datadog 2.7.1 → 2.17.0

data/lib/datadog/core/utils/network.rb

@@ -32,7 +32,7 @@ module Datadog
           def stripped_ip_from_request_headers(headers, ip_headers_to_check: DEFAULT_IP_HEADERS_NAMES)
             ip = ip_header(headers, ip_headers_to_check)
 
-            ip ? ip.to_s : nil
+            ip&.to_s
           end
 
           # @param [String] IP value.
@@ -40,7 +40,7 @@ module Datadog
           # @return [nil] when no valid IP value found.
           def stripped_ip(ip)
             ip = ip_to_ipaddr(ip)
-            ip ? ip.to_s : nil
+            ip&.to_s
           end
 
           private
@@ -52,10 +52,10 @@ module Datadog
             return unless ip
 
             clean_ip = if likely_ipv4?(ip)
-                         strip_ipv4_port(ip)
-                       else
-                         strip_zone_specifier(strip_ipv6_port(ip))
-                       end
+              strip_ipv4_port(ip)
+            else
+              strip_zone_specifier(strip_ipv6_port(ip))
+            end
 
             begin
               IPAddr.new(clean_ip)

data/lib/datadog/core/utils/only_once_successful.rb

@@ -5,14 +5,25 @@ require_relative 'only_once'
 module Datadog
   module Core
     module Utils
-      # Helper class to execute something with only one success.
+      # Helper class to execute something with only one successful execution.
       #
-      # This is useful for cases where we want to ensure that a block of code is only executed once, and only if it
-      # succeeds. One such example is sending app-started telemetry event.
+      # If limit is not provided to the constructor, +run+ will execute the
+      # block an unlimited number of times until the block indicates that it
+      # executed successfully by returning a truthy value. After a block
+      # executes successfully, subsequent +run+ calls will not invoke the
+      # block.
       #
-      # Successful execution is determined by the return value of the block: any truthy value is considered success.
+      # If a non-zero limit is provided to the constructor, +run+ will
+      # execute the block up to that many times, and will mark the instance
+      # of OnlyOneSuccessful as failed if none of the executions succeeded.
       #
-      # Thread-safe when used correctly (e.g. be careful of races when lazily initializing instances of this class).
+      # One consumer of this class is sending the app-started telemetry event.
+      #
+      # Successful execution is determined by the return value of the block:
+      # any truthy value is considered success.
+      #
+      # This class is thread-safe (however, instances of it must also be
+      # created in a thread-safe manner).
       #
       # Note: In its current state, this class is not Ractor-safe.
       # In https://github.com/DataDog/dd-trace-rb/pull/1398#issuecomment-797378810 we have a discussion of alternatives,

data/lib/datadog/core/utils/time.rb

@@ -31,6 +31,16 @@ module Datadog
         #
         # @param block [Proc] block that returns a `Time` object representing the current wall time
         def now_provider=(block)
+          class << self
+            # Avoid method redefinition warning.
+            # `rescue nil` is added in case customers remove the method
+            # themselves to squelch the warning.
+            begin
+              remove_method(:now)
+            rescue
+              nil
+            end
+          end
           define_singleton_method(:now, &block)
         end
 
@@ -43,6 +53,16 @@ module Datadog
         #
         # @param block [Proc] block that accepts unit and returns timestamp in the requested unit
         def get_time_provider=(block)
+          class << self
+            # Avoid method redefinition warning
+            # `rescue nil` is added in case customers remove the method
+            # themselves to squelch the warning.
+            begin
+              remove_method(:get_time)
+            rescue
+              nil
+            end
+          end
           define_singleton_method(:get_time, &block)
         end
 

data/lib/datadog/core/utils/truncation.rb

@@ -0,0 +1,21 @@
+# frozen_string_literal: true
+
+module Datadog
+  module Core
+    module Utils
+      # Helper methods for truncating data
+      module Truncation
+        module_function
+
+        def truncate_in_middle(string, max_prefix_length, max_suffix_length)
+          max_length = max_prefix_length + 3 + max_suffix_length
+          if string.length > max_length
+            "#{string[0...max_prefix_length]}...#{string[-max_suffix_length..-1]}"
+          else
+            string
+          end
+        end
+      end
+    end
+  end
+end

data/lib/datadog/core/vendor/multipart-post/multipart/post/composite_read_io.rb

@@ -108,7 +108,7 @@ module Datadog
             end
 
             def respond_to?(meth, include_all = false)
-              @io.respond_to?(meth, include_all) || super(meth, include_all)
+              @io.respond_to?(meth, include_all) || super
             end
           end
         end

data/lib/datadog/core/vendor/multipart-post/multipart/post/multipartable.rb

@@ -28,29 +28,29 @@ module Datadog
               "--#{SecureRandom.uuid}"
             end
 
-            def initialize(path, params, headers={}, boundary = Multipartable.secure_boundary)
+            def initialize(path, params, headers = {}, boundary = Multipartable.secure_boundary)
               headers = headers.clone # don't want to modify the original variable
               parts_headers = headers.delete(:parts) || {}
               super(path, headers)
-              parts = params.map do |k,v|
+              parts = params.map do |k, v|
                 case v
                 when Array
-                  v.map {|item| Parts::Part.new(boundary, "#{k}[]", item, parts_headers[k]) }
+                  v.map { |item| Parts::Part.new(boundary, "#{k}[]", item, parts_headers[k]) }
                 else
                   Parts::Part.new(boundary, k, v, parts_headers[k])
                 end
               end.flatten
               parts << Parts::EpiloguePart.new(boundary)
-              ios = parts.map {|p| p.to_io }
-              self.set_content_type(headers["Content-Type"] || "multipart/form-data",
-                                    { "boundary" => boundary })
-              self.content_length = parts.inject(0) {|sum,i| sum + i.length }
+              ios = parts.map { |p| p.to_io }
+              set_content_type(headers["Content-Type"] || "multipart/form-data",
+                {"boundary" => boundary})
+              self.content_length = parts.inject(0) { |sum, i| sum + i.length }
               self.body_stream = CompositeReadIO.new(*ios)
 
               @boundary = boundary
             end
 
-            attr :boundary
+            attr_reader :boundary
           end
         end
       end

data/lib/datadog/core/vendor/multipart-post/multipart/post/parts.rb

@@ -58,7 +58,7 @@ module Datadog
                 part = ''
                 part << "--#{boundary}\r\n"
                 part << "Content-ID: #{headers["Content-ID"]}\r\n" if headers["Content-ID"]
-                part << "Content-Disposition: form-data; name=\"#{name.to_s}\"\r\n"
+                part << "Content-Disposition: form-data; name=\"#{name}\"\r\n"
                 part << "Content-Type: #{headers["Content-Type"]}\r\n" if headers["Content-Type"]
                 part << "\r\n"
                 part << "#{value}\r\n"
@@ -76,9 +76,9 @@ module Datadog
               # @param io [IO]
               # @param headers [Hash]
               def initialize(boundary, name, io, headers = {})
-                file_length = io.respond_to?(:length) ?  io.length : File.size(io.local_path)
+                file_length = io.respond_to?(:length) ? io.length : File.size(io.local_path)
                 @head = build_head(boundary, name, io.original_filename, io.content_type, file_length,
-                                  io.respond_to?(:opts) ? io.opts.merge(headers) : headers)
+                  io.respond_to?(:opts) ? io.opts.merge(headers) : headers)
                 @foot = "\r\n"
                 @length = @head.bytesize + file_length + @foot.length
                 @io = CompositeReadIO.new(StringIO.new(@head), io, StringIO.new(@foot))
@@ -98,16 +98,16 @@ module Datadog
 
                 part = ''
                 part << "--#{boundary}\r\n"
-                part << "Content-Disposition: #{content_disposition}; name=\"#{name.to_s}\"; filename=\"#{filename}\"\r\n"
+                part << "Content-Disposition: #{content_disposition}; name=\"#{name}\"; filename=\"#{filename}\"\r\n"
                 part << "Content-Length: #{content_len}\r\n"
                 if content_id = opts.delete("Content-ID")
                   part << "Content-ID: #{content_id}\r\n"
                 end
 
-                if opts["Content-Type"] != nil
-                  part <<  "Content-Type: " + opts["Content-Type"] + "\r\n"
+                part << if !opts["Content-Type"].nil?
+                  "Content-Type: " + opts["Content-Type"] + "\r\n"
                 else
-                  part << "Content-Type: #{type}\r\n"
+                  "Content-Type: #{type}\r\n"
                 end
 
                 part << "Content-Transfer-Encoding: #{trans_encoding}\r\n"

data/lib/datadog/core/worker.rb

@@ -12,7 +12,7 @@ module Datadog
       end
 
       def perform(*args)
-        task.call(*args) unless task.nil?
+        task&.call(*args)
       end
 
       protected

data/lib/datadog/core/workers/async.rb

@@ -47,6 +47,14 @@ module Datadog
             @run_async = false
             Datadog.logger.debug { "Forcibly terminating worker thread for: #{self}" }
             worker.terminate
+            # Wait for the worker thread to end
+            begin
+              Timeout.timeout(SHUTDOWN_TIMEOUT) do
+                worker.join
+              end
+            rescue Timeout::Error
+              Datadog.logger.debug { "Worker thread did not end after #{SHUTDOWN_TIMEOUT} seconds: #{self}" }
+            end
             true
           end
 
@@ -112,23 +120,33 @@ module Datadog
             @worker ||= nil
           end
 
+          # Returns true if worker thread is successfully started,
+          # false if it is not started. Reasons for not starting the worker
+          # thread: it is already running, or the process forked and fork
+          # policy is to stop the workers on fork (which means they are
+          # not started in children, really).
           def start_async(&block)
             mutex.synchronize do
-              return if running?
+              return false if running?
 
               if forked?
                 case fork_policy
                 when FORK_POLICY_STOP
                   stop_fork
+                  false
                 when FORK_POLICY_RESTART
+                  # restart_after_fork should return true
                   restart_after_fork(&block)
                 end
               elsif !run_async?
+                # start_worker should return true
                 start_worker(&block)
               end
             end
           end
 
+          # Returns true if worker thread is successfully started,
+          # which should generally be always.
           def start_worker
             @run_async = true
             @pid = Process.pid
@@ -136,22 +154,21 @@ module Datadog
             Datadog.logger.debug { "Starting thread for: #{self}" }
 
             @worker = ::Thread.new do
-              begin
-                yield
-              # rubocop:disable Lint/RescueException
-              rescue Exception => e
-                @error = e
-                Datadog.logger.debug(
-                  "Worker thread error. Cause: #{e.class.name} #{e.message} Location: #{Array(e.backtrace).first}"
-                )
-                raise
-              end
+              yield
+            # rubocop:disable Lint/RescueException
+            rescue Exception => e
+              @error = e
+              Datadog.logger.debug(
+                "Worker thread error. Cause: #{e.class.name} #{e.message} Location: #{Array(e.backtrace).first}"
+              )
+              raise
+
               # rubocop:enable Lint/RescueException
             end
             @worker.name = self.class.name
             @worker.thread_variable_set(:fork_safe, true)
 
-            nil
+            true
           end
 
           def stop_fork

data/lib/datadog/core/workers/interval_loop.rb

@@ -21,7 +21,18 @@ module Datadog
         # Methods that must be prepended
         module PrependedMethods
           def perform(*args)
-            perform_loop { super(*args) }
+            perform_loop do
+              @in_iteration = true
+              begin
+                super(*args)
+              ensure
+                @in_iteration = false
+              end
+            end
+          end
+
+          def in_iteration?
+            defined?(@in_iteration) && @in_iteration
           end
         end
 

data/lib/datadog/core/workers/runtime_metrics.rb

@@ -20,8 +20,8 @@ module Datadog
         attr_reader \
           :metrics
 
-        def initialize(options = {})
-          @metrics = options.fetch(:metrics) { Core::Runtime::Metrics.new }
+        def initialize(telemetry:, **options)
+          @metrics = options.fetch(:metrics) { Core::Runtime::Metrics.new(logger: options[:logger], telemetry: telemetry) }
 
           # Workers::Async::Thread settings
           self.fork_policy = options.fetch(:fork_policy, Workers::Async::Thread::FORK_POLICY_STOP)

data/lib/datadog/core.rb

@@ -11,6 +11,14 @@ module Datadog
   # for higher-level features.
   module Core
     extend Core::Deprecations
+
+    LIBDATADOG_API_FAILURE =
+      begin
+        require "libdatadog_api.#{RUBY_VERSION[/\d+.\d+/]}_#{RUBY_PLATFORM}"
+        nil
+      rescue LoadError => e
+        e.message
+      end
   end
 
   extend Core::Extensions

data/lib/datadog/di/base.rb

@@ -0,0 +1,115 @@
+# frozen_string_literal: true
+
+# This file is loaded by datadog/di/preload.rb.
+# It contains just the global DI reference to the (normally one and only)
+# code tracker for the current process.
+# This file should not require the rest of DI, specifically none of the
+# contrib code that is meant to be loaded after third-party libraries
+# are loaded, and also none of the rest of datadog library which also
+# has contrib code in other products.
+
+require_relative 'code_tracker'
+
+module Datadog
+  # Namespace for Datadog dynamic instrumentation.
+  #
+  # @api private
+  module DI
+    LOCK = Mutex.new
+
+    class << self
+      attr_reader :code_tracker
+
+      # Activates code tracking. Normally this method should be called
+      # when the application starts. If instrumenting third-party code,
+      # code tracking needs to be enabled before the third-party libraries
+      # are loaded. Any third-party code loaded before code tracking is
+      # activated will NOT be instrumentable using dynamic instrumentation.
+      #
+      # TODO test that activating tracker multiple times preserves
+      # existing mappings in the registry
+      def activate_tracking!
+        (@code_tracker ||= CodeTracker.new).start
+      end
+
+      # Activates code tracking if possible.
+      #
+      # This method does nothing if invoked in an environment that does not
+      # implement required trace points for code tracking (MRI Ruby < 2.6,
+      # JRuby) and rescues any exceptions that may be raised by downstream
+      # DI code.
+      def activate_tracking
+        # :script_compiled trace point was added in Ruby 2.6.
+        return unless RUBY_VERSION >= '2.6'
+
+        begin
+          # Activate code tracking by default because line trace points will not work
+          # without it.
+          Datadog::DI.activate_tracking!
+        rescue => exc
+          if defined?(Datadog.logger)
+            Datadog.logger.warn { "di: Failed to activate code tracking for DI: #{exc.class}: #{exc}" }
+          else
+            # We do not have Datadog logger potentially because DI code tracker is
+            # being loaded early in application boot process and the rest of datadog
+            # wasn't loaded yet. Output to standard error.
+            warn("datadog: di: Failed to activate code tracking for DI: #{exc.class}: #{exc}")
+          end
+        end
+      end
+
+      # Deactivates code tracking. In normal usage of DI this method should
+      # never be called, however it is used by DI's test suite to reset
+      # state for individual tests.
+      #
+      # Note that deactivating tracking clears out the registry, losing
+      # the ability to look up files that have been loaded into the process
+      # already.
+      def deactivate_tracking!
+        code_tracker&.stop
+      end
+
+      # Returns whether code tracking is available.
+      # This method should be used instead of querying #code_tracker
+      # because the latter one may be nil.
+      def code_tracking_active?
+        code_tracker&.active? || false
+      end
+
+      # DI code tracker is instantiated globally before the regular set of
+      # components is created, but the code tracker needs to call out to the
+      # "current" DI component to perform instrumentation when application
+      # code is loaded. Because this call may happen prior to Datadog
+      # components having been initialized, we maintain the "current component"
+      # which contains a reference to the most recently instantiated
+      # DI::Component. This way, if a DI component hasn't been instantiated,
+      # we do not try to reference Datadog.components.
+      # In other words, this method exists so that we never attempt to call
+      # Datadog.components from the code tracker.
+      def current_component
+        LOCK.synchronize do
+          @current_components&.last
+        end
+      end
+
+      # To avoid potential races with DI::Component being added and removed,
+      # we maintain a list of the components. Normally the list should contain
+      # either zero or one component depending on whether DI is enabled in
+      # Datadog configuration. However, if a new instance of DI::Component
+      # is created while the previous instance is still running, we are
+      # guaranteed to not end up with no component when one is running.
+      def add_current_component(component)
+        LOCK.synchronize do
+          @current_components ||= []
+          @current_components << component
+        end
+      end
+
+      def remove_current_component(component)
+        LOCK.synchronize do
+          @current_components&.delete(component)
+        end
+      end
+    end
+  end
+end

data/lib/datadog/di/boot.rb

@@ -0,0 +1,34 @@
+# frozen_string_literal: true
+
+require_relative 'logger'
+require_relative 'base'
+require_relative 'error'
+require_relative 'code_tracker'
+require_relative 'component'
+require_relative 'instrumenter'
+require_relative 'probe'
+require_relative 'probe_builder'
+require_relative 'probe_manager'
+require_relative 'probe_notification_builder'
+require_relative 'probe_notifier_worker'
+require_relative 'redactor'
+require_relative 'serializer'
+require_relative 'transport/http'
+require_relative 'utils'
+
+if %w[1 true yes].include?(ENV['DD_DYNAMIC_INSTRUMENTATION_ENABLED']) # steep:ignore
+  # For initial release of Dynamic Instrumentation, activate code tracking
+  # only if DI is explicitly requested in the environment.
+  # Code tracking is required for line probes to work; see the comments
+  # above for the implementation of the method.
+  #
+  # If DI is enabled programmatically, the application can (and must,
+  # for line probes to work) activate tracking in an initializer.
+  # We seem to have Datadog.logger here already
+  Datadog.logger.debug("di: activating code tracking")
+  Datadog::DI.activate_tracking
+end
+
+require_relative 'contrib'
+
+Datadog::DI::Contrib.load_now_or_later

data/lib/datadog/di/code_tracker.rb

@@ -2,6 +2,8 @@
 
 # rubocop:disable Lint/AssignmentInCondition
 
+require_relative 'error'
+
 module Datadog
   module DI
     # Tracks loaded Ruby code by source file and maintains a map from
@@ -78,19 +80,21 @@ module Datadog
               registry_lock.synchronize do
                 registry[path] = tp.instruction_sequence
               end
-            end
-
-            DI.component&.probe_manager&.install_pending_line_probes(path)
 
+              # Also, pending line probes should only be installed for
+              # non-eval'd code.
+              DI.current_component&.probe_manager&.install_pending_line_probes(path)
+            end
           # Since this method normally is called from customer applications,
           # rescue any exceptions that might not be handled to not break said
           # customer applications.
           rescue => exc
-            # TODO we do not have DI.component defined yet, remove steep:ignore
-            # before release.
-            if component = DI.component # steep:ignore
+            # Code tracker may be loaded without the rest of DI,
+            # in which case DI.component will not yet be defined,
+            # but we will have DI.current_component (set to nil).
+            if component = DI.current_component
               raise if component.settings.dynamic_instrumentation.internal.propagate_all_exceptions
-              component.logger.warn("Unhandled exception in script_compiled trace point: #{exc.class}: #{exc}")
+              component.logger.debug { "di: unhandled exception in script_compiled trace point: #{exc.class}: #{exc}" }
               component.telemetry&.report(exc, description: "Unhandled exception in script_compiled trace point")
               # TODO test this path
             else
@@ -136,16 +140,23 @@ module Datadog
           exact = registry[suffix]
           return [suffix, exact] if exact
 
-          inexact = []
-          registry.each do |path, iseq|
-            if Utils.path_matches_suffix?(path, suffix)
-              inexact << [path, iseq]
+          suffix = suffix.dup
+          loop do
+            inexact = []
+            registry.each do |path, iseq|
+              if Utils.path_matches_suffix?(path, suffix)
+                inexact << [path, iseq]
+              end
             end
+            if inexact.length > 1
+              raise Error::MultiplePathsMatch, "Multiple paths matched requested suffix"
+            end
+            if inexact.any?
+              return inexact.first
+            end
+            return nil unless suffix.include?('/')
+            suffix.sub!(%r{.*/+}, '')
           end
-          if inexact.length > 1
-            raise Error::MultiplePathsMatch, "Multiple paths matched requested suffix"
-          end
-          inexact.first
         end
       end