fix(profiling): always report CPU time regardless of Thread running state

Author: KowalskiThomas

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

@@ -54,13 +54,11 @@ class ThreadInfo
     mach_port_t mach_port;
 #endif
     microsecond_t cpu_time;
-    bool running_ = false;
 
     uintptr_t asyncio_loop = 0;
     uintptr_t tstate_addr = 0; // Remote address of PyThreadState for accessing asyncio_tasks_head
 
     [[nodiscard]] Result<void> update_cpu_time();
-    bool is_running();
 
     [[nodiscard]] Result<void> sample(EchionSampler&, int64_t, PyThreadState*, microsecond_t);
     void unwind(EchionSampler&, PyThreadState*);

ddtrace/internal/datadog/profiling/stack/src/echion/threads.cc

@@ -584,7 +584,7 @@ ThreadInfo::sample(EchionSampler& echion, int64_t iid, PyThreadState* tstate, mi
         return ErrorKind::CpuTimeError;
     }
 
-    Renderer::get().render_cpu_time(is_running() ? cpu_time - previous_cpu_time : 0);
+    Renderer::get().render_cpu_time(cpu_time - previous_cpu_time);
 
     this->unwind(echion, tstate);
 
@@ -640,29 +640,18 @@ Result<void>
 ThreadInfo::update_cpu_time()
 {
 #if defined PL_LINUX
-    struct timespec ts1;
-    if (clock_gettime(cpu_clock_id, &ts1)) {
+    struct timespec ts;
+    if (clock_gettime(cpu_clock_id, &ts)) {
         // If the clock is invalid, we skip updating the CPU time.
         // This can happen if we try to compute CPU time for a thread that has exited.
         if (errno == EINVAL) {
-            this->running_ = false;
             return Result<void>::ok();
         }
 
         return ErrorKind::CpuTimeError;
     }
 
-    this->cpu_time = TS_TO_MICROSECOND(ts1);
-
-    // Determine if running by checking if CPU time advances between two back-to-back
-    // measurements. This is done here to avoid a separate is_running() call with
-    // its own syscalls (reduces 3 syscalls per thread to 2).
-    struct timespec ts2;
-    if (clock_gettime(cpu_clock_id, &ts2) != 0) {
-        this->running_ = false;
-    } else {
-        this->running_ = (ts1.tv_sec != ts2.tv_sec || ts1.tv_nsec != ts2.tv_nsec);
-    }
+    this->cpu_time = TS_TO_MICROSECOND(ts);
 #elif defined PL_DARWIN
     thread_basic_info_data_t info;
     mach_msg_type_number_t count = THREAD_BASIC_INFO_COUNT;
@@ -673,33 +662,22 @@ ThreadInfo::update_cpu_time()
         // If the thread is invalid, we skip updating the CPU time.
         // This can happen if we try to compute CPU time for a thread that has exited.
         if (kr == KERN_INVALID_ARGUMENT) {
-            this->running_ = false;
             return Result<void>::ok();
         }
 
         return ErrorKind::CpuTimeError;
     }
 
     if (info.flags & TH_FLAGS_IDLE) {
-        this->running_ = false;
         return Result<void>::ok();
     }
 
     this->cpu_time = TV_TO_MICROSECOND(info.user_time) + TV_TO_MICROSECOND(info.system_time);
-    // On macOS, thread_info already gives us run_state, so no need to check if the clock is advancing
-    this->running_ = (info.run_state == TH_STATE_RUNNING);
 #endif
 
     return Result<void>::ok();
 }
 
-bool
-ThreadInfo::is_running()
-{
-    // Running state is computed in update_cpu_time by taking two back-to-back measurements of the CPU time.
-    return this->running_;
-}
-
 void
 for_each_thread(EchionSampler& echion, InterpreterInfo& interp, PyThreadStateCallback callback)
 {

releasenotes/notes/profiling-always-report-cpu-time-5f9aa07e648801fc.yaml

@@ -0,0 +1,4 @@
+fixes:
+  - |
+    profiling: The Profiler now always reports CPU time for threads, regardless of whether they are running when
+    the sample is captured.