bpo-40010: Optimize signal handling in multithreaded applications

Doc/whatsnew/3.9.rst

@@ -411,6 +411,16 @@ Optimizations
 
   (Contributed by Serhiy Storchaka in :issue:`32856`.)
 
+* Optimize signal handling in multithreaded applications. If a thread different
+  than the main thread gets a signal, the bytecode evaluation loop is no longer
+  interrupted at each bytecode instruction to check for pending signals which
+  cannot be handled. Only the main thread of the main interpreter can handle
+  signals.
+
+  Previously, the bytecode evaluation loop was interrupted at each instruction
+  until the main thread handles signals.
+  (Contributed by Victor Stinner in :issue:`40010`.)
+
 
 Build and C API Changes
 =======================

Misc/NEWS.d/next/Core and Builtins/2020-03-19-02-26-13.bpo-40010.Y-LIR0.rst

@@ -0,0 +1,8 @@
+Optimize signal handling in multithreaded applications. If a thread different
+than the main thread gets a signal, the bytecode evaluation loop is no longer
+interrupted at each bytecode instruction to check for pending signals which
+cannot be handled. Only the main thread of the main interpreter can handle
+signals.
+
+Previously, the bytecode evaluation loop was interrupted at each instruction
+until the main thread handles signals.

Python/ceval.c

@@ -120,14 +120,24 @@ static size_t opcache_global_hits = 0;
 static size_t opcache_global_misses = 0;
 #endif
 
+
+/* Only handle signals on the main thread of the main interpreter. */
+static int
+thread_can_handle_signals(void)
+{
+    return (PyThread_get_thread_ident() == _PyRuntime.main_thread);
+}
+
+
 /* This can set eval_breaker to 0 even though gil_drop_request became
    1.  We believe this is all right because the eval loop will release
    the GIL eventually anyway. */
 #define COMPUTE_EVAL_BREAKER(ceval, ceval2) \
     _Py_atomic_store_relaxed( \
         &(ceval2)->eval_breaker, \
         _Py_atomic_load_relaxed(&(ceval)->gil_drop_request) | \
-        _Py_atomic_load_relaxed(&(ceval)->signals_pending) | \
+        (_Py_atomic_load_relaxed(&(ceval)->signals_pending) \
+            && thread_can_handle_signals()) | \
         _Py_atomic_load_relaxed(&(ceval2)->pending.calls_to_do) | \
         (ceval2)->pending.async_exc)
 
@@ -156,10 +166,11 @@ static size_t opcache_global_misses = 0;
         COMPUTE_EVAL_BREAKER(ceval, ceval2); \
     } while (0)
 
+/* eval_breaker is not set to 1 if thread_can_handle_signals() is false. */
 #define SIGNAL_PENDING_SIGNALS(ceval, ceval2) \
     do { \
         _Py_atomic_store_relaxed(&(ceval)->signals_pending, 1); \
-        _Py_atomic_store_relaxed(&(ceval2)->eval_breaker, 1); \
+        COMPUTE_EVAL_BREAKER(ceval, ceval2); \
     } while (0)
 
 #define UNSIGNAL_PENDING_SIGNALS(ceval, ceval2) \
@@ -540,8 +551,7 @@ handle_signals(PyThreadState *tstate)
 {
     _PyRuntimeState *runtime = tstate->interp->runtime;
 
-    /* Only handle signals on main thread */
-    if (PyThread_get_thread_ident() != runtime->main_thread) {
+    if (!thread_can_handle_signals()) {
         return 0;
     }
     /*

Python/ceval_gil.h

@@ -280,9 +280,18 @@ take_gil(PyThreadState *tstate)
     COND_SIGNAL(gil->switch_cond);
     MUTEX_UNLOCK(gil->switch_mutex);
 #endif
+
     if (_Py_atomic_load_relaxed(&ceval->gil_drop_request)) {
         RESET_GIL_DROP_REQUEST(ceval, ceval2);
     }
+    else {
+        /* bpo-40010: eval_breaker should be recomputed to be set to 1 if there
+           a pending signal: signal received by another thread which cannot
+           handle signals.
+
+           Note: RESET_GIL_DROP_REQUEST() calls COMPUTE_EVAL_BREAKER(). */
+        COMPUTE_EVAL_BREAKER(ceval, ceval2);
+    }
 
     int must_exit = tstate_must_exit(tstate);