ddtrace 0.42.0 → 0.52.0

data/lib/datadog/core/environment/socket.rb

@@ -0,0 +1,17 @@
+# typed: true
+require 'socket'
+
+module Datadog
+  module Core
+    module Environment
+      # For runtime identity
+      module Socket
+        module_function
+
+        def hostname
+          ::Socket.gethostname
+        end
+      end
+    end
+  end
+end

data/lib/datadog/core/environment/thread_count.rb

@@ -0,0 +1,19 @@
+# typed: true
+module Datadog
+  module Core
+    module Environment
+      # Retrieves number of threads from runtime
+      module ThreadCount
+        module_function
+
+        def value
+          Thread.list.count
+        end
+
+        def available?
+          Thread.respond_to?(:list)
+        end
+      end
+    end
+  end
+end

data/lib/datadog/core/environment/variable_helpers.rb

@@ -0,0 +1,42 @@
+# typed: false
+module Datadog
+  module Core
+    # Namespace for handling application environment
+    module Environment
+      # Defines helper methods for environment
+      module VariableHelpers
+        extend self
+
+        def env_to_bool(var, default = nil)
+          var = decode_array(var)
+          var && ENV.key?(var) ? ENV[var].to_s.strip.downcase == 'true' : default
+        end
+
+        def env_to_int(var, default = nil)
+          var = decode_array(var)
+          var && ENV.key?(var) ? ENV[var].to_i : default
+        end
+
+        def env_to_float(var, default = nil)
+          var = decode_array(var)
+          var && ENV.key?(var) ? ENV[var].to_f : default
+        end
+
+        def env_to_list(var, default = [])
+          var = decode_array(var)
+          if var && ENV.key?(var)
+            ENV[var].split(',').map(&:strip)
+          else
+            default
+          end
+        end
+
+        private
+
+        def decode_array(var)
+          var.is_a?(Array) ? var.find { |env_var| ENV.key?(env_var) } : var
+        end
+      end
+    end
+  end
+end

data/lib/ddtrace.rb

@@ -1,5 +1,4 @@
-require 'thread'
-
+# typed: strict
 # During development, we load `ddtrace` by through `ddtrace.gemspec`,
 # which in turn eager loads 'ddtrace/version'.
 #
@@ -15,64 +14,39 @@ require 'ddtrace/quantization/http'
 require 'ddtrace/pipeline'
 require 'ddtrace/configuration'
 require 'ddtrace/patcher'
-require 'ddtrace/augmentation'
 require 'ddtrace/metrics'
+require 'ddtrace/auto_instrument_base'
+require 'ddtrace/profiling'
+
+require 'datadog/contrib'
+require 'ddtrace/contrib/auto_instrument'
+require 'ddtrace/contrib/extensions'
+
+require 'ddtrace/opentelemetry/extensions'
 
 # \Datadog global namespace that includes all tracing functionality for Tracer and Span classes.
 module Datadog
-  extend Augmentation
   extend Configuration
+  extend AutoInstrumentBase
 
-  # Load and extend Contrib by default
-  require 'ddtrace/contrib/extensions'
+  # Load built-in Datadog integrations
   extend Contrib::Extensions
+  # Load Contrib auto instrumentation
+  extend Contrib::AutoInstrument
+  # Load Contrib extension to global Datadog objects
+  Configuration::Settings.include Contrib::Extensions::Configuration::Settings
 
   # Load and extend OpenTelemetry compatibility by default
-  require 'ddtrace/opentelemetry/extensions'
   extend OpenTelemetry::Extensions
 
   # Add shutdown hook:
   # Ensures the tracer has an opportunity to flush traces
   # and cleanup before terminating the process.
-  at_exit { Datadog.shutdown! }
+  at_exit do
+    if Interrupt === $! # rubocop:disable Style/SpecialGlobalVars is process terminating due to a ctrl+c or similar?
+      Datadog.send(:handle_interrupt_shutdown!)
+    else
+      Datadog.shutdown!
+    end
+  end
 end
-
-require 'ddtrace/contrib/action_cable/integration'
-require 'ddtrace/contrib/action_pack/integration'
-require 'ddtrace/contrib/action_view/integration'
-require 'ddtrace/contrib/active_model_serializers/integration'
-require 'ddtrace/contrib/active_record/integration'
-require 'ddtrace/contrib/active_support/integration'
-require 'ddtrace/contrib/aws/integration'
-require 'ddtrace/contrib/concurrent_ruby/integration'
-require 'ddtrace/contrib/dalli/integration'
-require 'ddtrace/contrib/delayed_job/integration'
-require 'ddtrace/contrib/elasticsearch/integration'
-require 'ddtrace/contrib/ethon/integration'
-require 'ddtrace/contrib/excon/integration'
-require 'ddtrace/contrib/faraday/integration'
-require 'ddtrace/contrib/grape/integration'
-require 'ddtrace/contrib/graphql/integration'
-require 'ddtrace/contrib/grpc/integration'
-require 'ddtrace/contrib/http/integration'
-require 'ddtrace/contrib/httprb/integration'
-require 'ddtrace/contrib/integration'
-require 'ddtrace/contrib/kafka/integration'
-require 'ddtrace/contrib/presto/integration'
-require 'ddtrace/contrib/que/integration'
-require 'ddtrace/contrib/mysql2/integration'
-require 'ddtrace/contrib/mongodb/integration'
-require 'ddtrace/contrib/racecar/integration'
-require 'ddtrace/contrib/rack/integration'
-require 'ddtrace/contrib/rails/integration'
-require 'ddtrace/contrib/rake/integration'
-require 'ddtrace/contrib/redis/integration'
-require 'ddtrace/contrib/resque/integration'
-require 'ddtrace/contrib/rest_client/integration'
-require 'ddtrace/contrib/sequel/integration'
-require 'ddtrace/contrib/shoryuken/integration'
-require 'ddtrace/contrib/sidekiq/integration'
-require 'ddtrace/contrib/sinatra/integration'
-require 'ddtrace/contrib/sneakers/integration'
-require 'ddtrace/contrib/sucker_punch/integration'
-require 'ddtrace/monkey'

data/lib/ddtrace/analytics.rb

@@ -1,3 +1,4 @@
+# typed: true
 require 'ddtrace/ext/analytics'
 
 module Datadog
@@ -6,11 +7,13 @@ module Datadog
     class << self
       def set_sample_rate(span, sample_rate)
         return if span.nil? || !sample_rate.is_a?(Numeric)
+
         span.set_metric(Datadog::Ext::Analytics::TAG_SAMPLE_RATE, sample_rate)
       end
 
       def set_measured(span, value = true)
         return if span.nil?
+
         # rubocop:disable Style/MultipleComparison
         value = value == true || value == 1 ? 1 : 0
         span.set_metric(Datadog::Ext::Analytics::TAG_MEASURED, value)

data/lib/ddtrace/auto_instrument.rb

@@ -0,0 +1,5 @@
+# typed: strict
+require 'ddtrace'
+
+Datadog.add_auto_instrument
+Datadog.profiler.start if Datadog.profiler

data/lib/ddtrace/auto_instrument_base.rb

@@ -0,0 +1,7 @@
+# typed: true
+module Datadog
+  # base methods stubbed for adding auto instrument extensions
+  module AutoInstrumentBase
+    def add_auto_instrument; end
+  end
+end

data/lib/ddtrace/buffer.rb

@@ -1,6 +1,5 @@
-require 'thread'
+# typed: true
 require 'ddtrace/diagnostics/health'
-require 'ddtrace/runtime/object_space'
 
 # Trace buffer that accumulates traces for a consumer.
 # Consumption can happen from a different thread.
@@ -18,6 +17,7 @@ module Datadog
     # even if the buffer is full. In that case, a random item is discarded.
     def push(item)
       return if closed?
+
       full? ? replace!(item) : add!(item)
       item
     end
@@ -168,8 +168,8 @@ module Datadog
       synchronize { super }
     end
 
-    def synchronize
-      @mutex.synchronize { yield }
+    def synchronize(&block)
+      @mutex.synchronize(&block)
     end
   end
 
@@ -213,6 +213,8 @@ module Datadog
 
   # Health metrics for trace buffers.
   module MeasuredBuffer
+    include Kernel # Ensure that kernel methods are always available (https://sorbet.org/docs/error-reference#7003)
+
     def initialize(*_)
       super
 
@@ -259,7 +261,7 @@ module Datadog
 
       @buffer_spans += trace.length
     rescue StandardError => e
-      Datadog.logger.debug("Failed to measure queue accept. Cause: #{e.message} Source: #{e.backtrace.first}")
+      Datadog.logger.debug("Failed to measure queue accept. Cause: #{e.message} Source: #{Array(e.backtrace).first}")
     end
 
     def measure_drop(trace)
@@ -267,7 +269,7 @@ module Datadog
 
       @buffer_spans -= trace.length
     rescue StandardError => e
-      Datadog.logger.debug("Failed to measure queue drop. Cause: #{e.message} Source: #{e.backtrace.first}")
+      Datadog.logger.debug("Failed to measure queue drop. Cause: #{e.message} Source: #{Array(e.backtrace).first}")
     end
 
     def measure_pop(traces)
@@ -290,7 +292,7 @@ module Datadog
       @buffer_dropped = 0
       @buffer_spans = 0
     rescue StandardError => e
-      Datadog.logger.debug("Failed to measure queue. Cause: #{e.message} Source: #{e.backtrace.first}")
+      Datadog.logger.debug("Failed to measure queue. Cause: #{e.message} Source: #{Array(e.backtrace).first}")
     end
   end
 
@@ -318,7 +320,7 @@ module Datadog
   #
   # TODO We should restructure this module, so that classes are not declared at top-level ::Datadog.
   # TODO Making such a change is potentially breaking for users manually configuring the tracer.
-  TraceBuffer = if Datadog::Ext::Runtime::RUBY_ENGINE == 'ruby' # rubocop:disable Style/ConstantName
+  TraceBuffer = if Datadog::Core::Environment::Ext::RUBY_ENGINE == 'ruby'
                   CRubyTraceBuffer
                 else
                   ThreadSafeTraceBuffer

data/lib/ddtrace/chunker.rb

@@ -1,3 +1,4 @@
+# typed: false
 require 'json'
 require 'msgpack'
 

data/lib/ddtrace/configuration.rb

@@ -1,14 +1,42 @@
+# typed: true
 require 'forwardable'
-
 require 'ddtrace/configuration/pin_setup'
 require 'ddtrace/configuration/settings'
 require 'ddtrace/configuration/components'
 
 module Datadog
   # Configuration provides a unique access point for configurations
-  module Configuration
+  module Configuration # rubocop:disable Metrics/ModuleLength
+    include Kernel # Ensure that kernel methods are always available (https://sorbet.org/docs/error-reference#7003)
     extend Forwardable
 
+    # Used to ensure that @components initialization/reconfiguration is performed one-at-a-time, by a single thread.
+    #
+    # This is important because components can end up being accessed from multiple application threads (for instance on
+    # a threaded webserver), and we don't want their initialization to clash (for instance, starting two profilers...).
+    #
+    # Note that a Mutex **IS NOT** reentrant: the same thread cannot grab the same Mutex more than once.
+    # This means below we are careful not to nest calls to methods that would trigger initialization and grab the lock.
+    #
+    # Every method that directly or indirectly mutates @components should be holding the lock (through
+    # #safely_synchronize) while doing so.
+    COMPONENTS_WRITE_LOCK = Mutex.new
+    private_constant :COMPONENTS_WRITE_LOCK
+
+    # We use a separate lock when reading the @components, so that they continue to be accessible during reconfiguration.
+    # This was needed because we ran into several issues where we still needed to read the old
+    # components while the COMPONENTS_WRITE_LOCK was being held (see https://github.com/DataDog/dd-trace-rb/pull/1387
+    # and https://github.com/DataDog/dd-trace-rb/pull/1373#issuecomment-799593022 ).
+    #
+    # Technically on MRI we could get away without this lock, but on non-MRI Rubies, we may run into issues because
+    # we fall into the "UnsafeDCLFactory" case of https://shipilev.net/blog/2014/safe-public-construction/ .
+    # Specifically, on JRuby reads from the @components do NOT have volatile semantics, and on TruffleRuby they do
+    # BUT just as an implementation detail, see https://github.com/jruby/jruby/wiki/Concurrency-in-jruby#volatility and
+    # https://github.com/DataDog/dd-trace-rb/pull/1329#issuecomment-776750377 .
+    # Concurrency is hard.
+    COMPONENTS_READ_LOCK = Mutex.new
+    private_constant :COMPONENTS_READ_LOCK
+
     attr_writer :configuration
 
     def configuration
@@ -19,13 +47,15 @@ module Datadog
       if target.is_a?(Settings)
         yield(target) if block_given?
 
-        # Build immutable components from settings
-        @components ||= nil
-        @components = if @components
-                        replace_components!(target, @components)
-                      else
-                        build_components(target)
-                      end
+        safely_synchronize do |write_components|
+          write_components.call(
+            if components?
+              replace_components!(target, @components)
+            else
+              build_components(target)
+            end
+          )
+        end
 
         target
       else
@@ -36,40 +66,91 @@ module Datadog
     def_delegators \
       :components,
       :health_metrics,
+      :profiler,
       :runtime_metrics,
       :tracer
 
     def logger
-      if instance_variable_defined?(:@components) && @components
+      # avoid initializing components if they didn't already exist
+      current_components = components(allow_initialization: false)
+
+      if current_components
         @temp_logger = nil
-        components.logger
+        current_components.logger
       else
-        # Use default logger without initializing components.
-        # This prevents recursive loops while initializing.
-        # e.g. Get logger --> Build components --> Log message --> Repeat...
-        @temp_logger ||= begin
-          logger = configuration.logger.instance || Datadog::Logger.new(STDOUT)
-          logger.level = configuration.diagnostics.debug ? ::Logger::DEBUG : configuration.logger.level
-          logger
-        end
+        logger_without_components
       end
     end
 
+    # Gracefully shuts down all components.
+    #
+    # Components will still respond to method calls as usual,
+    # but might not internally perform their work after shutdown.
+    #
+    # This avoids errors being raised across the host application
+    # during shutdown, while allowing for graceful decommission of resources.
+    #
+    # Components won't be automatically reinitialized after a shutdown.
     def shutdown!
-      if instance_variable_defined?(:@components) && @components
-        components.shutdown!
-        @components = nil
+      safely_synchronize do
+        @components.shutdown! if components?
       end
     end
 
     protected
 
-    def components
-      @components ||= build_components(configuration)
+    def components(allow_initialization: true)
+      current_components = COMPONENTS_READ_LOCK.synchronize { defined?(@components) && @components }
+      return current_components if current_components || !allow_initialization
+
+      safely_synchronize do |write_components|
+        (defined?(@components) && @components) || write_components.call(build_components(configuration))
+      end
     end
 
     private
 
+    # Gracefully shuts down the tracer and disposes of component references,
+    # allowing execution to start anew.
+    #
+    # In contrast with +#shutdown!+, components will be automatically
+    # reinitialized after a reset.
+    #
+    # Used internally to ensure a clean environment between test runs.
+    def reset!
+      safely_synchronize do |write_components|
+        @components.shutdown! if components?
+        write_components.call(nil)
+        configuration.reset!
+      end
+    end
+
+    def safely_synchronize
+      # Writes to @components should only happen through this proc. Because this proc is only accessible to callers of
+      # safely_synchronize, this forces all writers to go through this method.
+      write_components = proc do |new_value|
+        COMPONENTS_READ_LOCK.synchronize { @components = new_value }
+      end
+
+      COMPONENTS_WRITE_LOCK.synchronize do
+        begin
+          yield write_components
+        rescue ThreadError => e
+          logger_without_components.error(
+            'Detected deadlock during ddtrace initialization. ' \
+            'Please report this at https://github.com/DataDog/dd-trace-rb/blob/master/CONTRIBUTING.md#found-a-bug' \
+            "\n\tSource:\n\t#{Array(e.backtrace).join("\n\t")}"
+          )
+          nil
+        end
+      end
+    end
+
+    def components?
+      # This does not need to grab the COMPONENTS_READ_LOCK because it's not returning the components
+      (defined?(@components) && @components) != nil
+    end
+
     def build_components(settings)
       components = Components.new(settings)
       components.startup!(settings)
@@ -83,5 +164,32 @@ module Datadog
       components.startup!(settings)
       components
     end
+
+    def logger_without_components
+      # Use default logger without initializing components.
+      # This enables logging during initialization, otherwise we'd run into deadlocks.
+      @temp_logger ||= begin
+        logger = configuration.logger.instance || Datadog::Logger.new($stdout)
+        logger.level = configuration.diagnostics.debug ? ::Logger::DEBUG : configuration.logger.level
+        logger
+      end
+    end
+
+    # Called from our at_exit hook whenever there was a pending Interrupt exception (e.g. typically due to ctrl+c)
+    # to print a nice message whenever we're taking a bit longer than usual to finish the process.
+    def handle_interrupt_shutdown!
+      logger = Datadog.logger
+      shutdown_thread = Thread.new { shutdown! }
+      print_message_treshold_seconds = 0.2
+
+      slow_shutdown = shutdown_thread.join(print_message_treshold_seconds).nil?
+
+      if slow_shutdown
+        logger.info 'Reporting remaining data... Press ctrl+c to exit immediately.'
+        shutdown_thread.join
+      end
+
+      nil
+    end
   end
 end