[ruby-core:124898] [Ruby Feature#21930] Add Ractor#empty? method to check for pending messages without blocking

2 Mar 2026

      Issue #21930 has been updated by synacker (Mikhail Milovidov).

nobu (Nobuyoshi Nakada) wrote in #note-3:
...
This sounds like leading to a typical TOC/TOU problem.
I appreciate the concern about a potential TOC/TOU (Time‑of‑Check to Time‑of‑Use) issue, but I believe it doesn’t apply in this specific case. Consider the following pattern:

```ruby
messages = []
while !Ractor.current.empty?
  messages << Ractor.receive
end
process_batch(messages) if messages.any?
```
In this code:

* The «check» (empty?) and the «use» (receive) are tightly coupled in a loop.
* Even if a new message arrives after the empty? check but before the receive call, the loop will catch it on the next iteration.
* The batch simply grows by one more message — no data is lost, and no invalid state is entered.
* This pattern is by design: the goal is to collect all available messages at the moment of polling, not to make an atomic decision based on a single state snapshot.

Thus, ```Ractor#empty?``` doesn’t introduce a new race condition — it enables a safe and efficient polling mechanism that’s already common in concurrent systems (e.g., event loops).

nobu (Nobuyoshi Nakada) wrote in #note-3:
...
As for your example, why does `Worker` ractor handle both of `main_task` and dispatch alone, instead of launching each ractors?
You asked why the Worker Ractor handles both main_task and dispatch logic instead of launching a separate Ractor per task. Here’s why creating one Ractor per task is impractical:

1. Key drawbacks of one‑Ractor‑per‑task:

* High overhead. Creating a Ractor is significantly more expensive than sending a message or scheduling a Fiber. For 10 000 tasks, spawning 10 000 Ractors would cause massive memory and scheduling overhead.
* Resource exhaustion. The OS and Ruby VM have limits on concurrent threads/processes. Unbounded Ractor creation risks crashing the system or exhausting system resources.
* Complex coordination. Managing 10 000+ Ractors (joining, error handling, monitoring, logging) becomes a complex task in itself, adding significant operational burden.

2. Why the Worker Ractor acts as a managed pool:
The current design uses a bounded number of Ractors (typically one per CPU core) and leverages Fibers for cooperative multitasking within each Ractor. Specifically:
* It receives a stream of commands (TimeCommand objects) via the Ractor message queue.
* It uses the Async gem to run their task method concurrently within the same Ractor, using Fibers to achieve lightweight concurrency.

This approach follows a well‑established architectural pattern for high‑load systems:
* Create a fixed number of Ractors, typically matching the number of CPU cores (or a small multiple of it), to avoid OS/VM resource exhaustion.
* Within each Ractor, use cooperative multitasking (Fibers, event loops, coroutines) to handle many concurrent operations efficiently.
* Use ```Ractor#empty?``` as a scheduler hint — to batch work and yield control when idle — not as a security or state‑decision primitive.

This pattern balances high concurrency with bounded resource usage, making it suitable for production workloads.

Thank you again for the thoughtful questions — they help clarify the design rationale. Let me know if you’d like me to elaborate on any point!

----------------------------------------
Feature #21930: Add Ractor#empty? method to check for pending messages without blocking
https://bugs.ruby-lang.org/issues/21930#change-116557

* Author: synacker (Mikhail Milovidov)
* Status: Feedback
----------------------------------------
**Summary**
In concurrent Ractor‑based architectures, there’s a critical need to check whether a Ractor has pending messages without blocking. Currently, this is not possible with the standard API

**Motivation**
The Ractor API provides a powerful mechanism for communication between system OS threads. However, in high‑load systems that use cooperative multitasking, the current Ractor#receive method presents limitations:

* It blocks the current thread until a message arrives.

* It doesn’t offer a non‑blocking way to check the message queue.

* This makes it difficult to integrate Ractors with cooperative scheduling frameworks (e.g., Async, Fiber‑based systems).

As a result, developers must either:

* Accept thread blocking (hurting responsiveness).

* Implement complex workarounds with timeouts or auxiliary queues.

**Proposed solution**
Add Ractor#empty? to the Ractor API. The method should:

* Return true if there are no pending messages in the Ractor’s main queue.

* Return false if there is at least one message available for processing.

* Not block the calling thread under any circumstances.

* Be safe to call from any Ractor (including the current one).

**Demonstration code**
Below is a proof‑of‑concept showing how Ractor#empty? enables cooperative multitasking with the Async gem:

```ruby
require 'async'

class TimeCommand
    attr_reader :id

    def initialize(id)
        @id = id
    end

    def task
        1.upto(3) do |i|      
            sleep(1)
            puts "[cmd #{@id}] step #{i} @ #{Time.now}"
        end
    end
end

class Worker
    def initialize
        @ractor = Ractor.new do
            loop do
                Sync do |task|
                    in_queue = Async::Queue.new
                    queue_task = task.async do |subtask|
                        while command = in_queue.dequeue
                            subtask.async do |child_task|
                                command.task
                            end
                        end
                    end

                    task.async(transient: true) do |main_task|
                        loop do
                            commands = []
                            if queue_task.children? || !in_queue.empty?
                                main_task.yield
                                commands.append Ractor.receive while !Ractor.current.empty?
                            else
                                commands.append Ractor.receive
                            end

                            unless commands.empty?
                                puts "Worker received batch of #{commands.size} commands."
                                commands.each { |command| in_queue.enqueue(command) }
                            end
                        end
                    end
                end
            end

        end
    end

    def send(command)
        @ractor.send(command, move: true)
    end

    def wait
        @ractor.join
    end
end

worker = Worker.new

1000.times do |i|
    100.times do |j|
        worker.send TimeCommand.new(i * 10 + j)
    end
    sleep(1)
end

worker.wait
```

**Key observations:**
With Ractor#empty?, developers can:

* Integrate Ractors with cooperative multitasking frameworks (e.g., Async) more naturally.

* Avoid thread blocking when checking for incoming messages.

* Batch process messages efficiently (collect all pending messages in one go).

* Improve responsiveness in high‑concurrency scenarios by yielding control back to the scheduler when no work is available.

**Benefits**

* Enables better integration with modern Ruby concurrency tools.

* Reduces need for complex workarounds.

* Improves performance in message‑driven architectures.

* Maintains Ractor’s thread‑safety guarantees.

-- 
https://bugs.ruby-lang.org/