Rework sampling and colorized logs (#140)
## Overview
This is a significant PR which has 3 very notable characteristics:
1. Omnitrace colorizes most of it's logging
2. Completely reworked the sampling
- Samples now record the current instruction pointers instead of strings
- This _dramatically_ decreases the overhead of taking a sample
- The collection of metrics during a sample are split out into another component, enabling that data collection to be disabled -- which decreases the sampling overhead even further
- When both `OMNITRACE_SAMPLING_CPUTIME` and `OMNITRACE_SAMPLING_REALTIME` are ON:
- `OMNITRACE_SAMPLING_CPUTIME_FREQ` and `OMNITRACE_SAMPLING_REALTIME_FREQ` can be used to individually control the sampling frequency
- `OMNITRACE_SAMPLING_CPUTIME_DELAY` and `OMNITRACE_SAMPLING_REALTIME_DELAY` can be used to individually control the delay time before starting
- Now, omnitrace does not start a real-time sampler on the main thread unless `OMNITRACE_SAMPLING_REALTIME` is ON
- In the future, an `OMNITRACE_SAMPLING_TIDS` (and real-time, cpu-time variants) configuration variable(s) will allow you to select which threads will be sampled
3. Files produced by `omnitrace` exe -- `available-instr.txt`, `instrumented-instr.txt`, etc. -- now no longer has `-instr` suffix and are placed in `instrumentation/` subfolder, i.e. `available-instr.txt` -> instrumentation/available.txt`
- This helped de-clutter the output folder
Most of the other edits were reorganization (e.g. internal namespace changes), cleanup, and splitting up functionality.
## Bug Fixes
There is a bug fix with respect to the HSA callbacks which disabled sampling on child threads when an HSA API call was made
## Details
- created thread_info struct for mapping different thread IDs
- reorganized file structure significantly
- added categories.hpp, concepts.hpp
- moved around name trait definitions
- moved all omnitrace components into `omnitrace::component` namespace
- there was a lot of inconsistency b/t using `tim::component` in some places and `omnitrace::component`
- added macros like OMNITRACE_DECLARE_COMPONENT in lieu of TIMEMORY_DECLARE_COMPONENT
- OMNITRACE_CRITICAL_TRACE_NUM_THREADS -> OMNITRACE_THREAD_POOL_SIZE
- roctracer and critical_trace use same thread pool
- critical_trace functions do not lock anymore bc of thread-local TaskGroup
- added `component::local_category_region` to support using `component::category_region` without explicitly passing in name
- removed `component::omnitrace` (unused)
- migrated KokkosP and OMPT to use `component::local_category_region`
- removed `component::user_region` as a result
- migrated omnitrace_{push,pop}_{trace,region}_hidden to use component::category_region
- removed `component::functors` as a result
- migrated some ppdefs
- `api::omnitrace` -> `project::omnitrace`
- `api::(...)` -> `category::(...)`
- improved recording the execution time of threads
- migrated this functionality out of pthread_create_gotcha and into thread_info
- moved mpi_gotcha, fork_gotcha, exit_gotcha, rcclp into omnitrace::component namespace
- split backtrace up into backtrace, backtrace_metrics, backtrace_timestamp components
- sampling.cpp handles setup and post-processing that was formerly in backtrace
- updated logging to use colors
- `OMNITRACE_COLORIZED_LOG` config variable
- updated docs on JSON output from timemory
- instrumentation info in instrumentation subfolder
- added testing for KokkosP entries
- added testing for ompt entries
- add_critical_trace function defined in critical_trace.hpp
- disable push_thread_state and pop_thread_state when thread state is Disabled or Completed
- add comp::page_rss to main bundle
- thread_data supports std::optional instead of std::unique_ptr
- thread_data supports tim::identity<T> to avoid unique_ptr or optional
- tracing::record_thread_start_time()
- tracing::push_timemory and tracing::pop_timemory are templated on CategoryT
- removed anonymous namespace from omnitrace::utility
- sampling backtrace stores instruction pointers instead of strings
- component::category_region updates
- handle disabled thread state
- handle finalized state
- fewer debug messages
- invoke thread_init()
- invoke thread_init_sampling()
- handle push/pop count based on category
- push/pop count only modified when used
- component::cpu_freq
- components/ensure_storage.hpp
- reworked the pthread_create replacement function
- updated parallel-overhead example to report # of times locked
- OMNITRACE_MAX_UNWIND_DEPTH build option
- update timemory submodule
[ROCm/rocprofiler-systems commit: 808ea7dfa7]
Tento commit je obsažen v:
Jonathan R. Madsen
GitHub
@@ -26,13 +26,19 @@
|
||||
|
||||
#define OMNITRACE_COMMON_LIBRARY_NAME "dl"
|
||||
|
||||
#include "dl.hpp"
|
||||
#include <timemory/log/color.hpp>
|
||||
|
||||
#define OMNITRACE_COMMON_LIBRARY_LOG_START \
|
||||
fprintf(stderr, "%s", ::tim::log::color::info());
|
||||
#define OMNITRACE_COMMON_LIBRARY_LOG_END fprintf(stderr, "%s", ::tim::log::color::end());
|
||||
|
||||
#include "common/defines.h"
|
||||
#include "common/delimit.hpp"
|
||||
#include "common/environment.hpp"
|
||||
#include "common/invoke.hpp"
|
||||
#include "common/join.hpp"
|
||||
#include "common/setup.hpp"
|
||||
#include "dl.hpp"
|
||||
|
||||
#include <cassert>
|
||||
#include <gnu/libc-version.h>
|
||||
@@ -45,13 +51,17 @@
|
||||
*(void**) (&VARNAME) = dlsym(HANDLE, FUNCNAME); \
|
||||
if(VARNAME == nullptr && _omnitrace_dl_verbose >= _warn_verbose) \
|
||||
{ \
|
||||
OMNITRACE_COMMON_LIBRARY_LOG_START \
|
||||
fprintf(stderr, "[omnitrace][dl][pid=%i]> %s :: %s\n", getpid(), FUNCNAME, \
|
||||
dlerror()); \
|
||||
OMNITRACE_COMMON_LIBRARY_LOG_END \
|
||||
} \
|
||||
else if(_omnitrace_dl_verbose > _info_verbose) \
|
||||
{ \
|
||||
OMNITRACE_COMMON_LIBRARY_LOG_START \
|
||||
fprintf(stderr, "[omnitrace][dl][pid=%i]> %s :: success\n", getpid(), \
|
||||
FUNCNAME); \
|
||||
OMNITRACE_COMMON_LIBRARY_LOG_END \
|
||||
} \
|
||||
}
|
||||
|
||||
@@ -146,12 +156,14 @@ struct OMNITRACE_HIDDEN_API indirect
|
||||
{
|
||||
if(_omnitrace_dl_verbose >= 1)
|
||||
{
|
||||
OMNITRACE_COMMON_LIBRARY_LOG_START
|
||||
fprintf(stderr, "[omnitrace][dl][pid=%i] %s resolved to '%s'\n", getpid(),
|
||||
::basename(_omnilib.c_str()), m_omnilib.c_str());
|
||||
fprintf(stderr, "[omnitrace][dl][pid=%i] %s resolved to '%s'\n", getpid(),
|
||||
::basename(_dllib.c_str()), m_dllib.c_str());
|
||||
fprintf(stderr, "[omnitrace][dl][pid=%i] %s resolved to '%s'\n", getpid(),
|
||||
::basename(_userlib.c_str()), m_userlib.c_str());
|
||||
OMNITRACE_COMMON_LIBRARY_LOG_END
|
||||
}
|
||||
|
||||
auto _search_paths = common::join(':', common::path::dirname(_omnilib),
|
||||
@@ -173,8 +185,10 @@ struct OMNITRACE_HIDDEN_API indirect
|
||||
{
|
||||
if(_omnitrace_dl_verbose >= 2)
|
||||
{
|
||||
OMNITRACE_COMMON_LIBRARY_LOG_START
|
||||
fprintf(stderr, "[omnitrace][dl][pid=%i] dlopen(\"%s\", %s) :: success\n",
|
||||
getpid(), _lib.c_str(), _omnitrace_dl_dlopen_descr);
|
||||
OMNITRACE_COMMON_LIBRARY_LOG_END
|
||||
}
|
||||
}
|
||||
else
|
||||
@@ -182,8 +196,10 @@ struct OMNITRACE_HIDDEN_API indirect
|
||||
if(_omnitrace_dl_verbose >= 0)
|
||||
{
|
||||
perror("dlopen");
|
||||
OMNITRACE_COMMON_LIBRARY_LOG_START
|
||||
fprintf(stderr, "[omnitrace][dl][pid=%i] dlopen(\"%s\", %s) :: %s\n",
|
||||
getpid(), _lib.c_str(), _omnitrace_dl_dlopen_descr, dlerror());
|
||||
OMNITRACE_COMMON_LIBRARY_LOG_END
|
||||
}
|
||||
}
|
||||
|
||||
@@ -451,7 +467,9 @@ bool _omnitrace_dl_fini = (std::atexit([]() {
|
||||
if(::omnitrace::dl::_omnitrace_dl_verbose >= LEVEL) \
|
||||
{ \
|
||||
fflush(stderr); \
|
||||
OMNITRACE_COMMON_LIBRARY_LOG_START \
|
||||
fprintf(stderr, "[omnitrace][" OMNITRACE_COMMON_LIBRARY_NAME "] " __VA_ARGS__); \
|
||||
OMNITRACE_COMMON_LIBRARY_LOG_END \
|
||||
fflush(stderr); \
|
||||
}
|
||||
|
||||
|
||||
Odkázat v novém úkolu
Zablokovat Uživatele