Introduce AbstractFiber as superclass of all scheduled control flows

See merge request !325

It is safe to perform a relaxed load in isRunnable(), since the
information is potentially outdated immediately after it was looked
at.

Also, since Fiber::isRunnable() is a virtual method, keeping its
definition in the header has no real advantage, hence we move it out
of the header.

[io/Stats] don't try to print worker stats when using a single uring

See merge request !324

add io latency evaluation

See merge request !323

* increase iterations to 10K this produced more stable averages
* add options to dump all measurements
* add baseline benchmark using two threads and read/write syscalls
* add iouring benchmark using two threads and iouring to read

Test more Fiber functionality in Future callbacks: blocking and spawning.

It uses a watch thread writing to eventfd and a ReadFuture with a
Callback to measure the latency between writing to the eventfd and
executing the resulting IO Continuation.

The worker submitting the read request starts a busy loop after the
submission to enforce that the IO-continuation is delayed on this
worker.

[CI] Move iwyu and clang-tidy out of the smoke-test stage

See merge request !322

[CI] Bump container image to 1.20

See merge request !321

Various improvements

See merge request !320

[Runtime] Set a name for every worker thread

See merge request !319

[Context] Fix DBG message

See merge request !318

The thread local currentContext was already set to nullptr when we
logged it. Use the right field instead.

[meson] add option to ignore wakeup hints

See merge request !316

I think wakeup hints should never be ignored but having the option
seams usefull to observe their benefits/cost.

[Runtime] Move EMPER_* environment variable handling into module

See merge request !314

[ScheduleOnTest] block worker thread if IO is not available

See merge request !315

That debug statement is noisy, as it is emitted all the time,
irregardless whether or not the environment variable is set.

Also add a DBG message that is emitted if such a EMPER_* environment
variable has been processed.

The alpha fiber waits to ensure the worker threads are suspended before
starting to schedule work on specific threads.
emper::sleep uses an AlarmFuture and thus needs emper to be build with IO
support. If IO is not available we now just block the whole worker thread.

[Coordinator] allow listen socket port reuse

See merge request !312

[Context] Move switchToOriginalStack() into module and add DBG statement

See merge request !313

This function is not performance critical and hence can be moved out
of the header into the compilation unit.

fix Future::cancel with new Scheduler::scheduleOn(fiber, workerId)

Closes #31

See merge request !296

LinuxVersion used the assumption that both strings have the same
amount of dot-separated components.
But this is obviously not always the case.
If we can't compare the two strings further they must been equal so far.

* sleeping workers have decremented the semaphore count before sleeping.
  But if they are notified specifically the semaphore counter is
  decremented excessively
  This results in unnecessary suspension/notifications because the
  counter is out of sync with the actual waiter count.
* waitv expects that the futex size is specified in the futex flags
* wake sleepers using FUTEX_PRIVATE_FLAG
* futex_waitv returns the index of the woken futex -> wake on ret > -1
* add debug output and asserts

A getter not calling sem.wait is needed so we don't call sem.wait twice:
once during Future::cancel() and Future::wait() to obtain the return
value afterwards.

Our only cancellation test case where it is possible that the cancellation
must happen on a specific worker uses a single fiber.
The introduced massCancelOnDifferentWorker() test case uses
workerCount * 5 fibers and actively tries to provoke cancellation on
other workers.

Remember the IoContext where a Future was prepared and submit
the CancelWrapper on the correct Worker using scheduleOn.