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

source/lib/omnitrace/library/ptl.cpp

@@ -26,6 +26,8 @@
 #include "library/defines.hpp"
 #include "library/runtime.hpp"
 #include "library/sampling.hpp"
+#include "library/thread_data.hpp"
+#include "library/thread_info.hpp"
 
 #include <PTL/ThreadPool.hh>
 
@@ -39,25 +41,60 @@ namespace tasking
 namespace
 {
 auto _thread_pool_cfg = []() {
+    int64_t _nthreads = 0;
+    if(config::settings_are_configured())
+    {
+        _nthreads = config::get_thread_pool_size();
+    }
+    else
+    {
+        const int64_t _max_threads = std::thread::hardware_concurrency() / 2;
+        const int64_t _min_threads = 1;
+
+        _nthreads = get_env<int64_t>("OMNITRACE_THREAD_POOL_SIZE", -1, false);
+        if(_nthreads == -1)
+        {
+            _nthreads = 4;
+            if(_nthreads > _max_threads) _nthreads = _max_threads;
+            if(_nthreads < _min_threads) _nthreads = _min_threads;
+
+            tim::set_env("OMNITRACE_THREAD_POOL_SIZE", _nthreads, 0);
+        }
+    }
+
     PTL::ThreadPool::Config _v{};
     _v.init         = true;
     _v.use_affinity = false;
     _v.use_tbb      = false;
     _v.verbose      = -1;
     _v.initializer  = []() {
-        threading::offset_this_id(true);
-        set_thread_state(ThreadState::Internal);
-        sampling::block_signals();
+        thread_info::init(true);
         threading::set_thread_name(
             JOIN('.', "ptl", PTL::Threading::GetThreadId()).c_str());
+        sampling::block_signals();
     };
     _v.finalizer = []() {};
     _v.priority  = 5;
-    _v.pool_size = 1;
+    _v.pool_size = _nthreads;
+    return _v;
+};
+
+auto&
+get_thread_pool_state()
+{
+    static auto _v = State::PreInit;
     return _v;
-}();
 }
 
+PTL::ThreadPool&
+get_thread_pool()
+{
+    static auto _v =
+        (get_thread_pool_state() = State::Active, PTL::ThreadPool{ _thread_pool_cfg() });
+    return _v;
+}
+}  // namespace
+
 namespace roctracer
 {
 namespace
@@ -94,13 +131,15 @@ join()
     if(roctracer::get_thread_pool_state() == State::Active)
     {
         OMNITRACE_DEBUG_F("waiting for all roctracer tasks to complete...\n");
-        tasking::roctracer::get_task_group().join();
+        for(size_t i = 0; i < max_supported_threads; ++i)
+            roctracer::get_task_group(i).join();
     }
 
     if(critical_trace::get_thread_pool_state() == State::Active)
     {
         OMNITRACE_DEBUG_F("waiting for all critical tasks to complete...\n");
-        tasking::critical_trace::get_task_group().join();
+        for(size_t i = 0; i < max_supported_threads; ++i)
+            critical_trace::get_task_group(i).join();
     }
 }
 
@@ -109,70 +148,62 @@ shutdown()
 {
     if(roctracer::get_thread_pool_state() == State::Active)
     {
-        OMNITRACE_DEBUG_F("Destroying the roctracer thread pool...\n");
-        std::unique_lock<std::mutex> _lk{ roctracer::get_mutex() };
-        roctracer::get_task_group().join();
-        roctracer::get_task_group().clear();
-        roctracer::get_task_group().set_pool(nullptr);
-        roctracer::get_thread_pool().destroy_threadpool();
+        OMNITRACE_DEBUG_F("Waiting on completion of roctracer tasks...\n");
+        for(size_t i = 0; i < max_supported_threads; ++i)
+        {
+            roctracer::get_task_group(i).join();
+            roctracer::get_task_group(i).clear();
+            roctracer::get_task_group(i).set_pool(nullptr);
+        }
         roctracer::get_thread_pool_state() = State::Finalized;
     }
 
     if(critical_trace::get_thread_pool_state() == State::Active)
     {
-        OMNITRACE_DEBUG_F("Destroying the critical trace thread pool...\n");
-        std::unique_lock<std::mutex> _lk{ critical_trace::get_mutex() };
-        critical_trace::get_task_group().join();
-        critical_trace::get_task_group().clear();
-        critical_trace::get_task_group().set_pool(nullptr);
-        critical_trace::get_thread_pool().destroy_threadpool();
+        OMNITRACE_DEBUG_F("Waiting on completion of critical trace tasks...\n");
+        for(size_t i = 0; i < max_supported_threads; ++i)
+        {
+            critical_trace::get_task_group(i).join();
+            critical_trace::get_task_group(i).clear();
+            critical_trace::get_task_group(i).set_pool(nullptr);
+        }
         critical_trace::get_thread_pool_state() = State::Finalized;
     }
+
+    if(get_thread_pool_state() == State::Active)
+    {
+        OMNITRACE_DEBUG_F("Destroying the omnitrace thread pool...\n");
+        get_thread_pool().destroy_threadpool();
+        get_thread_pool_state() = State::Finalized;
+    }
 }
 
-std::mutex&
-roctracer::get_mutex()
+size_t
+initialize_threadpool(size_t _v)
 {
-    static std::mutex _v{};
-    return _v;
-}
-
-PTL::ThreadPool&
-roctracer::get_thread_pool()
-{
-    static auto _v = (roctracer::get_thread_pool_state() = State::Active,
-                      PTL::ThreadPool{ _thread_pool_cfg });
-    return _v;
+    return get_thread_pool().initialize_threadpool(_v);
 }
 
 PTL::TaskGroup<void>&
-roctracer::get_task_group()
+roctracer::get_task_group(int64_t _tid)
 {
-    static PTL::TaskGroup<void> _v{ &roctracer::get_thread_pool() };
-    return _v;
-}
-
-std::mutex&
-critical_trace::get_mutex()
-{
-    static std::mutex _v{};
-    return _v;
-}
-
-PTL::ThreadPool&
-critical_trace::get_thread_pool()
-{
-    static auto _v = (critical_trace::get_thread_pool_state() = State::Active,
-                      PTL::ThreadPool{ _thread_pool_cfg });
-    return _v;
+    struct local
+    {};
+    using thread_data_t = thread_data<PTL::TaskGroup<void>, local>;
+    static auto& _v =
+        thread_data_t::instances(construct_on_init{}, &tasking::get_thread_pool());
+    return *_v.at(_tid);
 }
 
 PTL::TaskGroup<void>&
-critical_trace::get_task_group()
+critical_trace::get_task_group(int64_t _tid)
 {
-    static PTL::TaskGroup<void> _v{ &critical_trace::get_thread_pool() };
-    return _v;
+    struct local
+    {};
+    using thread_data_t = thread_data<PTL::TaskGroup<void>, local>;
+    static auto& _v =
+        thread_data_t::instances(construct_on_init{}, &tasking::get_thread_pool());
+    return *_v.at(_tid);
 }
-
 }  // namespace tasking
 }  // namespace omnitrace