kino 0.5.0 → 0.7.0

data/ext/kino/src/test_support.rs

@@ -92,3 +92,47 @@ pub fn close(ruby: &magnus::Ruby, id: u64) -> Result<(), magnus::Error> {
     chan.tx.lock().take();
     Ok(())
 }
+
+/// Build the cache-backed slice of a Rack env directly, the way `build_env`
+/// does for a real request: REMOTE_ADDR from `ip`, SERVER_NAME/SERVER_PORT
+/// from `host` (the Host-header path) or, when `authority` is given, from
+/// it (the :authority path, which also sets HTTP_HOST), plus one interned
+/// header value. The rooting stress spec calls this from several ractors
+/// at once with more distinct inputs than the LRU caches hold.
+pub fn env_probe(
+    ruby: &magnus::Ruby,
+    host: String,
+    authority: Option<String>,
+    ip: String,
+    user_agent: String,
+) -> Result<magnus::RHash, magnus::Error> {
+    use crate::env_strings;
+    use crate::request::split_host_port;
+
+    let ip: std::net::IpAddr = ip.parse().map_err(|e| {
+        magnus::Error::new(ruby.exception_arg_error(), format!("bad ip {ip:?}: {e}"))
+    })?;
+    let env = ruby.hash_new();
+    env_strings::set_addr_env(ruby, env, ip)?;
+    match &authority {
+        Some(authority) => {
+            env_strings::set_authority_env(ruby, env, authority, || split_host_port(authority, 80))?
+        }
+        None => {
+            env_strings::set_host_env(ruby, env, host.as_bytes(), || split_host_port(&host, 80))?
+        }
+    }
+    let strings = env_strings::get();
+    let key = strings
+        .header_names
+        .get("user-agent")
+        .expect("user-agent is a common header");
+    env_strings::set_value_env(
+        ruby,
+        env,
+        ruby.get_inner(*key),
+        "user-agent",
+        user_agent.as_bytes(),
+    )?;
+    Ok(env)
+}

data/ext/kino/src/tls.rs

@@ -17,7 +17,13 @@ fn pem_bytes(input: &str) -> Result<Vec<u8>, String> {
     }
 }
 
-pub fn build_acceptor(cert: &str, key: &str) -> Result<TlsAcceptor, String> {
+pub fn build_acceptor(cert: &str, key: &str, http2: bool) -> Result<TlsAcceptor, String> {
+    Ok(TlsAcceptor::from(Arc::new(server_config(
+        cert, key, http2,
+    )?)))
+}
+
+fn server_config(cert: &str, key: &str, http2: bool) -> Result<ServerConfig, String> {
     let cert_pem = pem_bytes(cert)?;
     let key_pem = pem_bytes(key)?;
 
@@ -36,14 +42,19 @@ pub fn build_acceptor(cert: &str, key: &str) -> Result<TlsAcceptor, String> {
         .with_no_client_auth()
         .with_single_cert(certs, key)
         .map_err(|e| format!("TLS config rejected: {e}"))?;
-    config.alpn_protocols = vec![b"http/1.1".to_vec()];
-
-    Ok(TlsAcceptor::from(Arc::new(config)))
+    // Preference order matters: h2 first, so an HTTP/2-capable client
+    // negotiates it; a client offering only http/1.1 still matches.
+    config.alpn_protocols = if http2 {
+        vec![b"h2".to_vec(), b"http/1.1".to_vec()]
+    } else {
+        vec![b"http/1.1".to_vec()]
+    };
+    Ok(config)
 }
 
 #[cfg(test)]
 mod tests {
-    use super::build_acceptor;
+    use super::{build_acceptor, server_config};
 
     const CERT: &str = "-----BEGIN CERTIFICATE-----
 MIIBfjCCASWgAwIBAgIUTs9+cVJSzJjy4TSi9YLEd+i4KiIwCgYIKoZIzj0EAwIw
@@ -65,12 +76,12 @@ WJ2lRijROyX9v7f8aSQlb6kEwKhI8kG8SbeUc+zbKkzGgRXNaZHY/mAa
 
     #[test]
     fn inline_pem_builds_an_acceptor() {
-        assert!(build_acceptor(CERT, KEY).is_ok());
+        assert!(build_acceptor(CERT, KEY, true).is_ok());
     }
 
     #[test]
     fn missing_file_paths_error_without_panicking() {
-        let err = build_acceptor("/nonexistent/cert.pem", "/nonexistent/key.pem")
+        let err = build_acceptor("/nonexistent/cert.pem", "/nonexistent/key.pem", true)
             .err()
             .expect("missing files");
         assert!(err.contains("cannot read"));
@@ -78,13 +89,15 @@ WJ2lRijROyX9v7f8aSQlb6kEwKhI8kG8SbeUc+zbKkzGgRXNaZHY/mAa
 
     #[test]
     fn pem_without_certificates_is_rejected() {
-        let err = build_acceptor(KEY, KEY).err().expect("a key is not a cert");
+        let err = build_acceptor(KEY, KEY, true)
+            .err()
+            .expect("a key is not a cert");
         assert!(err.contains("no certificates found"));
     }
 
     #[test]
     fn pem_without_a_key_is_rejected() {
-        let err = build_acceptor(CERT, CERT)
+        let err = build_acceptor(CERT, CERT, true)
             .err()
             .expect("a cert is not a key");
         assert!(err.contains("no private key found"));
@@ -95,9 +108,106 @@ WJ2lRijROyX9v7f8aSQlb6kEwKhI8kG8SbeUc+zbKkzGgRXNaZHY/mAa
         let err = build_acceptor(
             CERT,
             "-----BEGIN PRIVATE KEY-----\ngarbage\n-----END PRIVATE KEY-----",
+            true,
         )
         .err()
         .expect("garbage key");
         assert!(!err.is_empty());
     }
+
+    #[test]
+    fn alpn_advertises_h2_first_when_http2_is_on() {
+        let config = server_config(CERT, KEY, true).expect("valid PEM");
+        assert_eq!(
+            config.alpn_protocols,
+            vec![b"h2".to_vec(), b"http/1.1".to_vec()]
+        );
+    }
+
+    #[test]
+    fn alpn_advertises_only_http11_when_http2_is_off() {
+        let config = server_config(CERT, KEY, false).expect("valid PEM");
+        assert_eq!(config.alpn_protocols, vec![b"http/1.1".to_vec()]);
+    }
+
+    /// A real rustls handshake over an in-memory pipe: an h2-capable
+    /// client must land on "h2", proving the advertisement is not just a
+    /// config field but what the wire negotiates. The client skips
+    /// certificate verification (the fixture cert is CA-flagged, which
+    /// webpki refuses as an end-entity cert): ALPN is under test here,
+    /// not the trust chain.
+    #[tokio::test]
+    async fn handshake_negotiates_h2_with_a_capable_client() {
+        use std::sync::Arc;
+
+        use tokio_rustls::rustls::client::danger::{
+            HandshakeSignatureValid, ServerCertVerified, ServerCertVerifier,
+        };
+        use tokio_rustls::rustls::crypto::WebPkiSupportedAlgorithms;
+        use tokio_rustls::rustls::pki_types::ServerName;
+        use tokio_rustls::rustls::ClientConfig;
+        use tokio_rustls::{TlsAcceptor, TlsConnector};
+
+        #[derive(Debug)]
+        struct AcceptAny(WebPkiSupportedAlgorithms);
+
+        impl ServerCertVerifier for AcceptAny {
+            fn verify_server_cert(
+                &self,
+                _end_entity: &tokio_rustls::rustls::pki_types::CertificateDer<'_>,
+                _intermediates: &[tokio_rustls::rustls::pki_types::CertificateDer<'_>],
+                _server_name: &ServerName<'_>,
+                _ocsp_response: &[u8],
+                _now: tokio_rustls::rustls::pki_types::UnixTime,
+            ) -> Result<ServerCertVerified, tokio_rustls::rustls::Error> {
+                Ok(ServerCertVerified::assertion())
+            }
+
+            fn verify_tls12_signature(
+                &self,
+                _message: &[u8],
+                _cert: &tokio_rustls::rustls::pki_types::CertificateDer<'_>,
+                _dss: &tokio_rustls::rustls::DigitallySignedStruct,
+            ) -> Result<HandshakeSignatureValid, tokio_rustls::rustls::Error> {
+                Ok(HandshakeSignatureValid::assertion())
+            }
+
+            fn verify_tls13_signature(
+                &self,
+                _message: &[u8],
+                _cert: &tokio_rustls::rustls::pki_types::CertificateDer<'_>,
+                _dss: &tokio_rustls::rustls::DigitallySignedStruct,
+            ) -> Result<HandshakeSignatureValid, tokio_rustls::rustls::Error> {
+                Ok(HandshakeSignatureValid::assertion())
+            }
+
+            fn supported_verify_schemes(&self) -> Vec<tokio_rustls::rustls::SignatureScheme> {
+                self.0.supported_schemes()
+            }
+        }
+
+        let acceptor =
+            TlsAcceptor::from(Arc::new(server_config(CERT, KEY, true).expect("valid PEM")));
+
+        let provider = tokio_rustls::rustls::crypto::ring::default_provider();
+        let verifier = AcceptAny(provider.signature_verification_algorithms);
+        let mut client = ClientConfig::builder()
+            .dangerous()
+            .with_custom_certificate_verifier(Arc::new(verifier))
+            .with_no_client_auth();
+        client.alpn_protocols = vec![b"h2".to_vec(), b"http/1.1".to_vec()];
+        let connector = TlsConnector::from(Arc::new(client));
+
+        let (client_io, server_io) = tokio::io::duplex(16 * 1024);
+        let server = tokio::spawn(async move { acceptor.accept(server_io).await });
+        let domain = ServerName::try_from("localhost").expect("server name");
+        let client_stream = connector
+            .connect(domain, client_io)
+            .await
+            .expect("client handshake");
+        let server_stream = server.await.expect("join").expect("server handshake");
+
+        assert_eq!(client_stream.get_ref().1.alpn_protocol(), Some(&b"h2"[..]));
+        assert_eq!(server_stream.get_ref().1.alpn_protocol(), Some(&b"h2"[..]));
+    }
 }

data/lib/kino/cli.rb

@@ -127,7 +127,7 @@ module Kino
       stats = server.stats
       puts dim("- ruby:      #{RUBY_DESCRIPTION}")
       puts dim("- env:       #{ENV["RAILS_ENV"] || ENV["RACK_ENV"] || "development"}")
-      puts dim("- mode:      #{server.mode}, #{count(stats[:workers], "worker")} × #{count(stats[:threads], "thread")}")
+      puts dim("- mode:      #{server.mode}, #{workers_label(stats)} × #{count(stats[:threads], "thread")}")
       puts dim("- pid:       #{Process.pid}")
       puts dim("- listening: #{server.url}")
       puts dim("- control:   #{server.control_url}") if server.control_url
@@ -140,6 +140,14 @@ module Kino
       "#{number} #{noun}#{"s" unless number == 1}"
     end
 
+    # The pool as configured: "8 workers", or "8-32 workers" when it can
+    # grow.
+    def workers_label(stats)
+      return count(stats[:workers], "worker") if stats[:max_workers] == stats[:workers]
+
+      "#{stats[:workers]}-#{stats[:max_workers]} workers"
+    end
+
     # Roll credits when the process ends: normal exit or crash (at_exit
     # also runs after an uncaught exception; only a force-exit skips it).
     # @return [void]
@@ -234,7 +242,7 @@ module Kino
     end
 
     def write_sample(path)
-      require "kino"
+      require "kino" # audition:disable runtime-require
       Configuration.write_sample(path)
       puts "Kino: wrote sample config to #{path}"
       0
@@ -245,8 +253,8 @@ module Kino
 
     # Resolve the full configuration once: file + CLI flag overrides.
     def resolve_config(options)
-      require "kino"
-      require "rack"
+      require "kino" # audition:disable runtime-require
+      require "rack" # audition:disable runtime-require
 
       config_file = options[:config_file] || Configuration.default_path
 

data/lib/kino/configuration.rb

@@ -10,6 +10,8 @@ module Kino
       bind: "127.0.0.1",
       port: 0,
       workers: nil, # resolved to Kino.available_parallelism in #to_h
+      max_workers: nil, # nil = fixed pool; above workers = elastic pool
+      scale_down_after: nil, # resolved to 30 seconds in Server
       threads: nil, # resolved per mode in Server: 1 in :ractor, 3 in :threaded
       mode: :auto,
       queue_depth: 1024,
@@ -30,6 +32,7 @@ module Kino
       io_threads: nil,
       tokio_threads: nil,
       tls: nil,
+      http2: true,
       environment: nil,
       pidfile: nil,
       control_bind: nil,
@@ -43,7 +46,7 @@ module Kino
     SETTINGS = DEFAULTS.keys.freeze
 
     # Source template for {.sample}.
-    SAMPLE_TEMPLATE = File.expand_path("templates/kino.rb.tt", __dir__)
+    SAMPLE_TEMPLATE = File.expand_path("templates/kino.rb.tt", __dir__).freeze
 
     # Where the `kino` CLI and the Rack handler look for a config file when
     # none is named: the project root first, then the Rails-style config/.
@@ -145,6 +148,8 @@ module Kino
     #   bind "0.0.0.0"
     #   port 9292
     #   workers 8           # ractors (or thread groups in :threaded mode)
+    #   max_workers 32      # elastic pool ceiling; unset = fixed pool
+    #   scale_down_after 30 # seconds idle before an extra worker retires
     #   threads 3           # threads per worker
     #   mode :ractor        # :auto | :ractor | :threaded
     #   queue_depth 2048
@@ -171,9 +176,19 @@ module Kino
       # Port to listen on; 0 picks an ephemeral port.
       def port(port) = @config.set(:port, Integer(port))
 
-      # Worker count (ractors in :ractor mode); defaults to CPU cores.
+      # Worker count (ractors in :ractor mode); defaults to CPU cores. The
+      # pool floor when max_workers is set.
       def workers(count) = @config.set(:workers, Integer(count))
 
+      # Pool ceiling: under sustained queue pressure the pool grows past
+      # `workers`, one worker at a time, up to this many. Unset (the
+      # default) keeps the pool fixed at `workers`.
+      def max_workers(count) = @config.set(:max_workers, Integer(count))
+
+      # Seconds a worker above the floor must sit idle before it is
+      # retired (default 30). Only meaningful with max_workers.
+      def scale_down_after(seconds) = @config.set(:scale_down_after, seconds)
+
       # Threads per worker (I/O concurrency inside one ractor); default is
       # mode-dependent: 1 in :ractor mode, 3 in :threaded.
       def threads(count) = @config.set(:threads, Integer(count))
@@ -245,6 +260,11 @@ module Kino
       # TLS termination; file paths or inline PEM strings.
       def tls(cert:, key:) = @config.set(:tls, {cert: cert, key: key})
 
+      # HTTP/2: negotiated via ALPN on TLS binds, served to
+      # prior-knowledge clients on plaintext. On by default; set false
+      # to serve HTTP/1 only.
+      def http2(enabled = true) = @config.set(:http2, !!enabled)
+
       # Sets RACK_ENV (unless already set) before the CLI loads the app.
       def environment(env) = @config.set(:environment, env.to_s)
 

data/lib/kino/monitor.rb

@@ -0,0 +1,52 @@
+# frozen_string_literal: true
+
+module Kino
+  # @private
+  # A thread on the main ractor that calls `scan` every `tick` seconds
+  # until stopped. Main-ractor so it stays responsive when worker ractors
+  # are wedged. A scan that raises is logged and skipped, never fatal:
+  # monitors keep the server healthy, they must not take it down.
+  class Monitor
+    def initialize(name:, tick:)
+      @name = name
+      @tick = tick
+      @running = false
+      @thread = nil
+    end
+
+    def start
+      @running = true
+      @thread = Thread.new do
+        Thread.current.name = @name
+        run
+      end
+      self
+    end
+
+    def stop
+      @running = false
+      @thread&.join(@tick * 2)
+    end
+
+    private
+
+    def run
+      tick while @running
+    rescue => e
+      Log.error("#{@name} crashed: #{e.class}: #{e.message}")
+    end
+
+    def tick
+      scan
+    rescue => e
+      Log.error("#{@name} tick error: #{e.class}: #{e.message}")
+    ensure
+      sleep @tick
+    end
+
+    # One poll; subclasses define it.
+    def scan
+      raise NotImplementedError, "#{self.class} must define scan"
+    end
+  end
+end

data/lib/kino/pool_scaler.rb

@@ -0,0 +1,103 @@
+# frozen_string_literal: true
+
+module Kino
+  # @private
+  # Grows and shrinks the worker pool between `floor` and `ceiling`. One
+  # thread on the main ractor polls the native queue and per-slot sensors
+  # every tick and drives a pool (RactorSupervisor or ThreadedPool) through
+  # three methods: `active_count`, `groups` (worker index => slot ids for
+  # every worker that may be retired), `grow`, and `retire(index)`.
+  #
+  # Policy: grow by one worker per tick once requests have been waiting in
+  # the queue on two consecutive ticks (a burst that clears within a tick
+  # is not pressure); retire one worker per tick, the one idle longest,
+  # once it has been idle for `scale_down_after`. "Idle" means no slot of
+  # the worker held a request at two consecutive samples and its served
+  # count did not move between them, so a worker serving short requests
+  # between samples is never mistaken for an idle one.
+  class PoolScaler < Monitor
+    TICK = 0.1
+    # Consecutive ticks with a non-empty queue before the pool grows.
+    PRESSURE_TICKS = 2
+
+    def initialize(server_id:, pool:, floor:, ceiling:, scale_down_after:, tick: TICK)
+      super(name: "pool scaler", tick: tick)
+      @server_id = server_id
+      @pool = pool
+      @floor = floor
+      @ceiling = ceiling
+      @scale_down_after = scale_down_after
+      @pressure = 0
+      @last_served = {}
+      @idle_since = {}
+    end
+
+    # One policy step over one set of observations: the monotonic time,
+    # the queue depth, and worker_stats rows ([slot, served, in_flight,
+    # busy_ms, quarantined, retired]). Public so the policy is testable
+    # without a server.
+    def step(now, queued, rows)
+      @pressure = queued.positive? ? @pressure + 1 : 0
+      if @pressure >= PRESSURE_TICKS
+        grow if @pool.active_count < @ceiling
+        return
+      end
+
+      observe_idle(now, rows)
+      return unless @pool.active_count > @floor
+
+      index, since = @idle_since.min_by { |_index, at| at }
+      return unless index && now - since >= @scale_down_after
+
+      retire(index)
+    end
+
+    private
+
+    def scan
+      queued, _in_flight = Native.queue_stats(@server_id)
+      step(Process.clock_gettime(Process::CLOCK_MONOTONIC), queued, Native.worker_stats(@server_id))
+    end
+
+    def grow
+      index = @pool.grow
+      return unless index
+
+      Native.record_scale_up(@server_id)
+      Log.info("pool grew to #{@pool.active_count} workers (queue pressure)")
+    end
+
+    def retire(index)
+      return unless @pool.retire(index)
+
+      forget(index)
+      Native.record_scale_down(@server_id)
+      Log.info("pool shrank to #{@pool.active_count} workers (worker-#{index} idle)")
+    end
+
+    # Per worker: idle when no slot holds a request at this sample and the
+    # served total did not move since the previous one. First sighting of
+    # a worker is never idle (it takes two samples to know).
+    def observe_idle(now, rows)
+      by_slot = rows.to_h { |row| [row[0], row] }
+      groups = @pool.groups
+      (@idle_since.keys - groups.keys).each { |index| forget(index) }
+      groups.each do |index, slot_ids|
+        served = slot_ids.sum { |id| by_slot.dig(id, 1) || 0 }
+        busy = slot_ids.any? { |id| (by_slot.dig(id, 2) || 0).positive? }
+        idle = !busy && @last_served[index] == served
+        @last_served[index] = served
+        if idle
+          @idle_since[index] ||= now
+        else
+          @idle_since.delete(index)
+        end
+      end
+    end
+
+    def forget(index)
+      @idle_since.delete(index)
+      @last_served.delete(index)
+    end
+  end
+end

data/lib/kino/quarantine_monitor.rb

@@ -3,54 +3,22 @@
 module Kino
   # @private
   # Polls per-slot busy_ms and, past the timeout, quarantines a wedged slot
-  # and asks the replacer to spawn a fresh worker. Runs one thread on the
-  # main ractor (uncontended by wedged worker ractors, so it stays
-  # responsive in :ractor mode). Never interrupts the wedged worker.
-  class QuarantineMonitor
+  # and asks the replacer to spawn a fresh worker. Never interrupts the
+  # wedged worker.
+  class QuarantineMonitor < Monitor
     def initialize(server_id:, timeout_ms:, max:, replacer:, tick: 0.5)
+      super(name: "quarantine monitor", tick: tick)
       @server_id = server_id
       @timeout_ms = timeout_ms
       @max = max
       @replacer = replacer
-      @tick = tick
       @outstanding = 0
       @at_cap_logged = false
-      @running = false
-      @thread = nil
-    end
-
-    def start
-      @running = true
-      @thread = Thread.new do
-        Thread.current.name = "quarantine"
-        run
-      end
-      self
-    end
-
-    def stop
-      @running = false
-      @thread&.join(@tick * 2)
     end
 
     private
 
-    def run
-      tick while @running
-    rescue => e
-      Log.error("quarantine monitor crashed: #{e.class}: #{e.message}")
-    end
-
-    def tick
-      scan_slots
-    rescue => e
-      # A bad tick must never kill the monitor.
-      Log.error("quarantine tick error: #{e.class}: #{e.message}")
-    ensure
-      sleep @tick
-    end
-
-    def scan_slots
+    def scan
       Native.worker_stats(@server_id).each do |index, _served, _in_flight, busy_ms, quarantined|
         next if quarantined || busy_ms <= @timeout_ms