.supervised_by process
-          instance.mode = :fork
+          instance.mode = mode
         end
 
-        pid = fork do
-          process_instance.start
-        end
+        process_id = process_instance.start
 
-        configured_processes[pid] = configured_process
-        forks[pid] = process_instance
+        configured_processes[process_id] = configured_process
+        process_instances[process_id] = process_instance
       end
 
-      def set_procline
-        procline "supervising #{supervised_processes.join(", ")}"
+      def check_and_replace_terminated_processes
       end
 
       def terminate_gracefully
-        SolidQueue.instrument(:graceful_termination, process_id: process_id, supervisor_pid: ::Process.pid, supervised_processes: supervised_processes) do |payload|
-          term_forks
-
-          Timer.wait_until(SolidQueue.shutdown_timeout, -> { all_forks_terminated? }) do
-            reap_terminated_forks
-          end
+        SolidQueue.instrument(:graceful_termination, process_id: process_id, supervisor_pid: ::Process.pid, supervised_processes: configured_processes.keys) do |payload|
+          perform_graceful_termination
 
-          unless all_forks_terminated?
+          unless all_processes_terminated?
             payload[:shutdown_timeout_exceeded] = true
             terminate_immediately
           end
@@ -108,84 +111,37 @@ module SolidQueue
       end
 
       def terminate_immediately
-        SolidQueue.instrument(:immediate_termination, process_id: process_id, supervisor_pid: ::Process.pid, supervised_processes: supervised_processes) do
-          quit_forks
-        end
-      end
-
-      def shutdown
-        SolidQueue.instrument(:shutdown_process, process: self) do
-          run_callbacks(:shutdown) do
-            stop_maintenance_task
-          end
+        SolidQueue.instrument(:immediate_termination, process_id: process_id, supervisor_pid: ::Process.pid, supervised_processes: configured_processes.keys) do
+          perform_immediate_termination
         end
       end
 
-      def sync_std_streams
-        STDOUT.sync = STDERR.sync = true
+      def perform_graceful_termination
+        raise NotImplementedError
       end
 
-      def supervised_processes
-        forks.keys
+      def perform_immediate_termination
+        raise NotImplementedError
       end
 
-      def term_forks
-        signal_processes(forks.keys, :TERM)
+      def all_processes_terminated?
+        raise NotImplementedError
       end
 
-      def quit_forks
-        signal_processes(forks.keys, :QUIT)
-      end
-
-      def reap_and_replace_terminated_forks
-        loop do
-          pid, status = ::Process.waitpid2(-1, ::Process::WNOHANG)
-          break unless pid
-
-          replace_fork(pid, status)
-        end
-      end
-
-      def reap_terminated_forks
-        loop do
-          pid, status = ::Process.waitpid2(-1, ::Process::WNOHANG)
-          break unless pid
-
-          if (terminated_fork = forks.delete(pid)) && (!status.exited? || status.exitstatus > 0)
-            handle_claimed_jobs_by(terminated_fork, status)
-          end
-
-          configured_processes.delete(pid)
-        end
-      rescue SystemCallError
-        # All children already reaped
-      end
-
-      def replace_fork(pid, status)
-        SolidQueue.instrument(:replace_fork, supervisor_pid: ::Process.pid, pid: pid, status: status) do |payload|
-          if terminated_fork = forks.delete(pid)
-            payload[:fork] = terminated_fork
-            handle_claimed_jobs_by(terminated_fork, status)
-
-            start_process(configured_processes.delete(pid))
+      def shutdown
+        SolidQueue.instrument(:shutdown_process, process: self) do
+          run_callbacks(:shutdown) do
+            stop_maintenance_task
           end
         end
       end
 
-      # When a supervised fork crashes or exits we need to mark all the
-      # executions it had claimed as failed so that they can be retried
-      # by some other worker.
-      def handle_claimed_jobs_by(terminated_fork, status)
-        wrap_in_app_executor do
-          if registered_process = SolidQueue::Process.find_by(name: terminated_fork.name)
-            error = Processes::ProcessExitError.new(status)
-            registered_process.fail_all_claimed_executions_with(error)
-          end
-        end
+      def set_procline
+        procline "supervising #{configured_processes.keys.join(", ")}"
       end
 
-      def all_forks_terminated?
-        forks.empty?
+      def sync_std_streams
+        STDOUT.sync = STDERR.sync = true
       end
   end
 end

data/lib/solid_queue/timer.rb

@@ -4,18 +4,18 @@ module SolidQueue
   module Timer
     extend self
 
-    def wait_until(timeout, condition, &block)
+    def wait_until(timeout, condition)
       if timeout > 0
         deadline = monotonic_time_now + timeout
 
         while monotonic_time_now < deadline && !condition.call
           sleep 0.1
-          block.call
+          yield if block_given?
         end
       else
         while !condition.call
           sleep 0.5
-          block.call
+          yield if block_given?
         end
       end
     end

data/lib/solid_queue/version.rb

@@ -1,3 +1,3 @@
 module SolidQueue
-  VERSION = "1.2.4"
+  VERSION = "1.3.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: solid_queue
 version: !ruby/object:Gem::Version
-  version: 1.2.4
+  version: 1.3.0
 platform: ruby
 authors:
 - Rosa Gutierrez
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2025-10-30 00:00:00.000000000 Z
+date: 2026-01-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activerecord
@@ -122,6 +122,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.9'
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
 - !ruby/object:Gem::Dependency
   name: mocha
   requirement: !ruby/object:Gem::Requirement
@@ -297,11 +311,13 @@ files:
 - lib/puma/plugin/solid_queue.rb
 - lib/solid_queue.rb
 - lib/solid_queue/app_executor.rb
+- lib/solid_queue/async_supervisor.rb
 - lib/solid_queue/cli.rb
 - lib/solid_queue/configuration.rb
 - lib/solid_queue/dispatcher.rb
 - lib/solid_queue/dispatcher/concurrency_maintenance.rb
 - lib/solid_queue/engine.rb
+- lib/solid_queue/fork_supervisor.rb
 - lib/solid_queue/lifecycle_hooks.rb
 - lib/solid_queue/log_subscriber.rb
 - lib/solid_queue/pool.rb
@@ -316,6 +332,7 @@ files:
 - lib/solid_queue/processes/registrable.rb
 - lib/solid_queue/processes/runnable.rb
 - lib/solid_queue/processes/supervised.rb
+- lib/solid_queue/processes/thread_terminated_error.rb
 - lib/solid_queue/scheduler.rb
 - lib/solid_queue/scheduler/recurring_schedule.rb
 - lib/solid_queue/supervisor.rb