This further split up the stats machinery into smaller parts.

This required to break an include cycle between Fibril and
LockedQueue.

Thanks to Nicolas Pfeiffer for writing the initial prototypical
implementation of continuation stealing and the cactus stack
mechanism, on which this is based.

Co-authored-by: Nicolas Pfeiffer <pfeiffer@cs.fau.de>

The SpuriousFutex2Semaphore is able to notify a specific worker
by using two futexes two wait on.

One working like a normal semaphore used for global non specific
notifications via notify() and notify_many().

And a second one per worker which is based on a SleeperState.
To notify a specific worker we change its SleeperState to Notified
and call FUTEX_WAKE if needed.

A "fast check" consists of our smoke tests and the fast static analysis
this ensures that the emper variants even build successfully and
are not totally broken.

Waitfree work stealing is configured with the meson option
'waitfree_work_stealing'.

The retry logic is intentionally left in the Queues and not lifted to
the scheduler to reuse the load of an unsuccessful CAS.

Consider the following pseudo code examples:

steal() -> bool:                       steal() -> res
  load                                   load
loop:                                    if empty return EMPTY
  if empty return EMPTY                  cas
  cas                                    return cas ? STOLEN : LOST_RACE
  if not WAITFREE and not cas:
    goto loop                          outer():
  return cas ? STOLEN : LOST_RACE      loop:
                                         res = steal()
outer():                                 if not WAITFREE and res == LOST_RACE:
  steal()                                  goto loop

In the right example the value loaded by a possible unsuccessful CAS
can not be reused. And a loop of unsuccessful CAS' will result in
double loads.

The retries are configurable through a template variable maxRetries.
* maxRetries < 0: indefinitely retries
* maxRetries >= 0: maxRetries

The lockless algorithm can now be configured by setting -Dio_lockless_cq=true
and the used memory ordering by setting -Dio_lockless_memory_order={weak,strong}.

io_lockless_memory_order=weak:
    read with acquire
    write with release

io_lockless_memory_order=strong:
    read with seq_cst
    write with seq_cst

TODO: think about stats and possible ring buffer pointers overflow and ABA.

IO stealing is analog to work-stealing and means that worker thread
without work will try to steal IO completions (CQEs) from other worker's
IoContexts. The work stealing algorithm is modified to check a victims
CQ after findig their work queue empty.

This approach in combination with future additions (global notifications
on IO completions, and lock free CQE consumption) are a realistic candidate
to replace the completer thread without loosing its benefits.

To allow IO stealing the CQ must be synchronized which is already the
case with the IoContext::cq_lock.
Currently stealing workers always try to pop a single CQE (this could
be configurable).
Steal attempts are recorded in the IoContext's Stats object and
successfully stolen IO continuations in the AbstractWorkStealingWorkerStats.

I moved the code transforming CQEs into continuation Fibers from
reapCompletions into a seperate function to make the rather complicated
function more readable and thus easier to understand.

Remove the default CallerEnvironment template arguments to make
the code more explicit and prevent easy errors (not propagating
the caller environment or forgetting the function takes a caller environment).

io::Stats now need to use atomics because multiple thread may increment
them in parallel from EMPER and the OWNER.
And since using std::atomic<T*> in std::map is not easily possible we
use the compiler __atomic_* builtins.

Add, adjust and fix some comments.

The throttle algorithm had the same problem like our sleep algorithms
where notifications from anywhere may race with a worker going to
sleep resulting in lost wakeups.
In the sleep strategy we prevent those races by preventing sleep attempts
when notifing from anywhere.
The throttle algorithm also does now exactly this. A notifier from anywhere
will now always set the WakeupStrategy state to notified.
If the state was previously pending this new approach does not differ from
the previous behavior and a sleeping worker will be notified.
If the state was waking the waking worker skips its sleep if it observes
the WakeupStrategy state as notified.

std::localtime takes a global lock and is therefore not scalable and
inapplicable for analyzing timing sensible bugs.
Introduce a new option to add UTC timestamps. This allows on my system
to double the CPU load while using mmapped logging.

Also increase the LogBuffer size from 1MB to 1GB because I had some
crashes where a renewed buffer was still used.

* single io_uring
* pipe sleep strategy
* pipe sleep strategy without completer