ddtrace 0.42.0 → 0.54.2

data/lib/datadog/contrib.rb

@@ -0,0 +1,71 @@
+# typed: true
+require 'ddtrace/contrib/registry'
+
+module Datadog
+  module Contrib
+    # Registry is a global, declarative repository of all available integrations.
+    #
+    # Integrations should register themselves with the registry as early as
+    # possible as the initial tracer configuration can only activate integrations
+    # if they have already been registered.
+    #
+    # Despite that, integrations *can* be appended to the registry at any point
+    # of the program execution. Newly appended integrations can then be
+    # activated during tracer reconfiguration.
+    #
+    # The registry does not depend on runtime configuration and registered integrations
+    # must execute correctly after successive configuration changes.
+    # The registered integrations themselves can depend on the stateful configuration
+    # of the tracer.
+    #
+    # `Datadog.registry` is a helper accessor to this constant, but it's only available
+    # after the tracer has complete initialization. Use `Datadog::Contrib::REGISTRY` instead
+    # of `Datadog.registry` when you code might be called during tracer initialization.
+    REGISTRY = Registry.new
+  end
+end
+
+require 'ddtrace/contrib/action_cable/integration'
+require 'ddtrace/contrib/action_mailer/integration'
+require 'ddtrace/contrib/action_pack/integration'
+require 'ddtrace/contrib/action_view/integration'
+require 'ddtrace/contrib/active_model_serializers/integration'
+require 'ddtrace/contrib/active_job/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/httpclient/integration'
+require 'ddtrace/contrib/httprb/integration'
+require 'ddtrace/contrib/integration'
+require 'ddtrace/contrib/kafka/integration'
+require 'ddtrace/contrib/lograge/integration'
+require 'ddtrace/contrib/mongodb/integration'
+require 'ddtrace/contrib/mysql2/integration'
+require 'ddtrace/contrib/presto/integration'
+require 'ddtrace/contrib/qless/integration'
+require 'ddtrace/contrib/que/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/semantic_logger/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'

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

@@ -0,0 +1,52 @@
+# typed: true
+require 'datadog/core/environment/ext'
+
+module Datadog
+  module Core
+    module Environment
+      # Reads information from Linux cgroups.
+      # This information is used to extract information
+      # about the current Linux container identity.
+      # @see https://man7.org/linux/man-pages/man7/cgroups.7.html
+      module Cgroup
+        include Kernel # Ensure that kernel methods are always available (https://sorbet.org/docs/error-reference#7003)
+
+        LINE_REGEX = /^(\d+):([^:]*):(.+)$/.freeze
+
+        Descriptor = Struct.new(
+          :id,
+          :groups,
+          :path,
+          :controllers
+        )
+
+        module_function
+
+        def descriptors(process = 'self')
+          [].tap do |descriptors|
+            begin
+              filepath = "/proc/#{process}/cgroup"
+
+              if File.exist?(filepath)
+                File.foreach("/proc/#{process}/cgroup") do |line|
+                  line = line.strip
+                  descriptors << parse(line) unless line.empty?
+                end
+              end
+            rescue StandardError => e
+              Datadog.logger.error("Error while parsing cgroup. Cause: #{e.message} Location: #{Array(e.backtrace).first}")
+            end
+          end
+        end
+
+        def parse(line)
+          id, groups, path = line.scan(LINE_REGEX).first
+
+          Descriptor.new(id, groups, path).tap do |descriptor|
+            descriptor.controllers = groups.split(',') unless groups.nil?
+          end
+        end
+      end
+    end
+  end
+end

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

@@ -0,0 +1,20 @@
+# typed: true
+module Datadog
+  module Core
+    module Environment
+      # Retrieves number of classes from runtime
+      module ClassCount
+        module_function
+
+        def value
+          ::ObjectSpace.count_objects[:T_CLASS]
+        end
+
+        def available?
+          ::ObjectSpace.respond_to?(:count_objects) \
+           && ::ObjectSpace.count_objects.key?(:T_CLASS)
+        end
+      end
+    end
+  end
+end

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

@@ -0,0 +1,91 @@
+# typed: true
+require 'datadog/core/environment/cgroup'
+
+module Datadog
+  module Core
+    module Environment
+      # For container environments
+      module Container
+        include Kernel # Ensure that kernel methods are always available (https://sorbet.org/docs/error-reference#7003)
+
+        UUID_PATTERN = '[0-9a-f]{8}[-_]?[0-9a-f]{4}[-_]?[0-9a-f]{4}[-_]?[0-9a-f]{4}[-_]?[0-9a-f]{12}'.freeze
+        CONTAINER_PATTERN = '[0-9a-f]{64}'.freeze
+
+        PLATFORM_REGEX = /(?<platform>.*?)(?:.slice)?$/.freeze
+        POD_REGEX = /(?<pod>(pod)?#{UUID_PATTERN})(?:.slice)?$/.freeze
+        CONTAINER_REGEX = /(?<container>#{UUID_PATTERN}|#{CONTAINER_PATTERN})(?:.scope)?$/.freeze
+        FARGATE_14_CONTAINER_REGEX = /(?<container>[0-9a-f]{32}-[0-9]{1,10})/.freeze
+
+        Descriptor = Struct.new(
+          :platform,
+          :container_id,
+          :task_uid
+        )
+
+        module_function
+
+        def platform
+          descriptor.platform
+        end
+
+        def container_id
+          descriptor.container_id
+        end
+
+        def task_uid
+          descriptor.task_uid
+        end
+
+        def descriptor
+          @descriptor ||= Descriptor.new.tap do |descriptor|
+            begin
+              Cgroup.descriptors.each do |cgroup_descriptor|
+                # Parse container data from cgroup descriptor
+                path = cgroup_descriptor.path
+                next if path.nil?
+
+                # Split path into parts
+                parts = path.split('/')
+                parts.shift # Remove leading empty part
+
+                # Read info from path
+                next if parts.empty?
+
+                platform = parts[0][PLATFORM_REGEX, :platform]
+                container_id, task_uid = nil
+
+                case parts.length
+                when 0..1
+                  next
+                when 2
+                  container_id = parts[-1][CONTAINER_REGEX, :container] \
+                                || parts[-1][FARGATE_14_CONTAINER_REGEX, :container]
+                else
+                  if (container_id = parts[-1][CONTAINER_REGEX, :container])
+                    task_uid = parts[-2][POD_REGEX, :pod] || parts[1][POD_REGEX, :pod]
+                  else
+                    container_id = parts[-1][FARGATE_14_CONTAINER_REGEX, :container]
+                  end
+                end
+
+                # If container ID wasn't found, ignore.
+                # Path might describe a non-container environment.
+                next if container_id.nil?
+
+                descriptor.platform = platform
+                descriptor.container_id = container_id
+                descriptor.task_uid = task_uid
+
+                break
+              end
+            rescue StandardError => e
+              Datadog.logger.error(
+                "Error while parsing container info. Cause: #{e.message} Location: #{Array(e.backtrace).first}"
+              )
+            end
+          end
+        end
+      end
+    end
+  end
+end

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

@@ -0,0 +1,27 @@
+# typed: true
+require 'ddtrace/version'
+
+module Datadog
+  module Core
+    module Environment
+      module Ext
+        # Identity
+        LANG = 'ruby'.freeze
+        LANG_ENGINE = RUBY_ENGINE
+        LANG_INTERPRETER = "#{RUBY_ENGINE}-#{RUBY_PLATFORM}".freeze
+        LANG_PLATFORM = RUBY_PLATFORM
+        LANG_VERSION = RUBY_VERSION
+        RUBY_ENGINE = ::RUBY_ENGINE # e.g. 'ruby', 'jruby', 'truffleruby'
+        TRACER_VERSION = Datadog::VERSION::STRING
+
+        # e.g for CRuby '3.0.1', for JRuby '9.2.19.0', for TruffleRuby '21.1.0'
+        ENGINE_VERSION = if defined?(RUBY_ENGINE_VERSION)
+                           RUBY_ENGINE_VERSION
+                         else
+                           # CRuby < 2.3 doesn't support RUBY_ENGINE_VERSION
+                           RUBY_VERSION
+                         end
+      end
+    end
+  end
+end

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

@@ -0,0 +1,19 @@
+# typed: true
+module Datadog
+  module Core
+    module Environment
+      # Retrieves garbage collection statistics
+      module GC
+        module_function
+
+        def stat
+          ::GC.stat
+        end
+
+        def available?
+          defined?(::GC) && ::GC.respond_to?(:stat)
+        end
+      end
+    end
+  end
+end

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

@@ -0,0 +1,51 @@
+# typed: false
+require 'securerandom'
+require 'datadog/core/environment/ext'
+require 'ddtrace/utils/forking'
+
+module Datadog
+  module Core
+    module Environment
+      # For runtime identity
+      module Identity
+        extend Datadog::Utils::Forking
+
+        module_function
+
+        # Retrieves number of classes from runtime
+        def id
+          @id ||= SecureRandom.uuid
+
+          # Check if runtime has changed, e.g. forked.
+          after_fork! { @id = SecureRandom.uuid }
+
+          @id
+        end
+
+        def lang
+          Core::Environment::Ext::LANG
+        end
+
+        def lang_engine
+          Core::Environment::Ext::LANG_ENGINE
+        end
+
+        def lang_interpreter
+          Core::Environment::Ext::LANG_INTERPRETER
+        end
+
+        def lang_platform
+          Core::Environment::Ext::LANG_PLATFORM
+        end
+
+        def lang_version
+          Core::Environment::Ext::LANG_VERSION
+        end
+
+        def tracer_version
+          Core::Environment::Ext::TRACER_VERSION
+        end
+      end
+    end
+  end
+end

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/datadog/core/environment/vm_cache.rb

@@ -0,0 +1,46 @@
+# typed: true
+module Datadog
+  module Core
+    module Environment
+      # Reports Ruby VM cache performance statistics.
+      # This currently encompasses cache invalidation counters and is CRuby-specific.
+      #
+      # JRuby emulates some CRuby global cache statistics, but they are synthetic and don't
+      # provide actionable performance information in the same way CRuby does.
+      # @see https://github.com/jruby/jruby/issues/4384#issuecomment-267069314
+      #
+      # TruffleRuby does not have a global runtime cache invalidation cache.
+      # @see http://archive.today/2021.09.10-205702/https://medium.com/graalvm/precise-method-and-constant-invalidation-in-truffleruby-4dd56c6bac1a
+      module VMCache
+        module_function
+
+        # Global constant cache "generation" counter.
+        #
+        # Whenever a constant creation busts the global constant cache
+        # this value is incremented. This has a measurable performance impact
+        # and thus show be avoided after application warm up.
+        def global_constant_state
+          ::RubyVM.stat[:global_constant_state]
+        end
+
+        # Global method cache "generation" counter.
+        #
+        # Whenever a method creation busts the global method cache
+        # this value is incremented. This has a measurable performance impact
+        # and thus show be avoided after application warm up.
+        #
+        # Since Ruby 3.0, the method class is kept on a per-class basis,
+        # largely mitigating global method cache busting. `global_method_state`
+        # is thus not available since Ruby 3.0.
+        # @see https://bugs.ruby-lang.org/issues/16614
+        def global_method_state
+          ::RubyVM.stat[:global_method_state]
+        end
+
+        def available?
+          defined?(::RubyVM) && ::RubyVM.respond_to?(:stat)
+        end
+      end
+    end
+  end
+end

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.
@@ -15,9 +14,14 @@ module Datadog
     end
 
     # Add a new ``item`` in the local queue. This method doesn't block the execution
-    # even if the buffer is full. In that case, a random item is discarded.
+    # even if the buffer is full.
+    #
+    # When the buffer is full, we try to ensure that we are fairly sampling newly
+    # pushed traces by randomly inserting them into the buffer slots. This discards
+    # old traces randomly while trying to ensure that recent traces are still captured.
     def push(item)
       return if closed?
+
       full? ? replace!(item) : add!(item)
       item
     end
@@ -64,7 +68,7 @@ module Datadog
 
     protected
 
-    # Segment items into two distinct segments: underflow and overflow.
+    # Segment items into two segments: underflow and overflow.
     # Underflow are items that will fit into buffer.
     # Overflow are items that will exceed capacity, after underflow is added.
     # Returns each array, and nil if there is no underflow/overflow.
@@ -168,17 +172,14 @@ module Datadog
       synchronize { super }
     end
 
-    def synchronize
-      @mutex.synchronize { yield }
+    def synchronize(&block)
+      @mutex.synchronize(&block)
     end
   end
 
   # Buffer that stores objects, has a maximum size, and
   # can be safely used concurrently with CRuby.
   #
-  # Under extreme concurrency scenarios, this class can exceed
-  # its +max_size+ by up to 4%.
-  #
   # Because singular +Array+ operations are thread-safe in CRuby,
   # we can implement the trace buffer without an explicit lock,
   # while making the compromise of allowing the buffer to go
@@ -187,7 +188,6 @@ module Datadog
   # On the following scenario:
   # * 4.5 million spans/second.
   # * Pushed into a single CRubyTraceBuffer from 1000 threads.
-  # The buffer can exceed its maximum size by no more than 4%.
   #
   # This implementation allocates less memory and is faster
   # than {Datadog::ThreadSafeBuffer}.
@@ -195,24 +195,38 @@ module Datadog
   # @see spec/ddtrace/benchmark/buffer_benchmark_spec.rb Buffer benchmarks
   # @see https://github.com/ruby-concurrency/concurrent-ruby/blob/c1114a0c6891d9634f019f1f9fe58dcae8658964/lib/concurrent-ruby/concurrent/array.rb#L23-L27
   class CRubyBuffer < Buffer
+    # A very large number to allow us to effectively
+    # drop all items when invoking `slice!(i, FIXNUM_MAX)`.
+    FIXNUM_MAX = (1 << 62) - 1
+
     # Add a new ``trace`` in the local queue. This method doesn't block the execution
     # even if the buffer is full. In that case, a random trace is discarded.
     def replace!(item)
-      # we should replace a random trace with the new one
-      replace_index = rand(@items.size)
-      replaced_trace = @items.delete_at(replace_index)
-      @items << item
-
-      # We might have deleted an element right when the buffer
-      # was drained, thus +replaced_trace+ will be +nil+.
-      # In that case, nothing was replaced, and this method
-      # performed a simple insertion into the buffer.
-      replaced_trace
+      # Ensure buffer stays within +max_size+ items.
+      # This can happen when there's concurrent modification
+      # between a call the check in `full?` and the `add!` call in
+      # `full? ? replace!(item) : add!(item)`.
+      #
+      # We can still have `@items.size > @max_size` for a short period of
+      # time, but we will always try to correct it here.
+      #
+      # `slice!` is performed before `delete_at` & `<<` to avoid always
+      # removing the item that was just inserted.
+      #
+      # DEV: `slice!` with two integer arguments is ~10% faster than
+      # `slice!` with a {Range} argument.
+      @items.slice!(@max_size, FIXNUM_MAX)
+
+      # We should replace a random trace with the new one
+      replace_index = rand(@max_size)
+      @items[replace_index] = item
     end
   end
 
   # 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 +273,7 @@ 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 +281,7 @@ 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 +304,7 @@ 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 +332,7 @@ 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'