perf(profiling): unwind only one Frame per Task

Author: KowalskiThomas

ddtrace/internal/datadog/profiling/stack/echion/echion/stacks.h

@@ -44,10 +44,10 @@ inline FrameStack python_stack;
 
 // ----------------------------------------------------------------------------
 static size_t
-unwind_frame(PyObject* frame_addr, FrameStack& stack)
+unwind_frame(PyObject* frame_addr, FrameStack& stack, size_t max_depth = 0)
 {
     std::unordered_set<PyObject*> seen_frames; // Used to detect cycles in the stack
-    int count = 0;
+    size_t count = 0;
 
     PyObject* current_frame_addr = frame_addr;
     while (current_frame_addr != NULL && stack.size() < max_frames) {
@@ -72,6 +72,10 @@ unwind_frame(PyObject* frame_addr, FrameStack& stack)
 
         stack.push_back(*maybe_frame);
         count++;
+
+        if (max_depth > 0 && count >= max_depth) {
+            break;
+        }
     }
 
     return count;

ddtrace/internal/datadog/profiling/stack/echion/echion/tasks.h

@@ -321,29 +321,15 @@ TaskInfo::unwind(FrameStack& stack)
         PyObject* frame = coro_frames.top();
         coro_frames.pop();
 
-        auto new_frames = unwind_frame(frame, stack);
+        auto new_frames = unwind_frame(frame, stack, 1);
+        assert(new_frames <= 1 && "expected exactly 1 frame to be unwound (or 0 in case of an error)");
 
         // If we failed to unwind the Frame, stop unwinding the coroutine chain; otherwise we could
         // end up with Stacks with missing Frames between two coroutines Frames.
         if (new_frames == 0) {
             break;
         }
-
-        // If this is the first Frame being unwound (we have not added any Frames to the Stack yet),
-        // use the number of Frames added to the Stack to determine the size of the upper Python stack.
-        if (count == 0) {
-            // The first Frame is the coroutine Frame, so the Python stack size is the number of Frames - 1
-            auto upper_python_stack_size = new_frames - 1;
-
-            // Remove the Python Frames from the Stack (they will be added back later)
-            // We cannot push those Frames now because otherwise they would be added once per Task,
-            // we only want to add them once per Leaf Task, and on top of all non-leaf Tasks.
-            for (size_t i = 0; i < upper_python_stack_size; i++) {
-                stack.pop_back();
-            }
-        }
-
-        count += new_frames;
+        count += 1;
     }
 
     return count;