protobuf-nats 0.13.1 → 0.13.2.pre1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: aeb96c5f90852f8dfdf32450fe5290325684cec82dbb88bd7b7e393db09cb6bb
-  data.tar.gz: b577ae715c8fc9669b815510f0e2032b9454e9aef63c58731590c2fe2c3152c0
+  metadata.gz: 89549ac1d866b16970644740b1da683f985b150db9c03ed5a06d5c20eb81d77b
+  data.tar.gz: 3908346e349fb6e8c95ba13e89b5fa31872dc38be7a6103ad5bd327a19806062
 SHA512:
-  metadata.gz: 81fe350143450675623252856ce7fe30253e3204699c9a2a6dbe8c7c270ea381567d55d3b7bde2b2c17078c64e46700a5f35a75f660bcc7b6f3e81b5fc4ea5b9
-  data.tar.gz: f8c98030a76607518ecfdce5c47a9f2cba2d2ab52ffddfd46a75e0d173e5d62203b122fe747aacd805245815ae4901c1625f7147d5f4228f0497f94ea2f41aec
+  metadata.gz: 78886bd247470672da944c13f90b538e6913bf5378677bb3da5dc0ac48ee3f501e582a40d6501c8ae0b41ef66dc6368626a79d852a17929ca6739acdc27bd378
+  data.tar.gz: ba529ee4a32f3c4360d22bbd52a8bb04a175b97684fe8c5ca8b8e65b5a11d6f3a04fceaf5415872b951cc373f284146b76422bbe7eff467fa52c264af878f47d

data/lib/protobuf/nats/response_muxer.rb

@@ -13,6 +13,16 @@ module Protobuf
       MAX_RESPONSES_PER_TOKEN = 10
       TOKEN_TTL_SECONDS = 600 # 10 minutes
 
+      # Sentinel pushed onto a token's queue to wake a waiter blocked in
+      # next_message. We cannot rely on Queue#close alone: on JRuby, close does
+      # NOT wake a pop() that is blocked with a timeout: -- neither the native
+      # Queue (Ruby >= 3.2 / JRuby 10) nor concurrent-ruby's RubyTimeoutQueue
+      # (Ruby < 3.2 / JRuby 9.4, whose timed pop only wakes on push) signals a
+      # timed waiter on close. CRuby's Queue#close does wake it, which is why
+      # this only ever bit JRuby. Pushing an explicit sentinel wakes the waiter
+      # immediately on every engine; next_message treats it as a timeout.
+      QUEUE_WAKE = ::Object.new
+
       def initialize
         # Per-token response queues for lock-free message delivery. @resp_map is a
         # Concurrent::Map so request threads and dispatcher threads can insert,
@@ -66,9 +76,24 @@ module Protobuf
       end
 
       def cleanup(token)
-        # Atomic remove-and-return; close the queue to wake any waiting threads.
+        # Atomic remove-and-return; wake+close the queue to release any waiter.
         entry = @resp_map.delete(token)
-        entry[:queue]&.close if entry
+        wake_and_close_queue(entry[:queue]) if entry
+      end
+
+      # Wake any waiter blocked in next_message on this queue, then close it.
+      # Pushing QUEUE_WAKE is what actually wakes a timed pop on JRuby (see the
+      # QUEUE_WAKE comment); close alone is insufficient there. Safe to call on
+      # an already-closed queue.
+      def wake_and_close_queue(queue)
+        return unless queue
+        begin
+          queue.push(QUEUE_WAKE)
+        rescue ::ClosedQueueError, ::ThreadError
+          # Already closed by another path; a plain (untimed) waiter, if any,
+          # was already woken by that close. Nothing more to do.
+        end
+        queue.close
       end
 
       def next_message(token, timeout)
@@ -101,7 +126,10 @@ module Protobuf
           # Queue.pop returns nil when:
           # 1. The queue is closed
           # 2. The timeout expires
-          unless msg
+          # QUEUE_WAKE is the sentinel pushed by wake_and_close_queue to wake a
+          # timed pop on JRuby (where close alone does not); treat it as a
+          # timeout so the caller fails over instead of returning garbage.
+          if msg.nil? || msg.equal?(QUEUE_WAKE)
             logger.warn "Queue closed or timeout for token #{token} during next_message"
             raise ::NATS::Timeout
           end
@@ -293,8 +321,8 @@ module Protobuf
           next unless data
           stale_count += 1
           logger.warn "Cleaning up stale token #{token} created at #{data[:created_at]}"
-          # Close the queue to wake any waiting threads
-          data[:queue]&.close
+          # Wake any waiting thread, then close the queue.
+          wake_and_close_queue(data[:queue])
         end
 
         if stale_count > 0
@@ -348,7 +376,7 @@ module Protobuf
       # Must be called while holding LOCK (only from drop_subscription_locked).
       def fail_inflight_requests
         @resp_map.each_pair do |_token, entry|
-          entry[:queue]&.close
+          wake_and_close_queue(entry[:queue])
         end
       end
 

data/lib/protobuf/nats/super_subscription_manager.rb

@@ -89,14 +89,12 @@ module Protobuf
             break
           end
 
-          # Non-blocking push with timeout
-          begin
-            Timeout.timeout(1) do
-              @pending_queue << msg
-            end
+          # Push with a deadline (see push_with_deadline: no Timeout.timeout,
+          # which corrupts the SizedQueue mutex on JRuby).
+          if push_with_deadline(msg, 1)
             migrated_count += 1
             logger.warn "Migrated message #{migrated_count} from old queue to central queue"
-          rescue Timeout::Error
+          else
             logger.error "Failed to migrate message to central queue (queue full), dropping message"
             break
           end
@@ -117,15 +115,15 @@ module Protobuf
 
         # Wake every handler with its own poison pill.
         handlers.size.times do
-          begin
-            # Clear some space if the queue is full so the shutdown signal fits.
-            if @pending_queue.num_waiting.zero? && @pending_queue.size >= @pending_queue.max
-              logger.warn "Queue full during shutdown, clearing to make room for shutdown signal"
-              @pending_queue.clear rescue nil
-            end
+          # Clear some space if the queue is full so the shutdown signal fits.
+          if @pending_queue.num_waiting.zero? && @pending_queue.size >= @pending_queue.max
+            logger.warn "Queue full during shutdown, clearing to make room for shutdown signal"
+            @pending_queue.clear rescue nil
+          end
 
-            Timeout.timeout(1) { @pending_queue << :shutdown }
-          rescue Timeout::Error
+          # Push with a deadline (see push_with_deadline: no Timeout.timeout,
+          # which corrupts the SizedQueue mutex on JRuby).
+          unless push_with_deadline(:shutdown, 1)
             logger.error "Failed to send shutdown signal (queue blocked); will force-kill remaining handlers"
             break
           end
@@ -178,6 +176,32 @@ module Protobuf
         ::Protobuf::Nats.monotonic_time
       end
 
+      # Push onto the shared SizedQueue with a deadline, WITHOUT Timeout.timeout.
+      # Timeout uses an asynchronous Thread#raise, which is unsafe around the
+      # mutex SizedQueue#push takes internally: on JRuby (10.x in particular) a
+      # timeout firing mid-push unwinds through the held mutex and raises
+      # "ThreadError: Attempt to unlock a mutex which is locked by another
+      # thread/fiber" instead of Timeout::Error -- so the rescue :Timeout::Error
+      # never fires and shutdown/migration blow up. CRuby happens to unwind
+      # cleanly, which is why this only bit JRuby. Poll a non-blocking push
+      # against a monotonic deadline instead: no async raise, safe on every
+      # engine. Returns true if pushed, false if the deadline passed (queue
+      # still full) or the queue was closed.
+      def push_with_deadline(obj, timeout)
+        deadline = monotonic + timeout
+        loop do
+          begin
+            @pending_queue.push(obj, true) # non_block: raises ThreadError when full
+            return true
+          rescue ::ClosedQueueError
+            return false
+          rescue ::ThreadError
+            return false if monotonic >= deadline
+            sleep 0.01
+          end
+        end
+      end
+
       # Spawn one intake handler. Each thread owns its own crash_count so the
       # self-healing exponential backoff is correct under true parallelism (a
       # shared counter would lose updates across handlers on JRuby). The counter

data/lib/protobuf/nats/version.rb

@@ -1,5 +1,5 @@
 module Protobuf
   module Nats
-    VERSION = "0.13.1"
+    VERSION = "0.13.2.pre1"
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: protobuf-nats
 version: !ruby/object:Gem::Version
-  version: 0.13.1
+  version: 0.13.2.pre1
 platform: ruby
 authors:
 - Brandon Dewitt
@@ -183,9 +183,7 @@ extensions: []
 extra_rdoc_files: []
 files:
 - ".circleci/config.yml"
-- ".github/workflows/ci.yml"
 - ".gitignore"
-- ".travis.yml"
 - CHANGELOG.md
 - Gemfile
 - LICENSE.txt

data/.github/workflows/ci.yml

@@ -1,64 +0,0 @@
-name: CI
-
-on:
-  push:
-    branches: [master]
-  pull_request:
-
-jobs:
-  test:
-    runs-on: ubuntu-latest
-    strategy:
-      fail-fast: false
-      matrix:
-        ruby:
-          - "3.1"
-          - "3.4"
-          - "jruby-9.4"
-          - "jruby-10.0"
-
-    # Real NATS server for the integration specs (spec/integration/); they
-    # auto-detect it on localhost:4222 (see spec/spec_helper.rb).
-    services:
-      nats:
-        image: nats:2.14-linux
-        ports:
-          - 4222:4222
-
-    env:
-      JRUBY_OPTS: "-J-Xmx1024m"
-      RAILS_ENV: test
-
-    steps:
-      - uses: actions/checkout@v4
-
-      - uses: ruby/setup-ruby@v1
-        with:
-          ruby-version: ${{ matrix.ruby }}
-          bundler-cache: true
-
-      # The cluster failover spec (spec/integration/failover_spec.rb) spawns
-      # its own two-node cluster, so it needs the nats-server binary itself --
-      # the service container above only covers the single-node specs.
-      - name: Install nats-server binary (cluster failover spec)
-        run: |
-          NATS_VERSION=v2.14.3
-          curl -sfL "https://github.com/nats-io/nats-server/releases/download/${NATS_VERSION}/nats-server-${NATS_VERSION}-linux-amd64.tar.gz" | tar xz
-          sudo mv "nats-server-${NATS_VERSION}-linux-amd64/nats-server" /usr/local/bin/
-          nats-server --version
-
-      - name: Wait for NATS
-        run: |
-          echo "Waiting for NATS to start..."
-          for i in $(seq 1 30); do
-            if nc -z localhost 4222; then
-              echo "NATS is ready!"
-              exit 0
-            fi
-            sleep 1
-          done
-          echo "NATS did not become ready" >&2
-          exit 1
-
-      - name: Run tests
-        run: bundle exec rspec

data/.travis.yml

@@ -1,16 +0,0 @@
-sudo: false
-language: ruby
-jdk:
- - openjdk8
-rvm:
-  - 2.3.0
-  - 2.7.0
-  - jruby-9.1.7.0
-  - jruby-9.2.13.0
-before_install:
-  # Install and start gnatsd
-  - ./scripts/install_gnatsd.sh
-  - $HOME/nats-server/nats-server &
-  # Install deps for project
-  - gem install bundler
-  - gem update --system