forked from OSchip/llvm-project
tsan: optimize test-only barrier
The updated lots_of_threads.c test with 300 threads started running for too long on machines with low hardware parallelism (e.g. taskset -c 0-1). On lots of CPUs it finishes in ~2 secs. But with taskset -c 0-1 it runs for hundreds of seconds effectively spinning in the barrier in the sleep loop. We now have the handy futex API in sanitizer_common. Use it instead of the passive spin loop. It makes the test run only faster with taskset -c 0-1, it runs for ~1.5 secs, while with full parallelism it still runs for ~2 secs (but consumes less CPU time). Depends on D107131. Reviewed By: vitalybuka Differential Revision: https://reviews.llvm.org/D107132
This commit is contained in:
parent
dbe36e4073
commit
97795be22f
|
@ -2916,30 +2916,36 @@ void InitializeInterceptors() {
|
|||
// Note that no_sanitize_thread attribute does not turn off atomic interception
|
||||
// so attaching it to the function defined in user code does not help.
|
||||
// That's why we now have what we have.
|
||||
constexpr uptr kBarrierThreadBits = 10;
|
||||
constexpr uptr kBarrierThreads = 1 << kBarrierThreadBits;
|
||||
constexpr u32 kBarrierThreadBits = 10;
|
||||
constexpr u32 kBarrierThreads = 1 << kBarrierThreadBits;
|
||||
|
||||
extern "C" SANITIZER_INTERFACE_ATTRIBUTE
|
||||
void __tsan_testonly_barrier_init(u64 *barrier, u32 count) {
|
||||
if (count >= kBarrierThreads) {
|
||||
Printf("barrier_init: count is too large (%d)\n", count);
|
||||
extern "C" SANITIZER_INTERFACE_ATTRIBUTE void __tsan_testonly_barrier_init(
|
||||
atomic_uint32_t *barrier, u32 num_threads) {
|
||||
if (num_threads >= kBarrierThreads) {
|
||||
Printf("barrier_init: count is too large (%d)\n", num_threads);
|
||||
Die();
|
||||
}
|
||||
// kBarrierThreadBits lsb is thread count,
|
||||
// the remaining are count of entered threads.
|
||||
*barrier = count;
|
||||
atomic_store(barrier, num_threads, memory_order_relaxed);
|
||||
}
|
||||
|
||||
extern "C" SANITIZER_INTERFACE_ATTRIBUTE
|
||||
void __tsan_testonly_barrier_wait(u64 *barrier) {
|
||||
constexpr uptr kThreadMask = kBarrierThreads - 1;
|
||||
unsigned old = __atomic_fetch_add(barrier, kBarrierThreads, __ATOMIC_RELAXED);
|
||||
unsigned old_epoch = (old >> kBarrierThreadBits) / (old & kThreadMask);
|
||||
static u32 barrier_epoch(u32 value) {
|
||||
return (value >> kBarrierThreadBits) / (value & (kBarrierThreads - 1));
|
||||
}
|
||||
|
||||
extern "C" SANITIZER_INTERFACE_ATTRIBUTE void __tsan_testonly_barrier_wait(
|
||||
atomic_uint32_t *barrier) {
|
||||
u32 old = atomic_fetch_add(barrier, kBarrierThreads, memory_order_relaxed);
|
||||
u32 old_epoch = barrier_epoch(old);
|
||||
if (barrier_epoch(old + kBarrierThreads) != old_epoch) {
|
||||
FutexWake(barrier, (1 << 30));
|
||||
return;
|
||||
}
|
||||
for (;;) {
|
||||
unsigned cur = __atomic_load_n(barrier, __ATOMIC_RELAXED);
|
||||
unsigned cur_epoch = (cur >> kBarrierThreadBits) / (cur & kThreadMask);
|
||||
if (cur_epoch != old_epoch)
|
||||
break;
|
||||
internal_usleep(100);
|
||||
u32 cur = atomic_load(barrier, memory_order_relaxed);
|
||||
if (barrier_epoch(cur) != old_epoch)
|
||||
return;
|
||||
FutexWait(barrier, cur);
|
||||
}
|
||||
}
|
||||
|
|
|
@ -17,7 +17,7 @@
|
|||
// TSan-invisible barrier.
|
||||
// Tests use it to establish necessary execution order in a way that does not
|
||||
// interfere with tsan (does not establish synchronization between threads).
|
||||
typedef unsigned long long invisible_barrier_t;
|
||||
typedef unsigned invisible_barrier_t;
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
|
|
Loading…
Reference in New Issue