Files
rocm-systems/projects/rocprofiler-systems/source/lib/core/perf.cpp
T
Jonathan R. Madsen 557adea45a 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

[ROCm/rocprofiler-systems commit: 9de3a6b0b4]
2023-04-13 02:14:35 -05:00

245 baris
8.2 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 "perf.hpp"
#include "debug.hpp"
#include <timemory/units.hpp>
namespace omnitrace
{
namespace perf
{
namespace units = ::tim::units;
std::vector<std::string>
get_config_choices()
{
namespace regex_const = ::std::regex_constants;
auto _data = std::vector<std::string>{};
auto _papi_events = tim::papi::available_events_info();
const auto _prefix = std::string_view{ "perf::" };
auto _regex =
std::regex{ "^(perf::|)PERF_COUNT_(HW|SW|HW_CACHE)_([A-Z_]+)(|:[A-Z]+)$",
regex_const::optimize };
for(const auto& itr : _papi_events)
{
if(std::regex_match(itr.symbol(), _regex))
{
auto _symbol = itr.symbol();
auto _pos = _symbol.find(_prefix);
if(_pos == 0) _symbol = _symbol.substr(_prefix.length());
_data.emplace_back(_symbol);
}
}
std::sort(_data.begin(), _data.end());
_data.erase(std::unique(_data.begin(), _data.end()), _data.end());
return _data;
}
event_type
get_event_type(std::string_view _v)
{
if(_v.find("PERF_COUNT_SW_") != std::string_view::npos)
return event_type::software;
else if(_v.find("PERF_COUNT_SW_") != std::string_view::npos &&
!std::regex_search(_v.data(),
std::regex{ "PERF_COUNT_HW_CACHE_(MISSES|REFERENCES)$" }))
return event_type::hw_cache;
else if(_v.find("PERF_COUNT_HW_") != std::string_view::npos)
return event_type::hardware;
return event_type::max;
}
hw_config
get_hw_config(std::string_view _v)
{
#define HW_CONFIG_REGEX(KEY) std::regex_search(_v.data(), std::regex{ "(HW_" KEY ")$" })
if(HW_CONFIG_REGEX("CPU_CYCLES"))
return hw_config::cpu_cycles;
else if(HW_CONFIG_REGEX("INSTRUCTIONS"))
return hw_config::instructions;
else if(HW_CONFIG_REGEX("CACHE_REFERENCES"))
return hw_config::cache_references;
else if(HW_CONFIG_REGEX("CACHE_MISSES"))
return hw_config::cache_misses;
else if(HW_CONFIG_REGEX("BRANCH_INSTRUCTIONS"))
return hw_config::branch_instructions;
else if(HW_CONFIG_REGEX("BRANCH_MISSES"))
return hw_config::branch_misses;
else if(HW_CONFIG_REGEX("BUS_CYCLES"))
return hw_config::bus_cycles;
else if(HW_CONFIG_REGEX("STALLED_CYCLES_FRONTEND"))
return hw_config::stalled_cycles_frontend;
else if(HW_CONFIG_REGEX("STALLED_CYCLES_BACKEND"))
return hw_config::stalled_cycles_backend;
else if(HW_CONFIG_REGEX("REF_CPU_CYCLES"))
return hw_config::reference_cpu_cycles;
else
{
OMNITRACE_THROW("Unknown perf hardware config: %s", _v.data());
}
#undef HW_CONFIG_REGEX
return hw_config::max;
}
sw_config
get_sw_config(std::string_view _v)
{
#define SW_CONFIG_REGEX(KEY) std::regex_search(_v.data(), std::regex{ "(SW_" KEY ")$" })
if(SW_CONFIG_REGEX("CPU_CLOCK"))
return sw_config::cpu_clock;
else if(SW_CONFIG_REGEX("TASK_CLOCK"))
return sw_config::task_clock;
else if(SW_CONFIG_REGEX("PAGE_FAULTS"))
return sw_config::page_faults;
else if(SW_CONFIG_REGEX("CONTEXT_SWITCHES"))
return sw_config::context_switches;
else if(SW_CONFIG_REGEX("CPU_MIGRATIONS"))
return sw_config::cpu_migrations;
else if(SW_CONFIG_REGEX("PAGE_FAULTS_MIN"))
return sw_config::page_faults_minor;
else if(SW_CONFIG_REGEX("PAGE_FAULTS_MAJ"))
return sw_config::page_faults_major;
else if(SW_CONFIG_REGEX("ALIGNMENT_FAULTS"))
return sw_config::alignment_faults;
else if(SW_CONFIG_REGEX("EMULATION_FAULTS"))
return sw_config::emulation_faults;
else
{
OMNITRACE_THROW("Unknown perf hw cache config: %s", _v.data());
}
#undef SW_CONFIG_REGEX
return sw_config::max;
}
int
get_hw_cache_config(std::string_view _v)
{
int _value = 0;
#define HW_CACHE_CONFIG_REGEX(KEY) \
std::regex_search(_v.data(), std::regex{ "(HW_CACHE_" KEY ")" })
if(HW_CACHE_CONFIG_REGEX("L1D"))
_value |= static_cast<int>(hw_cache_config::l1d);
else if(HW_CACHE_CONFIG_REGEX("L1I"))
_value |= static_cast<int>(hw_cache_config::l1i);
else if(HW_CACHE_CONFIG_REGEX("LL"))
_value |= static_cast<int>(hw_cache_config::ll);
else if(HW_CACHE_CONFIG_REGEX("DTLB"))
_value |= static_cast<int>(hw_cache_config::dtlb);
else if(HW_CACHE_CONFIG_REGEX("ITLB"))
_value |= static_cast<int>(hw_cache_config::itlb);
else if(HW_CACHE_CONFIG_REGEX("BPU"))
_value |= static_cast<int>(hw_cache_config::bpu);
else if(HW_CACHE_CONFIG_REGEX("NODE"))
_value |= static_cast<int>(hw_cache_config::node);
else
OMNITRACE_THROW("Unknown perf software config: %s", _v.data());
#undef HW_CACHE_CONFIG_REGEX
#define HW_CACHE_OP_REGEX(KEY) \
std::regex_search(_v.data(), std::regex{ "(HW_CACHE_([A-Z1]+):" KEY ")" })
if(HW_CACHE_OP_REGEX("READ"))
_value |= (static_cast<int>(hw_cache_op::read) << 8);
else if(HW_CACHE_OP_REGEX("WRITE"))
_value |= (static_cast<int>(hw_cache_op::write) << 8);
else if(HW_CACHE_OP_REGEX("PREFETCH"))
_value |= (static_cast<int>(hw_cache_op::prefetch) << 8);
else
_value |= (static_cast<int>(hw_cache_op::read) << 8);
#undef HW_CACHE_OP_REGEX
#define HW_CACHE_OP_RESULT_REGEX(KEY) \
std::regex_search(_v.data(), std::regex{ "(HW_CACHE_([A-Z1]+):" KEY ")" })
if(HW_CACHE_OP_RESULT_REGEX("READ"))
_value |= (static_cast<int>(hw_cache_op_result::access) << 16);
else if(HW_CACHE_OP_RESULT_REGEX("WRITE"))
_value |= (static_cast<int>(hw_cache_op_result::miss) << 16);
else
_value |= (static_cast<int>(hw_cache_op_result::access) << 16);
#undef HW_CACHE_OP_RESULT_REGEX
return _value;
}
void
config_overflow_sampling(struct perf_event_attr& _pe, std::string_view _event,
double _freq)
{
auto _period = (1.0 / _freq) * units::sec;
_pe.type = static_cast<int>(perf::get_event_type(_event));
switch(_pe.type)
{
case PERF_TYPE_HARDWARE:
{
_pe.config = static_cast<int>(perf::get_hw_config(_event));
break;
}
case PERF_TYPE_SOFTWARE:
{
_pe.config = static_cast<int>(perf::get_sw_config(_event));
break;
}
case PERF_TYPE_HW_CACHE:
{
_pe.config = static_cast<int>(perf::get_hw_cache_config(_event));
break;
}
case PERF_TYPE_BREAKPOINT:
case PERF_TYPE_TRACEPOINT:
case PERF_TYPE_RAW:
case PERF_TYPE_MAX:
default:
{
OMNITRACE_THROW("unsupported perf type");
}
};
if(_pe.type == PERF_TYPE_SOFTWARE &&
(_pe.config == PERF_COUNT_SW_CPU_CLOCK || _pe.config == PERF_COUNT_SW_TASK_CLOCK))
{
_pe.sample_period = static_cast<uint64_t>(_period);
}
else
{
_pe.sample_period = static_cast<uint64_t>(_freq);
}
}
} // namespace perf
} // namespace omnitrace