Files
rocm-systems/source/lib/omnitrace/library/components/pthread_mutex_gotcha.cpp
T
Jonathan R. Madsen 9de3a6b0b4 Linux Perf Support + Causal Profiling Updates (#276)
* causal backtrace updates

- fix initial causal sampling period value

* causal delay updates

- tweak handling of sleep_for_overhead

* Fix experiment global scaling for prog pts

- results in drastically improved predictions

* pthread_mutex_gotcha updates

- disable all wrappers during causal profiling

* validate-causal-json.py updates

- support decimal stddev
- fix setting stddev from command-line

* causal perform_experiment_impl update

- handle start failing because finalizing

* deprecate causal::component::sample_rate

- appears to not help at all

* Rework sample info

* Increase causal unwind_depth

- use OMNITRACE_MAX_UNWIND_DEPTH

* validate-causal-json updates

- min experiments
  - exclude reporting predictions with less than X experiments at a given speedup
- percent samples
  - only print samples within X% of the peak (default: 95%)

* Update timemory submodule

- extensions to sampling for signals delivered via non-timer method
  - e.g. via HW counter overflow

* dwarf_entry::operator< updates

- sort via file

* causal profiling docs updates

- info about backends
- info about installing/enabling perf

* config updates: causal backend

- CausalBackend enum
- OMNITRACE_CAUSAL_BACKEND: perf, timer, auto
- omnitrace-causal option: --backend

* debug update

- use spin_mutex instead of std::mutex

* address_range::contains update

- range from 0-100 contains range from 10-100 but was returning false because high was == 100 not < 100

* symbol::operator< update

- handle load address differences

* sampling updates (non-causal)

- update get_timer to get_trigger + dynamic_cast

* container::static_vector updates

- support construction from container::c_array
- update_size private member func for handling atomic m_size

* Move perf files

- moved library/causal/perf.{hpp,cpp} to library/perf.{hpp,cpp}

* causal example update

- created impl.hpp (forward decls)
- renamed {cpu,rng}_func_impl to {cpu,rng}_impl_func
- only create two threads which run N iterations instead of two threads each iteration

* Update timemory submodule

- updates to unwind::processed_entry
- updates to procfs::maps

* Updated causal documentation

- fixed line numbers changed by modifications to causal example

* omnitrace-causal exe updates

- set OMNITRACE_THREAD_POOL_SIZE to zero by default

* core/containers updates

- static_vector: provide data() member function
- c_array pop_front() and pop_back() member functions

* core: config and argparse updates + perf

- core/perf.{hpp,cpp}
  - forward decl of enums
  - config-related capabilities
- argparse: --sample-overflow
- renamed some config functions
  - e.g. get_sampling_cpu_freq -> get_sampling_cputime_freq
- added config settings related to overflow sampling via perf
- added timer_sampling and overflow_sampling categories

* Update timemory submodule

- sampling allocator flushing

* binary updates

- lookup_ipaddr_entry
- use bfd_find_nearest_line instead of bfd_find_nearest_line_discriminator
  - discriminators are not used
- explicit instantiations of inlined_symbol::serialize

* Bump VERSION to 1.10.0

* sampling and perf updates

- support overflow sampling via Linux Perf
- update perf namespace
- update perf::perf_event
  - update record ctor: pointer instead of const ref
  - update open member func: return optional string
  - add m_batch_size member variable
- sampling updates
  - support overflow sampling
  - flush allocators
  - increase buffer size from 1024 to 2048
  - restructure post-processing in light of perf overflow supports
  - improve offload memory usage only load buffers for thread
  - load_offload_buffer(tid) uses thread-specific filepos
- component updates
  - backtrace_metrics::operator-=
  - backtrace_metrics::operator-
  - backtrace::sample does not record for overflow signal
  - callchain: perf overflow sample

* core updates

- component::sampling_percent does not report self + uses_percent_units

* causal updates

- tweak get_line_info
- overloads for set_current_selection (uint64_t, c_array, std::array)
- delay
  - use sampling::pause/sampling::resume
- experiment
  - experiment::sample derives from unwind::processed_entry
  - experiment::samples is vector instead of set
  - fixed samples
  - overloads for is_selected (uint64_t, c_array, std::array)
  - scaling factor defaults to 100 instead of 50
  - serialize updates follow change to experiment::sample
  - modify algorithm for increasing/decreasing experiment length
- sample_data
  - use map<uintptr, uint64_t> instead of set<sample_data>
  - get_samples returns vector<sample_data> instead of set<sample_data>
- sampling
  - support overflow via Linux Perf
  - update causal_offload_buffer
  - flush sampling allocator
- backtrace
  - overflow component

* libomnitrace-dl updates

- handle dl::InstrumentMode::PythonProfile

* testing updates (causal)

- causal line 155 -> causal line 100
- causal line 165 -> causal line 110

* formatting

* exit_gotcha updates

- exit_info for abort()
- message about non-zero exit code

* testing updates

- fail regex for causal tests
- validate-causal-json: >= min_experiments instead of > min_experiments
- handle OMNITRACE_DEBUG_SETTINGS in omnitrace_write_test_config

* causal sampling updates

- add new lines where appropriate

* causal data updates

- reorder diagnostic info when experiment fails to start

* binary updates

- symbol address range from address to address + symsize + 1
  - add 1 based on debug info

* causal data updates

- sample_selection wait_ns defaults to 1,000 instead of 10,000
- sample_selection wait scaled by iteration number
- save_line_info_impl verbosity
- print latest_eligible_pc when experiment does not start

* causal sampling + component updates

- perf backend disables component::backtrace
- ensure get_sampling_(realtime|cputime|overflow)_signal do not malloc

* causal: remove period stats

* validate-causal-json update

- fix --help

* causal data updates

- improve eligible pc history reporting when experiment fails to start

* causal data updates

- fix compute_eligible_lines_impl
  - eligible address ranges returning too many ranges
  - occasionally, overwrite all *true* eligible address ranges

* causal data updates

- reduce scoped ranges to symbol ranges
- is_eligible_address() returns true contains (not just coarse)
- revert some sample_selection behavior

* binary address_multirange updates

- make coarse_range private
- fix operator+=(pair<coarse, uintptr_t>)

* causal example update

- fix nsync to default to once per iteration

* binary analysis updates

- tweak header file includes

* causal updates

- remove factoring in sleep_for_overhead
- invoke delay::process() even if experiment is not active

* causal data updates

- update latest_eligible_pc structure

* update omnitrace-install.py.in

- fix support for fedora
  - /etc/os-release does not have ID_LIKE
  - fallback to RHEL 8.7 if version not specified

* update omnitrace-install.py.in

- fix support for debian
  - /etc/os-release does not have ID_LIKE
  - version mapping

* Update documentation

- update docs on installation

* causal data and experiment updates

- data: reset_sample_selection

* causal set_current_selection debugging

- debug messages for failed e2e runs

* causal data and backtrace component updates

- data: set_current_selection returns the number of eligible addresses added
- backtrace: if cputime signal has selected zero IPs > 5x, then realtime signal starts contributing call-stacks

* core library updates

- move config::parse_numeric_range to utility namespace
- add core/utility.cpp
- support range:increment, e.g. 5-25:10 expands to '5 15 25' instead of '5 10 15 20 25'

* omnitrace-causal update

- end-to-end expands all speedups
- support range:increment in speedups

* causal backtrace updates

- remove select_ival (realtime signal always contributes when select_count == 0)

* containers: static_vector update

- explicit c_array constructor
- explicit std::array constructor

* causal data updates

- remove set_current_selection(uint64_t)
- remove set_current_selection(std::array)
- sample_selection increase default wait time
- report eligible PC candidates
- move reset_sample_selection to perform_experiment_impl
- decrease latest_eligible_pc array size
- set_current_selection does not guard for experiment::active

* core debug updates

- OMNITRACE_PRINT_COLOR macros

* causal data updates

- tweak to experiment never started message

* causal gotcha updates

- remove unused code

* critical trace updates

- remove unused code

* omnitrace-causal

- OMNITRACE_LAUNCHER

* causal data updates

- don't fail on end-to-end + omnitrace-causal

* causal backtrace updates

- reintroduce select_ival behavior

* causal data updates

- tweak verbose messages about number of PC candidates

* core mproc updates

- utilities for waiting on child PID and diagnosing status
  - omnitrace::mproc::wait_pid
  - omnitrace::mproc::diagnose_status

* omnitrace-run updates

- support --fork argument for executing via fork in current process + execvpe on child instead of execvpe in current process

* omnitrace-causal updates

- wait_pid and diagnose_status just call equivalent functions in omnitrace::mproc

* ubuntu-focal workflow update

- attempt to launch ubuntu-focal-codecov job with CAP_SYS_ADMIN and use perf backend

* tests reorg and updates

- remove binary-rewrite-sampling and runtime-instrument-sampling tests
- rename *-preload tests (which use omnitrace-sample exe) to *-sampling
- split tests/CMakeLists.txt into several tests/omnitrace-<category>-tests.cmake files
- tweak to causal-both-omni-func test
  - add args: -n 2 -b timer

* update validate-causal-json.py

- better reasoning info for adjusting tolerance
- always apply tolerance adjustments in CI mode

* causal e2e tests update

- add label "causal-e2e" label
- tweak params
  - old: 80 12 432525 500000000
  - new: 80 50 432525 100000000
- disable processor affinity for slow-func/line-100 tests
  - artificially inflates some speedups with perf

* unblocking_gotcha updates

- overload operator() according to gotcha function index

* blocking_gotcha updates

- overload operator() according to gotcha function index
- fix bug where potentially post block functors (e.g. pthread_mutex_trylock) throw error if lock is not acquired.

* parse_numeric_range update

- support unordered_set

* config update

- OMNITRACE_DEBUG_{TIDS,PIDS} use parse_numeric_range
2023-04-13 02:14:35 -05:00

302 строки
10 KiB
C++

// MIT License
//
// Copyright (c) 2022 Advanced Micro Devices, Inc. All Rights Reserved.
//
// Permission is hereby granted, free of charge, to any person obtaining a copy
// of this software and associated documentation files (the "Software"), to deal
// in the Software without restriction, including without limitation the rights
// to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
// copies of the Software, and to permit persons to whom the Software is
// furnished to do so, subject to the following conditions:
//
// The above copyright notice and this permission notice shall be included in all
// copies or substantial portions of the Software.
//
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
// IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
// FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
// AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
// LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
// OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
// SOFTWARE.
#include "library/components/pthread_mutex_gotcha.hpp"
#include "core/config.hpp"
#include "core/debug.hpp"
#include "core/utility.hpp"
#include "library/components/category_region.hpp"
#include "library/critical_trace.hpp"
#include "library/runtime.hpp"
#include "library/thread_info.hpp"
#include <timemory/backends/threading.hpp>
#include <timemory/utility/signals.hpp>
#include <timemory/utility/types.hpp>
#include <cstdint>
#include <pthread.h>
#include <stdexcept>
namespace omnitrace
{
namespace component
{
using Device = critical_trace::Device;
using Phase = critical_trace::Phase;
pthread_mutex_gotcha::hash_array_t&
pthread_mutex_gotcha::get_hashes()
{
// theoretically, this private function will NEVER be called until it
// is called by a gotcha wrapper, which means the tool ids should be
// fully populated. If that fails to be the case for some reason,
// we could see weird results.
static auto _v = []() {
const auto& _data = pthread_mutex_gotcha_t::get_gotcha_data();
auto _init = hash_array_t{};
auto _skip = std::set<size_t>{};
if(!config::get_trace_thread_locks())
{
for(size_t i = 0; i < 3; ++i)
_skip.emplace(i);
}
if(!config::get_trace_thread_rwlocks())
{
for(size_t i = 3; i < 8; ++i)
_skip.emplace(i);
}
if(!config::get_trace_thread_spin_locks())
{
for(size_t i = 9; i < 12; ++i)
_skip.emplace(i);
}
if(!config::get_trace_thread_barriers()) _skip.emplace(8);
if(!config::get_trace_thread_join()) _skip.emplace(12);
for(size_t i = 0; i < gotcha_capacity; ++i)
{
auto&& _id = _data.at(i).tool_id;
if(!_id.empty())
_init.at(i) = critical_trace::add_hash_id(_id.c_str());
else
{
if(_skip.count(i) > 0) continue;
OMNITRACE_VERBOSE(
1,
"WARNING!!! pthread_mutex_gotcha tool id at index %zu was empty!\n",
i);
}
OMNITRACE_CI_FAIL(
_id.empty() || _init.at(i) == 0,
"pthread_mutex_gotcha tool id at index %zu has no hash value\n", i);
}
return _init;
}();
return _v;
}
void
pthread_mutex_gotcha::configure()
{
pthread_mutex_gotcha_t::get_initializer() = []() {
if(!tim::settings::enabled() || get_use_causal()) return;
if(config::get_trace_thread_locks())
{
pthread_mutex_gotcha_t::configure(
comp::gotcha_config<0, int, pthread_mutex_t*>{ "pthread_mutex_lock" });
pthread_mutex_gotcha_t::configure(
comp::gotcha_config<1, int, pthread_mutex_t*>{ "pthread_mutex_unlock" });
pthread_mutex_gotcha_t::configure(
comp::gotcha_config<2, int, pthread_mutex_t*>{ "pthread_mutex_trylock" });
}
if(config::get_trace_thread_rwlocks())
{
pthread_mutex_gotcha_t::configure(
comp::gotcha_config<3, int, pthread_rwlock_t*>{
"pthread_rwlock_rdlock" });
pthread_mutex_gotcha_t::configure(
comp::gotcha_config<4, int, pthread_rwlock_t*>{
"pthread_rwlock_wrlock" });
pthread_mutex_gotcha_t::configure(
comp::gotcha_config<5, int, pthread_rwlock_t*>{
"pthread_rwlock_tryrdlock" });
pthread_mutex_gotcha_t::configure(
comp::gotcha_config<6, int, pthread_rwlock_t*>{
"pthread_rwlock_trywrlock" });
pthread_mutex_gotcha_t::configure(
comp::gotcha_config<7, int, pthread_rwlock_t*>{
"pthread_rwlock_unlock" });
}
if(config::get_trace_thread_barriers())
{
pthread_mutex_gotcha_t::configure(
comp::gotcha_config<8, int, pthread_barrier_t*>{
"pthread_barrier_wait" });
}
if(config::get_trace_thread_spin_locks())
{
pthread_mutex_gotcha_t::configure(
comp::gotcha_config<9, int, pthread_spinlock_t*>{ "pthread_spin_lock" });
pthread_mutex_gotcha_t::configure(
comp::gotcha_config<10, int, pthread_spinlock_t*>{
"pthread_spin_trylock" });
pthread_mutex_gotcha_t::configure(
comp::gotcha_config<11, int, pthread_spinlock_t*>{
"pthread_spin_unlock" });
}
if(config::get_trace_thread_join())
{
pthread_mutex_gotcha_t::configure(
comp::gotcha_config<12, int, pthread_t, void**>{ "pthread_join" });
}
};
}
void
pthread_mutex_gotcha::shutdown()
{
pthread_mutex_gotcha_t::disable();
}
pthread_mutex_gotcha::pthread_mutex_gotcha(const gotcha_data_t& _data)
: m_data{ &_data }
{}
template <typename... Args>
auto
pthread_mutex_gotcha::operator()(uintptr_t&& _id, int (*_callee)(Args...),
Args... _args) const
{
using bundle_t = category_region<category::pthread>;
if(is_disabled() || m_protect)
{
if(!_callee)
{
if(m_data)
{
OMNITRACE_PRINT("Warning! nullptr to %s\n", m_data->tool_id.c_str());
}
return EINVAL;
}
return (*_callee)(_args...);
}
struct local_dtor
{
explicit local_dtor(bool& _v)
: _protect{ _v }
{}
~local_dtor() { _protect = false; }
bool& _protect;
} _dtor{ m_protect = true };
uint64_t _cid = 0;
uint64_t _parent_cid = 0;
uint32_t _depth = 0;
int64_t _ts = 0;
if(_id < std::numeric_limits<uintptr_t>::max() && get_use_critical_trace())
{
OMNITRACE_SCOPED_THREAD_STATE(ThreadState::Internal);
std::tie(_cid, _parent_cid, _depth) = create_cpu_cid_entry();
_ts = comp::wall_clock::record();
}
bundle_t::audit(std::string_view{ m_data->tool_id }, audit::incoming{}, _args...);
auto _ret = (*_callee)(_args...);
bundle_t::audit(std::string_view{ m_data->tool_id }, audit::outgoing{}, _ret);
if(_id < std::numeric_limits<uintptr_t>::max() && get_use_critical_trace())
{
OMNITRACE_SCOPED_THREAD_STATE(ThreadState::Internal);
add_critical_trace<Device::CPU, Phase::DELTA>(
threading::get_id(), _cid, 0, _parent_cid, _ts, comp::wall_clock::record(), 0,
_id, get_hashes().at(m_data->index), _depth);
}
tim::consume_parameters(_id, _cid, _parent_cid, _depth, _ts);
return _ret;
}
int
pthread_mutex_gotcha::operator()(int (*_callee)(pthread_mutex_t*),
pthread_mutex_t* _mutex) const
{
if(get_state() != ::omnitrace::State::Active || m_protect) return (*_callee)(_mutex);
return (*this)(reinterpret_cast<uintptr_t>(_mutex), _callee, _mutex);
}
int
pthread_mutex_gotcha::operator()(int (*_callee)(pthread_spinlock_t*),
pthread_spinlock_t* _lock) const
{
if(get_state() != ::omnitrace::State::Active || m_protect) return (*_callee)(_lock);
return (*this)(reinterpret_cast<uintptr_t>(_lock), _callee, _lock);
}
int
pthread_mutex_gotcha::operator()(int (*_callee)(pthread_rwlock_t*),
pthread_rwlock_t* _lock) const
{
if(get_state() != ::omnitrace::State::Active || m_protect) return (*_callee)(_lock);
return (*this)(reinterpret_cast<uintptr_t>(_lock), _callee, _lock);
}
int
pthread_mutex_gotcha::operator()(int (*_callee)(pthread_barrier_t*),
pthread_barrier_t* _barrier) const
{
if(get_state() != ::omnitrace::State::Active || m_protect)
return (*_callee)(_barrier);
return (*this)(reinterpret_cast<uintptr_t>(_barrier), _callee, _barrier);
}
int
pthread_mutex_gotcha::operator()(int (*_callee)(pthread_t, void**), pthread_t _thr,
void** _tinfo) const
{
if(get_state() != ::omnitrace::State::Active || m_protect)
return (*_callee)(_thr, _tinfo);
return (*this)(static_cast<uintptr_t>(threading::get_id()), _callee, _thr, _tinfo);
}
bool
pthread_mutex_gotcha::is_disabled()
{
static thread_local const auto& _info = thread_info::get();
return (!_info || _info->is_offset || get_state() != ::omnitrace::State::Active ||
get_thread_state() != ThreadState::Enabled);
}
} // namespace component
} // namespace omnitrace
namespace tim
{
namespace policy
{
template <size_t N>
pthread_mutex_gotcha&
static_data<pthread_mutex_gotcha, pthread_mutex_gotcha_t>::operator()(
std::integral_constant<size_t, N>, const component::gotcha_data& _data) const
{
using thread_data_t =
omnitrace::thread_data<pthread_mutex_gotcha, std::integral_constant<size_t, N>>;
static thread_local auto& _v =
thread_data_t::instance(omnitrace::construct_on_thread{}, _data);
return *_v;
}
} // namespace policy
} // namespace tim