signalling a condvar from inside vs. signalling a condvar von outside

#include <iostream>
#include <thread>
#include <mutex>
#include <condition_variable>
#include <sys/resource.h>
using namespace std;
int main()
{
struct synch_t
{
mutex mtx;
bool signalled = false;
condition_variable cv;
};
atomic_long nVoluntary;
auto thr = [&]( synch_t &me, synch_t &you, auto &&toYou )
{
for( size_t r = 10'000; r; --r )
{
unique_lock lockMe( me.mtx );
me.cv.wait( lockMe, [&] { return me.signalled; } );
me.signalled = false;
lockMe.unlock();
toYou( you );
}
rusage ru;
getrusage( RUSAGE_THREAD, &ru );
nVoluntary.fetch_add( ru.ru_nvcsw );
};
auto doIt = [&]( char const *what, auto &&toYou )
{
synch_t synchA { {}, true, {} }, synchB;
nVoluntary.store( 0, memory_order_relaxed );
jthread
thrA( [&]() { thr( synchA, synchB, move( toYou ) ); } ),
thrB( [&]() { thr( synchB, synchA, move( toYou ) ); } );
thrA.join();
thrB.join();
cout << what << nVoluntary.load( memory_order_relaxed ) << endl;
};
doIt( "inside: ", []( synch_t &synch )
{
lock_guard lock( synch.mtx );
synch.signalled = true;
synch.cv.notify_one();
} );
doIt( "outside: ", []( synch_t &synch )
{
unique_lock lock( synch.mtx );
synch.signalled = true;
lock.unlock();
synch.cv.notify_one();
} );
}
It nearly doesn't matter in terms of numbers of context switches if
you  signal a condvar from inside our outside. The above program run
on a Zen4-CPU with WSL2:
inside: 20130
outside: 19811
On a 28 core Skylake-CPU with Ubuntu:
inside: 19997
outside: 19888