* Fix for thread limit tests. Which are failing due to exceeding the number of threads allowed.

Signed-off-by: Anuj-Kumar Shukla <AnujKumar.Shukla@amd.com>

* Update CMakeLists.txt

* Stopping thread creation after max thread limit

* Adressed review comments

* Update projects/rocprofiler-systems/tests/source/CMakeLists.txt

---------

Signed-off-by: Anuj-Kumar Shukla <AnujKumar.Shukla@amd.com>
Co-authored-by: anujshuk-amd <anujshuk@amd.com>
Этот коммит содержится в:
David Galiffi
2025-10-09 19:07:14 -04:00
коммит произвёл GitHub
родитель d195d925e9
Коммит 182a750c08
2 изменённых файлов: 59 добавлений и 25 удалений
+18 -1
Просмотреть файл
@@ -62,6 +62,9 @@ namespace component
{
using bundle_t = tim::lightweight_tuple<comp::wall_clock>;
using category_region_t = tim::lightweight_tuple<category_region<category::pthread>>;
// The maximum limit for the number of threads is set at 4096. declared and stored in the
// set_storage struct's `types.hpp` file.
constexpr size_t allowed_max_threads = 4096;
namespace
{
@@ -181,7 +184,21 @@ pthread_create_gotcha::wrapper::operator()() const
auto _coverage = (get_mode() == Mode::Coverage);
const auto& _parent_info = thread_info::get(m_config.parent_tid, InternalTID);
const auto& _info = thread_info::init(m_config.offset);
auto _dtor = [&]() {
auto _sequent_value = _info->index_data ? _info->index_data->sequent_value : -1;
if(static_cast<size_t>(_sequent_value) >= allowed_max_threads)
{
static std::once_flag thread_limit_warning_flag;
std::call_once(thread_limit_warning_flag, []() {
ROCPROFSYS_WARNING_F(
1,
"[rocprof-sys][WARNING] Maximum allowed thread limit (%zu) "
"reached. Further thread creation and profiling will be "
"disabled to prevent resource exhaustion.\n",
allowed_max_threads);
});
return m_routine(m_arg);
}
auto _dtor = [&]() {
set_thread_state(ThreadState::Internal);
if(_is_sampling)
{
+41 -24
Просмотреть файл
@@ -40,30 +40,47 @@ set(_thread_limit_environment
"ROCPROFSYS_VERBOSE=2"
"ROCPROFSYS_TIMEMORY_COMPONENTS=wall_clock,peak_rss,page_rss"
)
# Maximum allowed threads
set(ALLOWED_MAX_THREADS 4096)
math(EXPR THREAD_LIMIT_TEST_VALUE "${ROCPROFSYS_MAX_THREADS} + 24")
math(EXPR THREAD_LIMIT_TEST_VALUE_PLUS_ONE "${THREAD_LIMIT_TEST_VALUE} + 1")
math(EXPR THREAD_VAL_1 "${ROCPROFSYS_MAX_THREADS} + 24")
math(EXPR THREAD_VAL_2 "${ALLOWED_MAX_THREADS} + 1")
set(_thread_limit_pass_regex "\\|${THREAD_LIMIT_TEST_VALUE}>>>")
set(_thread_limit_fail_regex
"\\|${THREAD_LIMIT_TEST_VALUE_PLUS_ONE}>>>|ROCPROFSYS_ABORT_FAIL_REGEX"
)
set(THREAD_VALUES ${THREAD_VAL_1} ${THREAD_VAL_2})
rocprofiler_systems_add_test(
SKIP_BASELINE
NAME thread-limit
TARGET thread-limit
LABELS "max-threads"
REWRITE_ARGS -e -v 2 -i 1024 --label return args
RUNTIME_ARGS -e -v 1 -i 1024 --label return args
RUN_ARGS 35 2 ${THREAD_LIMIT_TEST_VALUE}
REWRITE_TIMEOUT 180
RUNTIME_TIMEOUT 360
RUNTIME_PASS_REGEX "${_thread_limit_pass_regex}"
SAMPLING_PASS_REGEX "${_thread_limit_pass_regex}"
REWRITE_RUN_PASS_REGEX "${_thread_limit_pass_regex}"
RUNTIME_FAIL_REGEX "${_thread_limit_fail_regex}"
SAMPLING_FAIL_REGEX "${_thread_limit_fail_regex}"
REWRITE_RUN_FAIL_REGEX "${_thread_limit_fail_regex}"
ENVIRONMENT "${_thread_limit_environment}"
)
# Loop over thread values
foreach(THREADS IN LISTS THREAD_VALUES)
set(THREAD_PASS_VALUE ${THREADS})
math(EXPR THREAD_FAIL_VALUE "${THREADS} + 1")
if(${THREADS} GREATER_EQUAL ${ALLOWED_MAX_THREADS})
math(EXPR THREAD_PASS_VALUE "${ALLOWED_MAX_THREADS} - 1")
math(EXPR THREAD_FAIL_VALUE "${THREADS}")
endif()
set(_thread_limit_pass_regex "\\|${THREAD_PASS_VALUE}>>>")
set(_thread_limit_fail_regex "\\|${THREAD_FAIL_VALUE}>>>|ROCPROFSYS_ABORT_FAIL_REGEX")
# Unique test name
set(_test_name thread-limit-${THREADS})
# Add test
rocprofiler_systems_add_test(
SKIP_BASELINE
NAME ${_test_name}
TARGET thread-limit
LABELS "max-threads"
REWRITE_ARGS -e -v 2 -i 1024 --label return args
RUNTIME_ARGS -e -v 1 -i 1024 --label return args
RUN_ARGS 35 2 ${THREADS}
SAMPLING_TIMEOUT 180
REWRITE_TIMEOUT 180
RUNTIME_TIMEOUT 360
RUNTIME_PASS_REGEX "${_thread_limit_pass_regex}"
SAMPLING_PASS_REGEX "${_thread_limit_pass_regex}"
REWRITE_RUN_PASS_REGEX "${_thread_limit_pass_regex}"
RUNTIME_FAIL_REGEX "${_thread_limit_fail_regex}"
SAMPLING_FAIL_REGEX "${_thread_limit_fail_regex}"
REWRITE_RUN_FAIL_REGEX "${_thread_limit_fail_regex}"
ENVIRONMENT "${_thread_limit_environment}"
)
endforeach()