Files
rocm-systems/source/lib/omnitrace/library/cpu_freq.cpp
T
Jonathan R. Madsen 9618ddefba Causal profiling (#229)
* Addition of basic structure

* Reworked categories

* More causal integration additions

* Causal implementation

* Update examples

* delete virtual_speedup files

* Update perfetto submodule to v31.0

* Update dyninst submodule

* Update timemory submodule

* ElfUtils build for libdw

* OMNITRACE_LIKELY and OMNITRACE_UNLIKELY

* Update common lib join

* Examples updates for causal profiling

* config updates with causal options

- OMNITRACE_CAUSAL_FIXED_LINE
- OMNITRACE_CAUSAL_FIXED_SPEEDUP
- OMNITRACE_CAUSAL_FILE
- OMNITRACE_CAUSAL_BINARY_SCOPE
- OMNITRACE_CAUSAL_SOURCE_SCOPE
- version info in banner
- support increments in parse_numeric_range
- fix occasional deadlock in first call to get_config

* PTL general task group

* Always include PID in debug/verbose messages

* Add blocking/unblocking gotchas to runtime init bundle

* CausalState

* thread_data updates

- generic component_bundle_cache

* Improve handling of causal in category_region

* components updates

- backtrace_causal component
- backtrace::get_data member func
- decrease ignore_depth in backtrace::sample(int)
- handle "omnitrace_main" in backtrace::filter_and_patch(...)
- tweak internal thread state scope for pthread_mutex_gotcha wrappers

* simplify tracing get_instrumentation_bundles usage

* sampling updates

- include backtrace_causal component
- disable backtrace_metrics if using causal and not using perfetto
- disable backtrace and backtrace_timestamp when using causal
- post_process_causal

* causal updates

- more checks in blocking_gotcha and unblocking_gotcha start/stop
- miscellaneous overhaul of data
- experiment update

* Remove virtual speedup

* libomnitrace code_object

* causal-profiling test

* libomnitrace library.cpp updates

- handle causal profiling
- fini_bundle

* Disable causal profiling by default

* Updated causal code and example

- example: three execution variants: cpu + rng, cpu, rng
- example: three instrumentation variants: none, omni, coz
- fix blocking gotcha credit
- rework perform_experiment_impl
- get_eligible_address_ranges
- compute_eligible_lines
- support fixed lines/speedups/functions
- update selected_entry to support function mode
- fix causal::delay
- experiment updates

* omnitrace_progress / omnitrace_user_progress

- with accompanying omnitrace_annotated_progress / omnitrace_user_annotated_progress

* Update timemory submodule

* CausalMode

- mode indicated whether causal predictions source be at line-level or function-level

* code_object, config, runtime, sampling, thread_data

- code_object: address_range
- code_object: basic::line_info serialize(), name(), hash()
- config updates
- two signals for causal sampling
- thread_data init fixes

* pthread updates

- pthread_create_gotcha processes delays
- pthread_mutex_gotcha does not wrap pthread_join in causal mode

* backtrace_causal update

- dynamic delay period stats

* main wrapper uses basename of argv[0]

* update elfio submodule

* perf support (currently unused)

* Fix experiment JSON serialization

- static_vector.hpp (unused)

* causal executable + config options updates

- omnitrace-causal exe simplifies running multiple causal configs
- changed the causal config option names

* Support both throughput and latency points

* process-causal-json.py script

- will be used later for testing

* stable_vector

* Rework thread_data

* Improve omnitrace-causal exe

- better verbosity handling
- correct diagnosis of status for child process
- execvpe when only one iteration (debugging)

* Update timemory submodule

* exe --version

- omnitrace, omnitrace-avail, and omnitrace-sample all support --version on command-line

* OMNITRACE_INTERNAL_API + OMNITRACE_{LIKELY,UNLIKELY}

* omnitrace-causal cmake format

* omnitrace config update

- OMNITRACE_CAUSAL_FILE_CLOBBER

* custom exception

- wraps STL exception and gets stacktrace during construction

* exit_gotcha supports _Exit

* use global construct_on_init + max threads

- add some safety when exceeding max # of threads

* update code_object binary filter

- exclude dyninst and tbbmalloc library

* containers: c_array, static_vector, stable_vector

- moved utility::c_array to container::c_array
- created static_vector: std::vector bound to std::array
- created stable_vector: vector with stable references

* grow thread_data when new thread created

* causal updates

- data: improve compute_eligible_lines to ignore lambdas
- data: use new thread_data
- delay: use new thread_data
- experiment: properly support latency points
- experiment: support file clobber
- experiment: ensure non-zero experiment time
- progress_point: use new thread_data
- backtrace_causal: use new thread_data

* Update causal-profiling tests

* fix omnitrace-causal backslash escaping

* process-causal-json script

* restructure causal implementation

- update verbose messages for omnitrace-causal diagnose_status
- migrated causal implementation in sampling.cpp to causal/sampling.cpp
- OMNITRACE_USE_CAUSAL does not require OMNITRACE_USE_SAMPLING
- added Mode::Causal
- causal sampling uses same signals as regular sampling
- moved tracing::thread_init to implementation file
- combined tracing::thread_init and tracing::thread_init_sampling
- added causal/components folder
- pthread_create_gotcha::wrapper_config
- omnitrace_preload checks OMNITRACE_USE_CAUSAL
  - updates mode accordingly

* update timemory submodule

* update timemory submodule

* causal example updates

- causal for lulesh

* perf code + utility - helpers

- relocated causal perf code
- placement new when generating unique ptr trait for potentially allocating during sampling
- additions to utility header
- removed previously added helpers.hpp

* update timemory submodule

* Default env variables for omnitrace-causal

- activate OMNITRACE_USE_KOKKOSP, etc.

* update stable_vector and static_vector

- static vector can use atomic for size tracking for thread-safe situations

* update causal example header

- CAUSAL_PROGRESS_NAMED
- use CAUSAL_ prefix for some macros

* Tweak lulesh example

- use CAUSAL_PROGRESS instead of CAUSAL_BEGIN and CAUSAL_END

* omnitrace-sample support for causal mode

- set OMNITRACE_USE_SAMPLING to off when OMNITRACE_MODE=causal

* refactor and cleanup code_object

- scope filter
- fixes to address_range

* overhaul causal data + causal config options

- full support for function and line mode
- support static vector of instruction pointers
- improve line info mapping resolution
- remove thread-locality from miscellanous functions where unnecessary
- causal options for {binary,source,function,fileline} exclusion

* causal experiment, sampling, and backtrace updates

- is_selected + unwind address array
- experiment warning about progress points
- increased buffer size for backtrace_casual sampler
- backtrace_causal only stores IP addresses instead of full unwind info

* category_region updates

- minor refactor
- local_category_region::mark

* Update causal tests

* Bump version to 1.8.0

* omnitrace-causal args + CLOBBER -> RESET

- renamed OMNITRACE_CAUSAL_FILE_CLOBBER to OMNITRACE_CAUSAL_FILE_RESET
- updated omnitrace-causal exe to support recently added configuration options
- other miscellaneous tweaks to data.cpp, experiment.cpp, and sampling.cpp

* Refactor causal and code_object

- code_object.hpp and code_object.cpp moved into binary folder
- causal components namespaced into omnitrace::causal::component
- moved sample_data out of backtrace_causal and into own file
- renamed backtrace_causal to causal::component::backtrace

* preload omnitrace_init + OMNITRACE_DEBUG_MARK

- env OMNITRACE_DEBUG_MARK
- fix omnitrace_init call when LD_PRELOAD-ing omnitrace

* Fix fileline support + line-info output names + experiment log

- line-info log files are prefixed with experiment name
- don't print experiment duration when E2E
- account for fileline scope in analysis

* KokkosP: OMNITRACE_KOKKOSP_NAME_LENGTH_MAX

- config option to limit the name of kokkos tool callbacks
- remove [kokkos] from KokkosP names

* Update causal example

- minor tweaks to decrease probability of overlapping regions in binary

* omnitrace-causal update

- prefix N / Ntot in environment printout

* Miscellaneous updates

- causal::finish_experimenting()
- OMNITRACE_CAUSAL_RANDOM_SEED
- KokkosP causal updates
  - exclude some callbacks, make some callbacks unique, etc.
- address_range::operator+=(address_range)
- combine contiguous ranges in binary/analysis.cpp when file, func, line is same and address range is contiguous
- bfd_line_info reads inline info
- wait for perform_experiment_impl to complete
- causal::delay updates
  - delay::process checks if experiment is active
  - uses threading::get_id()
- experiment scales duration up for larger speedup experiments
- line info samples includes excluded lines
- sampler uses CLOCK_REALTIME
- blocking_gotcha updates
  - is no longer fully static
  - adds audit routine which sets the postblock value to zero if try/timed routine fails
- category::host was added to causal_throughput_categories_t
- pthread_create_gotcha sets new threads local parent delay
  - was using internal value, now uses sequent value

* Causal improvements to KokkosP

* Updates to experiment time scaling

- use stats instead of just max

* binary/link_map.{hpp,cpp}

* update process-causal-json.py

* Folded fileline scope into source scope

* Update documentation

- Add documentation for causal profiling
- Replace 'Omnitrace' with 'OmniTrace' everywhere

* Update causal-helpers.cmake + omnitrace-testing.cmake

- split tests/CMakeLists.txt partially into omnitrace-testing.cmake

* omnitrace/causal.h

- OMNITRACE_CAUSAL_PROGRESS
- OMNITRACE_CAUSAL_PROGRESS_NAMED
- OMNITRACE_CAUSAL_BEGIN
- OMNITRACE_CAUSAL_END

* selected_entry + remove default filters for lambdas and operator()

- selected entry stores range and binary load address

* update process-causal-json.py

* format examples/lulesh/CMakeLists.txt

* causal-helpers find_package(Threads)

* OMNITRACE_KOKKOSP_KERNEL_LOGGER

- was OMNITRACE_KOKKOS_KERNEL_LOGGER

* quiet find of coz-profiler

* Fix rocm_smi exception handling

* Update timemory submodule (binutils)

- fix binutls compile error on some systems
- bump binutils to v2.40

* Fix miscellaneous tests

* OMNITRACE_KOKKOSP_PREFIX

* revert rocm_smi handling

* ElfUtils updates

- default to download version 0.188
- add -Wno-error=null-dereference due to GCC 12 compiler error

* Update causal example

* Remove OMNITRACE_VERBOSE from global workflow envs

* Reliable causal test

* disable compilation of causal perf files

* Remove set_current_selection with unwind stack

* update timemory submodule

* fix for segfault on bionic

- locking in TLS dtor was causing segfault

* remove experiment::is_selected(unwind_stack_t)

* update default init of selected_entry

* Fix for when IP is not offset by load address

* Update CMakeLists.txt

* Miscellaneous updates

- OMNITRACE_WARNING_OR_CI_THROW
- OMNITRACE_REQUIRE
- OMNITRACE_PREFER
- fixed issues with no ASLR
-  added load address variable and ipaddr() func to basic/bfd line info
- removed get_basic() from dwarf_line_info
- TIMEMORY_PREFER -> OMNITRACE_PREFER
- removed previously added binary_address and range variables from selected_entry

* Removed superfluous CausalState

* Additional causal tests (lulesh + kokkos)

* filter, prefer, analysis ASLR handling

- removed default filter on cold functions
- fixed OMNITRACE_PREFER
- fixed analysis ASLR handling

* Tweak line-info output

* Removed some superfluous code

- causal/delay
- causal/selected_entry

* Exclude main.cold in function mode

* Update validate-perfetto-proto.py

- account for occasional http errors

* Add sampling test disabling tmp files

* argparser for process-causal-json

- support validation
- support filtering

* Avoid pthread_{lock,unlock} in sampling offload

- use homemade atomic_mutex/atomic_lock since contention will be low and using pthread tools might trigger our wrappers

* Rename process-causal-json.py

- validate-causal-json.py

* rework omnitrace_add_causal_test

- capable of performing validation
- added validation tests

* Fix kokkosp_begin_deep_copy + causal

* Tweak address range in bfd_line_info::read_pc

* Tweak analysis and data IP handling

- look for gaps

* Disable scaling experiment time by speedup

* Revert change in max threads during CI

* binary updates

- significant overhaul of binary analysis implementation
- removed "basic_line_info" and "bfd_line_info" in lieu of "symbol" class
  - symbol class has basic BFD info + vector of inlines + vector of dwarf info

* Updated causal to use new binary analysis

- Fix symbol.cpp includes

* Updated formatting target

- include *.cmake files

* Updated causal tests

- causal tests should be stable now

* Update timemory and dyninst submodules

- TPLs are stripped + built w/o debug info

* Increase tolerance for causal validation speedups

- higher speedups have more variance (increased to +/- 5 from 3)

* Support causal output for MPI

- i.e. tag with MPI rank

* omnitrace-causal launcher argument

* improve experiment sampling output

* causal data updates

- call compute lines once
- fixed filtered cached binary info
- debugging info when experiment fails to start

* Tweaked causal validation tests

* dwarf_entry ranges

* CI updates

- increase max threads to 64

* Tweak causal E2E validation tests

- more threads
- shorter thread runtime
- more iterations

* Fix shadowed variable

* fix symbol read_bfd last PC calculation

* fix maybe-uninitialized warning

* omnitrace-causal launcher update

- only inject "omnitrace-causal --" once
- throw error if no matches found

* Update causal profiling docs for launcher

* fix address range boundaries
2023-01-24 18:53:23 -06:00

255 lines
9.0 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/cpu_freq.hpp"
#include "library/common.hpp"
#include "library/components/cpu_freq.hpp"
#include "library/components/fwd.hpp"
#include "library/config.hpp"
#include "library/debug.hpp"
#include "library/defines.hpp"
#include "library/perfetto.hpp"
#include "library/thread_data.hpp"
#include "library/thread_info.hpp"
#include "library/timemory.hpp"
#include <timemory/components/rusage/backends.hpp>
#include <timemory/mpl/types.hpp>
#include <timemory/units.hpp>
#include <timemory/utility/procfs/cpuinfo.hpp>
#include <timemory/utility/type_list.hpp>
#include <cstddef>
#include <cstdlib>
#include <string>
#include <sys/resource.h>
#include <tuple>
#include <utility>
#include <vector>
namespace omnitrace
{
namespace cpu_freq
{
template <typename... Tp>
using type_list = tim::type_list<Tp...>;
namespace
{
using cpu_data_tuple_t = std::tuple<size_t, int64_t, int64_t, int64_t, int64_t, int64_t,
int64_t, int64_t, component::cpu_freq>;
std::deque<cpu_data_tuple_t> data = {};
template <typename... Types>
void init_perfetto_counter_tracks(type_list<Types...>)
{
(perfetto_counter_track<Types>::init(), ...);
}
} // namespace
} // namespace cpu_freq
} // namespace omnitrace
namespace omnitrace
{
namespace cpu_freq
{
void
setup()
{
init_perfetto_counter_tracks(
type_list<category::cpu_freq, category::process_page, category::process_virt,
category::process_peak, category::process_context_switch,
category::process_page_fault, category::process_user_mode_time,
category::process_kernel_mode_time>{});
}
void
config()
{
component::cpu_freq::configure();
}
void
sample()
{
auto _ts = tim::get_clock_real_now<size_t, std::nano>();
auto _rcache = tim::rusage_cache{ RUSAGE_SELF };
auto _freqs = component::cpu_freq{}.sample();
// user and kernel mode times are in microseconds
data.emplace_back(
_ts, tim::get_page_rss(), tim::get_virt_mem(), _rcache.get_peak_rss(),
_rcache.get_num_priority_context_switch() +
_rcache.get_num_voluntary_context_switch(),
_rcache.get_num_major_page_faults() + _rcache.get_num_minor_page_faults(),
_rcache.get_user_mode_time() * 1000, _rcache.get_kernel_mode_time() * 1000,
std::move(_freqs));
}
void
shutdown()
{}
namespace
{
template <typename... Types, size_t N = sizeof...(Types)>
void
config_perfetto_counter_tracks(type_list<Types...>, std::array<const char*, N> _labels,
std::array<const char*, N> _units)
{
static_assert(sizeof...(Types) == N,
"Error! Number of types != number of labels/units");
auto _config = [&](auto _t) {
using type = std::decay_t<decltype(_t)>;
using track = perfetto_counter_track<type>;
constexpr auto _idx = tim::index_of<type, type_list<Types...>>::value;
if(!track::exists(0))
{
auto addendum = [&](const char* _v) { return JOIN(" ", "CPU", _v, "(S)"); };
track::emplace(0, addendum(_labels.at(_idx)), _units.at(_idx));
}
};
(_config(Types{}), ...);
}
struct index
{
size_t value = 0;
};
template <typename Tp, typename... Args>
void
write_perfetto_counter_track(Args... _args)
{
using track = perfetto_counter_track<Tp>;
TRACE_COUNTER(trait::name<Tp>::value, track::at(0, 0), _args...);
}
template <typename Tp, typename... Args>
void
write_perfetto_counter_track(index&& _idx, Args... _args)
{
using track = perfetto_counter_track<Tp>;
TRACE_COUNTER(trait::name<Tp>::value, track::at(_idx.value, 0), _args...);
}
} // namespace
void
post_process()
{
OMNITRACE_VERBOSE(1,
"Post-processing %zu cpu frequency and memory usage entries...\n",
data.size());
auto _process_frequencies = [](size_t _idx, size_t _offset) {
using freq_track = perfetto_counter_track<category::cpu_freq>;
const auto& _thread_info = thread_info::get(0, InternalTID);
OMNITRACE_CI_THROW(!_thread_info, "Missing thread info for thread 0");
if(!_thread_info) return;
if(!freq_track::exists(_idx))
{
auto addendum = [&](const char* _v) {
return JOIN(" ", "CPU", _v, JOIN("", '[', _idx, ']'), "(S)");
};
freq_track::emplace(_idx, addendum("Frequency"), "MHz");
}
for(auto& itr : data)
{
uint64_t _ts = std::get<0>(itr);
double _freq = std::get<8>(itr).at(_offset);
if(!_thread_info->is_valid_time(_ts)) continue;
write_perfetto_counter_track<category::cpu_freq>(index{ _idx }, _ts, _freq);
}
auto _end_ts = _thread_info->get_stop();
write_perfetto_counter_track<category::cpu_freq>(index{ _idx }, _end_ts, 0);
};
auto _process_cpu_rusage = []() {
config_perfetto_counter_tracks(
type_list<category::process_page, category::process_virt,
category::process_peak, category::process_context_switch,
category::process_page_fault, category::process_user_mode_time,
category::process_kernel_mode_time>{},
{ "Memory Usage", "Virtual Memory Usage", "Peak Memory", "Context Switches",
"Page Faults", "User Time", "Kernel Time" },
{ "MB", "MB", "MB", "", "", "sec", "sec" });
const auto& _thread_info = thread_info::get(0, InternalTID);
OMNITRACE_CI_THROW(!_thread_info, "Missing thread info for thread 0");
if(!_thread_info) return;
for(auto& itr : data)
{
uint64_t _ts = std::get<0>(itr);
if(!_thread_info->is_valid_time(_ts)) continue;
double _page = std::get<1>(itr);
double _virt = std::get<2>(itr);
double _peak = std::get<3>(itr);
uint64_t _cntx = std::get<4>(itr);
uint64_t _flts = std::get<5>(itr);
double _user = std::get<6>(itr);
double _kern = std::get<7>(itr);
write_perfetto_counter_track<category::process_page>(_ts,
_page / units::megabyte);
write_perfetto_counter_track<category::process_virt>(_ts,
_virt / units::megabyte);
write_perfetto_counter_track<category::process_peak>(_ts,
_peak / units::megabyte);
write_perfetto_counter_track<category::process_context_switch>(_ts, _cntx);
write_perfetto_counter_track<category::process_page_fault>(_ts, _flts);
write_perfetto_counter_track<category::process_user_mode_time>(
_ts, _user / units::sec);
write_perfetto_counter_track<category::process_kernel_mode_time>(
_ts, _kern / units::sec);
}
auto _end_ts = _thread_info->get_stop();
write_perfetto_counter_track<category::process_page>(_end_ts, 0.0);
write_perfetto_counter_track<category::process_virt>(_end_ts, 0.0);
write_perfetto_counter_track<category::process_peak>(_end_ts, 0.0);
write_perfetto_counter_track<category::process_context_switch>(_end_ts, 0);
write_perfetto_counter_track<category::process_page_fault>(_end_ts, 0);
write_perfetto_counter_track<category::process_user_mode_time>(_end_ts, 0.0);
write_perfetto_counter_track<category::process_kernel_mode_time>(_end_ts, 0.0);
};
_process_cpu_rusage();
auto& enabled_cpu_freqs = component::cpu_freq::get_enabled_cpus();
for(auto itr = enabled_cpu_freqs.begin(); itr != enabled_cpu_freqs.end(); ++itr)
{
auto _idx = *itr;
auto _offset = std::distance(enabled_cpu_freqs.begin(), itr);
_process_frequencies(_idx, _offset);
}
enabled_cpu_freqs.clear();
}
} // namespace cpu_freq
} // namespace omnitrace