cw-datadog 2.23.0.2

data/lib/datadog/core/buffer/cruby.rb

@@ -0,0 +1,55 @@
+# frozen_string_literal: true
+
+require_relative 'random'
+
+module Datadog
+  module Core
+    module Buffer
+      # Buffer that stores objects, has a maximum size, and
+      # can be safely used concurrently with CRuby.
+      #
+      # Because singular +Array+ operations are thread-safe in CRuby,
+      # we can implement the buffer without an explicit lock,
+      # while making the compromise of allowing the buffer to go
+      # over its maximum limit under extreme circumstances.
+      #
+      # On the following scenario:
+      # * 4.5 million spans/second.
+      # * Pushed into a single CRubyTraceBuffer from 1000 threads.
+      #
+      # This implementation allocates less memory and is faster
+      # than {Datadog::Core::Buffer::ThreadSafe}.
+      #
+      # @see spec/datadog/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 CRuby < Random
+        # 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 ``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.
+        def replace!(item)
+          # 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 item with the new one
+          replace_index = rand(@max_size)
+          @items[replace_index] = item
+        end
+      end
+    end
+  end
+end

data/lib/datadog/core/buffer/random.rb

@@ -0,0 +1,150 @@
+# frozen_string_literal: true
+
+module Datadog
+  module Core
+    module Buffer
+      # Buffer that accumulates items for a consumer.
+      # Consumption can happen from a different thread.
+
+      # Buffer that stores objects. The buffer has a maximum size and when
+      # the buffer is full, a random object is discarded.
+      class Random
+        def initialize(max_size)
+          @max_size = max_size
+          @items = []
+          @closed = false
+        end
+
+        # Add a new ``item`` in the local queue. This method doesn't block the execution
+        # even if the buffer is full.
+        #
+        # When the buffer is full, we try to ensure that we are fairly choosing newly
+        # pushed items by randomly inserting them into the buffer slots. This discards
+        # old items randomly while trying to ensure that recent items are still captured.
+        def push(item)
+          return if closed?
+
+          full? ? replace!(item) : add!(item)
+          item
+        end
+
+        # A bulk push alternative to +#push+. Use this method if
+        # pushing more than one item for efficiency.
+        def concat(items)
+          return if closed?
+
+          # Segment items into underflow and overflow
+          underflow, overflow = overflow_segments(items)
+
+          # Concatenate items do not exceed capacity.
+          add_all!(underflow) unless underflow.nil?
+
+          # Iteratively replace items, to ensure pseudo-random replacement.
+          overflow&.each { |item| replace!(item) }
+        end
+
+        def unshift(*items)
+          # TODO The existing concat implementation does not always append
+          # to the end of the buffer - if the buffer is full, a random
+          # item is deleted and the new item is added in the position of
+          # removed item.
+          # Therefore, if we want to preserve the item order, concat
+          # would also need to be changed to maintain order.
+          # With the existing implementation, the idea is to not move
+          # existing items around, which is what sets unshift apart from
+          # concat to begin with.
+          #
+          # Since this method currently delegates to +concat+, it does not
+          # have a matching definition in the thread-safe worker.
+          concat(items)
+        end
+
+        # Stored items are returned and the local buffer is reset.
+        def pop
+          drain!
+        end
+
+        # Return the current number of stored items.
+        def length
+          @items.length
+        end
+
+        # Return if the buffer is empty.
+        def empty?
+          @items.empty?
+        end
+
+        # Closes this buffer, preventing further pushing.
+        # Draining is still allowed.
+        def close
+          @closed = true
+        end
+
+        def closed?
+          @closed
+        end
+
+        protected
+
+        # 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.
+        def overflow_segments(items)
+          underflow = nil
+          overflow = nil
+
+          overflow_size = (@max_size > 0) ? (@items.length + items.length) - @max_size : 0
+
+          if overflow_size > 0
+            # Items will overflow
+            if overflow_size < items.length
+              # Partial overflow
+              underflow_end_index = items.length - overflow_size - 1
+              underflow = items[0..underflow_end_index]
+              overflow = items[(underflow_end_index + 1)..-1]
+            else
+              # Total overflow
+              overflow = items
+            end
+          else
+            # Items do not exceed capacity.
+            underflow = items
+          end
+
+          [underflow, overflow]
+        end
+
+        def full?
+          @max_size > 0 && @items.length >= @max_size
+        end
+
+        def add_all!(items)
+          @items.concat(items)
+        end
+
+        def add!(item)
+          @items << item
+        end
+
+        def replace!(item)
+          # Choose random item to be replaced
+          replace_index = rand(@items.length)
+
+          # Replace random item
+          discarded_item = @items[replace_index]
+          @items[replace_index] = item
+
+          # Return discarded item
+          discarded_item
+        end
+
+        def drain!
+          items = @items
+          @items = []
+          items
+        end
+      end
+    end
+  end
+end

data/lib/datadog/core/buffer/thread_safe.rb

@@ -0,0 +1,58 @@
+# frozen_string_literal: true
+
+require_relative 'random'
+
+module Datadog
+  module Core
+    module Buffer
+      # Buffer that stores objects, has a maximum size, and
+      # can be safely used concurrently on any environment.
+      #
+      # This implementation uses a {Mutex} around public methods, incurring
+      # overhead in order to ensure thread-safety.
+      #
+      # This is implementation is recommended for non-CRuby environments.
+      # If using CRuby, {Datadog::Core::Buffer::CRuby} is a faster implementation with minimal compromise.
+      class ThreadSafe < Random
+        def initialize(max_size)
+          super
+
+          @mutex = Mutex.new
+        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.
+        def push(item)
+          synchronize { super }
+        end
+
+        def concat(items)
+          synchronize { super }
+        end
+
+        # Return the current number of stored items.
+        def length
+          synchronize { super }
+        end
+
+        # Return if the buffer is empty.
+        def empty?
+          synchronize { super }
+        end
+
+        # Stored items are returned and the local buffer is reset.
+        def pop
+          synchronize { super }
+        end
+
+        def close
+          synchronize { super }
+        end
+
+        def synchronize(&block)
+          @mutex.synchronize(&block)
+        end
+      end
+    end
+  end
+end

data/lib/datadog/core/chunker.rb

@@ -0,0 +1,35 @@
+# frozen_string_literal: true
+
+module Datadog
+  module Core
+    # Chunks list of elements into batches
+    module Chunker
+      module_function
+
+      # Chunks a list into batches of at most +max_chunk_size+ elements each.
+      #
+      # An exception can occur if a single element is too large. That single
+      # element will be returned in its own chunk. You have to verify by yourself
+      # when such elements are returned.
+      #
+      # @param list [Enumerable] list of elements
+      # @param max_chunk_size [Numeric] maximum acceptable chunk size
+      # @return [Enumerable] lazy list of chunks
+      def chunk_by_size(list, max_chunk_size)
+        chunk_agg = 0
+        list.slice_before do |elem|
+          size = elem.size
+          chunk_agg += size
+          if chunk_agg > max_chunk_size
+            # Can't fit element in current chunk, start a new one.
+            chunk_agg = size
+            true
+          else
+            # Add to current chunk
+            false
+          end
+        end
+      end
+    end
+  end
+end