\makeglossaries

% ----------------------------------
% Acronyms
\newacronym{api}{API}{Application Programming Interface}
\newacronym{fifo}{FIFO}{First-In, First-Out}
\newacronym{io}{I/O}{Input and Output}
\newacronym{numa}{NUMA}{Non-Uniform Memory Access}
\newacronym{prng}{PRNG}{Pseudo Random Number Generator}
\newacronym{raii}{RAII}{Resource Acquisition Is Initialization}
\newacronym{tls}{TLS}{Thread Local Storage}

% ----------------------------------
% Definitions

\longnewglossaryentry{at}
{name={Thread},text={thread}}
{
A thread is an independent sequential execution path through a program. Each thread is scheduled for execution separately and independently from other threads. Systems offer one or more concrete implementations of this concept, \eg \gls{kthrd}, \gls{job}, task. However, most of the concepts of scheduling are independent of the particular implementations of the thread representation. For this reason, this document uses the term \gls{at} to mean any of these representation that meets the general definition.

\textit{Synonyms : Tasks, Jobs, Blocks.}
}

\longnewglossaryentry{proc}
{name={Processor},text={processor}}
{
Entity that executes a \gls{at}, \ie the resource being scheduled by the scheduler. In kernel-level threading, \ats are kernel threads and \procs are the \glspl{hthrd} on which the kernel threads are scheduled. In user-level threading and thread pools, \procs are kernel threads.

\textit{Synonyms : Server, Worker.}
}

\longnewglossaryentry{rQ}
{name={Ready Queue}, text={ready-queue}}
{
Data structure holding \ats that are ready to \glslink{atrun}{run}. Often a \glsxtrshort{fifo} queue for fairness, but can take many different forms, \eg binary tree and priority queue are also common.
}

\longnewglossaryentry{uthrding}
{name={User-Level Threading},text={user-level threading}}
{
Threading model where a scheduler runs in users space and maps threads managed and created inside the user-space onto \glspl{kthrd}.

\textit{Synonyms : User threads, Lightweight threads, Green threads, Virtual threads, Tasks.}
}

\longnewglossaryentry{rmr}
{name={Remote Memory Reference},text={remote memory reference}}
{
A memory reference to an address not in the current \gls{hthrd}'s cache is a remote reference. Memory references that \emph{are} in the current \gls{hthrd}'s cache is a \newterm{local} memory reference. For example, a cache line that must be updated from the any cache on another socket, or from RAM in a \glsxtrshort{numa} context.
}

% ----------------------------------

\longnewglossaryentry{hthrd}
{name={Hardware Threading},text={hardware thread}}
{
Threads representing the underlying hardware, \eg a CPU core or hyper-thread, if the hardware supports multiple threads of execution per core. The number of hardware threads present is fixed on any given computer.

\textit{Synonyms : Core, Hyper-Thread, Processing Unit, CPU.}
}

\longnewglossaryentry{kthrd}
{name={Kernel-Level Thread},text={kernel-level thread}}
{
Threads created and managed inside kernel space. Each kernel thread has its own stack and its own thread of execution. Kernel-level threads are owned, managed and scheduled by the underlying operating system.

\textit{Synonyms : OS threads, Hardware threads, Physical threads.}
}

\longnewglossaryentry{fiber}
{name={Fiber},text={fiber}}
{
Fibers are non-preemptive user-level threads. They share most of the characteristics of user-level threads except that they cannot be preempted by another fiber.

\textit{Synonyms : Tasks.}
}

\longnewglossaryentry{job}
{name={Job},text={job}}
{
Unit of work, often sent to a thread pool or worker pool to be executed. Has neither its own stack nor its own thread of execution.

\textit{Synonyms : Tasks.}
}

\longnewglossaryentry{pool}
{name={Thread Pool},text={thread-pool}}
{
Group of homogeneous threads that loop executing units of works. Often executing \glspl{jobs}.

\textit{Synonyms : Executor.}
}

\longnewglossaryentry{preemption}
{name={Preemption},text={preemption}}
{
Involuntary context switch imposed on threads at a given rate.

\textit{Synonyms : None.}
}

\longnewglossaryentry{atsched}
{name={Scheduling a \gls{at}}}
{
Scheduling a \at refers to notifying the scheduler that a \at is ready to run. When representing the scheduler as a queue of \ats, scheduling is the act of pushing a \at onto the end of the queue. This operation does not necessarily mean the \at is guaranteed CPU time (\gls{atrun}), \eg if the program terminates abruptly, scheduled \glspl{at} never run.

\textit{Synonyms : Unparking.}
}

\longnewglossaryentry{atrun}
{name={Running a \gls{at}}}
{
Running a \at refers to allocating CPU time to a \at that is ready to run. When representing the scheduler as a queue of \ats, running is the act of popping a \at from the front of the queue and putting it onto a \gls{proc}. The \gls{at} can then accomplish some or all of the work it is programmed to do.

\textit{Synonyms : None.}
}

\longnewglossaryentry{atmig}
{name={\Glspl{at} Migration}}
{
Migration refers to the idea of an \gls{at} running on a different \proc than the last time it was run. It is generally preferable to minimize migration as it incurs cost but any load balancing among \proc requires some amount of migration.

\textit{Synonyms : None.}
}

\longnewglossaryentry{atpass}
{name={Overtaking \gls{at}}}
{
When representing the scheduler as a queue of \glspl{at}, overtaking is the act breaking the FIFO-ness of the queue by moving a \gls{at} in front of some other \gls{at} when it arrived after. This remains true for schedulers that do not use a FIFO queue, when the order in which the \glspl{at} are \glslink{atsched}{scheduled} and \glslink{atrun}{run} in a different order. A \gls{at} is said to \emph{overtake} another if it is run \emph{before} but was \emph{scheduled} after the other \gls{at}.

\textit{Synonyms : None.}
}

\longnewglossaryentry{atblock}
{name={\Gls{at} Blocking}}
{
\Gls{at} blocking means taking a running \at off a CPU. Unless no other \at is ready, this action is immediately followed by running another \at.

\textit{Synonyms : Parking.}
}

\longnewglossaryentry{atcomplet}
{name={Running to completion}}
{
Running to completion refers to the entire sequence of : being scheduled, running and blocking, for a given \at.

See also \gls{atsched}, \gls{atrun}, \gls{atblock}

\textit{Synonyms : None.}
}

\longnewglossaryentry{load}
{name={System Load},text={load}}
{
The system load refers to the rate at which \glspl{at} are \glslink{atsched}{scheduled} versus the rate at which they are \glslink{atrun}{run}. When \glspl{at} are being scheduled faster than they are run, the system is considered \emph{overloaded}. When \glspl{at} are being run faster than they are scheduled, the system is considered \emph{underloaded}. Correspondingly, if both rates are equal, the system is considered \emph{loaded}. Note the system is considered loaded only if the rate at which \glspl{at} are scheduled/run is non-zero, otherwise the system is empty, \ie it has no load.

\textit{Synonyms : CPU Load, System Load.}
}