Index: doc/theses/colby_parsons_MMAth/Makefile =================================================================== --- doc/theses/colby_parsons_MMAth/Makefile (revision fa6ca1ac779b46c587efb95ae262f52a9c5378e0) +++ doc/theses/colby_parsons_MMAth/Makefile (revision 34b6a7b6878154693f83696df612a4adeee0fb87) @@ -101,6 +101,6 @@ -${BibTeX} ${Build}/${basename $@} # Some citations reference others so run again to resolve these citations - ${LaTeX} ${basename $@}.tex - -${BibTeX} ${Build}/${basename $@} +# ${LaTeX} ${basename $@}.tex +# -${BibTeX} ${Build}/${basename $@} # Make index from *.aux entries and input index at end of document makeglossaries -q -s ${Build}/${basename $@}.ist ${Build}/${basename $@} @@ -115,36 +115,38 @@ mkdir -p ${Build} -%.tex : %.fig ${Build} - fig2dev -L eepic $< > ${Build}/$@ +# The following rules are currently unused but could be used later +# if we want to swap figures to be .pngs +# %.tex : %.fig ${Build} +# fig2dev -L eepic $< > ${Build}/$@ -%.ps : %.fig | ${Build} - fig2dev -L ps $< > ${Build}/$@ +# %.ps : %.fig | ${Build} +# fig2dev -L ps $< > ${Build}/$@ -%.pstex : %.fig | ${Build} - fig2dev -L pstex $< > ${Build}/$@ - fig2dev -L pstex_t -p ${Build}/$@ $< > ${Build}/$@_t +# %.pstex : %.fig | ${Build} +# fig2dev -L pstex $< > ${Build}/$@ +# fig2dev -L pstex_t -p ${Build}/$@ $< > ${Build}/$@_t -#----------------------------------------------------------------------------------- -# Tools to generate png files -# to create a png we create a pdf and convert it to png -%.png : build/%.pstex figures/%.tex ${Build} - echo ${basename $@} - ${LaTeX} figures/${basename $@}.tex - dvips build/${basename $@}.dvi -o build/${basename $@}.ps - ps2pdf build/${basename $@}.ps - convert -negate ${basename $@}.pdf $@ +# #----------------------------------------------------------------------------------- +# # Tools to generate png files +# # to create a png we create a pdf and convert it to png +# %.png : build/%.pstex figures/%.tex ${Build} +# echo ${basename $@} +# ${LaTeX} figures/${basename $@}.tex +# dvips build/${basename $@}.dvi -o build/${basename $@}.ps +# ps2pdf build/${basename $@}.ps +# convert -negate ${basename $@}.pdf $@ # creating a pdf of a figure requires generating some latex that just includes the figure -figures/%.tex: build/%.pstex ${Build} - echo -n "\documentclass[preview]{standalone}\n" \ - "\usepackage[T1]{fontenc}\n" \ - "\usepackage[usenames]{color}\n" \ - "\usepackage{graphicx}\n" \ - "\usepackage{listings}\n" \ - "\usepackage{xspace}\n" \ - "\input{style}\n" \ - "\\\\begin{document}\n" \ - "{\\\\resizebox{3\\\\textwidth}{!}{\input{${basename ${notdir $@}}.pstex_t}}}\n" \ - "\end{document}" > $@ +# figures/%.tex: build/%.pstex ${Build} +# echo -n "\documentclass[preview]{standalone}\n" \ +# "\usepackage[T1]{fontenc}\n" \ +# "\usepackage[usenames]{color}\n" \ +# "\usepackage{graphicx}\n" \ +# "\usepackage{listings}\n" \ +# "\usepackage{xspace}\n" \ +# "\input{style}\n" \ +# "\\\\begin{document}\n" \ +# "{\\\\resizebox{3\\\\textwidth}{!}{\input{${basename ${notdir $@}}.pstex_t}}}\n" \ +# "\end{document}" > $@ data/%: ; Index: doc/theses/colby_parsons_MMAth/glossary.tex =================================================================== --- doc/theses/colby_parsons_MMAth/glossary.tex (revision fa6ca1ac779b46c587efb95ae262f52a9c5378e0) +++ doc/theses/colby_parsons_MMAth/glossary.tex (revision 34b6a7b6878154693f83696df612a4adeee0fb87) @@ -1,18 +1,61 @@ -\makeglossaries +% % Main glossary entries -- definitions of relevant terminology +% \newglossaryentry{computer} +% { +% name=computer, +% description={A programmable machine that receives input data, +% stores and manipulates the data, and provides +% formatted output} +% } +% % Nomenclature glossary entries -- New definitions, or unusual terminology +% \newglossary*{nomenclature}{Nomenclature} +% \newglossaryentry{dingledorf} +% { +% type=nomenclature, +% name=dingledorf, +% description={A person of supposed average intelligence who makes incredibly brainless misjudgments} +% } -% \longnewglossaryentry{uthread} -% {name={user-level thread}} +% % List of Abbreviations (abbreviations type is built in to the glossaries-extra package) +% \newabbreviation{aaaaz}{AAAAZ}{American Association of Amateur Astronomers and Zoologists} + +% % List of Symbols +% \newglossary*{symbols}{List of Symbols} +% \newglossaryentry{rvec} % { -% Threads created and managed inside user-space. Each thread has its own stack and its own thread of execution. User-level threads are invisible to the underlying operating system. +% name={$\mathbf{v}$}, +% sort={label}, +% type=symbols, +% description={Random vector: a location in n-dimensional Cartesian space, where each dimensional component is determined by a random process} +% } -% \textit{Synonyms : User threads, Lightweight threads, Green threads, Virtual threads, Tasks.} -% } -% C_TODO: replace usages of these acronyms with \acrshort{name} -\newacronym{tls}{TLS}{Thread Local Storage} -\newacronym{api}{API}{Application Program Interface} -\newacronym{raii}{RAII}{Resource Acquisition Is Initialization} -\newacronym{numa}{NUMA}{Non-Uniform Memory Access} -\newacronym{rtti}{RTTI}{Run-Time Type Information} -\newacronym{fcfs}{FCFS}{First Come First Served} -\newacronym{toctou}{TOCTOU}{time-of-check to time-of-use} +% Examples from template above + +\newabbreviation{raii}{RAII}{Resource Acquisition Is Initialization} +\newabbreviation{rtti}{RTTI}{Run-Time Type Information} +\newabbreviation{fcfs}{FCFS}{First Come First Served} +\newabbreviation{toctou}{TOCTOU}{time-of-check to time-of-use} + +\newglossaryentry{actor} +{ +name=actor, +description={A basic unit of an actor system that can store local state and send messages to other actors.} +} + +\newglossaryentry{impl_concurrency} +{ +name=implicit concurrency, +description={A class of concurrency features that abstract away explicit thread synchronization and mutual exclusion.} +} + +\newglossaryentry{actor_model} +{ +name=actor model, +description={A concurrent computation model, where tasks are broken into units of work that are distributed to actors in the form of messages.} +} + +\newglossaryentry{actor_system} +{ +name=actor system, +description={An implementation of the actor model.} +} Index: doc/theses/colby_parsons_MMAth/local.bib =================================================================== --- doc/theses/colby_parsons_MMAth/local.bib (revision fa6ca1ac779b46c587efb95ae262f52a9c5378e0) +++ doc/theses/colby_parsons_MMAth/local.bib (revision 34b6a7b6878154693f83696df612a4adeee0fb87) @@ -31,5 +31,5 @@ @phdthesis{Delisle22, author={{Delisle, Thierry}}, -title={The C∀ Scheduler}, +title={The \textsf{C}$\mathbf{\forall}$ Scheduler}, year={2022}, publisher="UWSpace", @@ -50,5 +50,5 @@ @mastersthesis{Beach21, author={{Beach, Andrew James}}, -title={Exception Handling in C∀}, +title={Exception Handling in \textsf{C}$\mathbf{\forall}$}, year={2021}, publisher="UWSpace", Index: doc/theses/colby_parsons_MMAth/style/cfa-format.tex =================================================================== --- doc/theses/colby_parsons_MMAth/style/cfa-format.tex (revision fa6ca1ac779b46c587efb95ae262f52a9c5378e0) +++ doc/theses/colby_parsons_MMAth/style/cfa-format.tex (revision 34b6a7b6878154693f83696df612a4adeee0fb87) @@ -9,128 +9,19 @@ \definecolor{identifierCol}{HTML}{000000} -% from https://gist.github.com/nikolajquorning/92bbbeef32e1dd80105c9bf2daceb89a -\lstdefinelanguage{sml} { - morekeywords= { - EQUAL, GREATER, LESS, NONE, SOME, abstraction, abstype, and, andalso, array, as, before, bool, case, char, datatype, do, else, end, eqtype, exception, exn, false, fn, fun, functor, handle, if, in, include, infix, infixr, int, let, list, local, nil, nonfix, not, o, of, op, open, option, orelse, overload, print, raise, real, rec, ref, sharing, sig, signature, string, struct, structure, substring, then, true, type, unit, val, vector, where, while, with, withtype, word - }, - morestring=[b]", - morecomment=[s]{(*}{*)}, -} - -\lstdefinelanguage{D}{ - % Keywords - morekeywords=[1]{ - abstract, alias, align, auto, body, break, cast, catch, class, const, - continue, debug, delegate, delete, deprecated, do, else, enum, export, - false, final, finally, for, foreach, foreach_reverse, function, goto, if, - immutable, import, in, inout, interface, invariant, is, lazy, macro, mixin, - module, new, nothrow, null, out, override, package, pragma, private, - protected, public, pure, ref, return, shared, static, struct, super, - switch, synchronized, template, this, throw, true, try, typedef, typeid, - typeof, union, unittest, volatile, while, with - }, - % Special identifiers, common functions - morekeywords=[2]{enforce}, - % Ugly identifiers - morekeywords=[3]{ - __DATE__, __EOF__, __FILE__, __LINE__, __TIMESTAMP__, __TIME__, __VENDOR__, - __VERSION__, __ctfe, __gshared, __monitor, __thread, __vptr, _argptr, - _arguments, _ctor, _dtor - }, - % Basic types - morekeywords=[4]{ - byte, ubyte, short, ushort, int, uint, long, ulong, cent, ucent, void, - bool, bit, float, double, real, ushort, int, uint, long, ulong, float, - char, wchar, dchar, string, wstring, dstring, ireal, ifloat, idouble, - creal, cfloat, cdouble, size_t, ptrdiff_t, sizediff_t, equals_t, hash_t - }, - % Strings - morestring=[b]{"}, - morestring=[b]{'}, - morestring=[b]{`}, - % Comments - comment=[l]{//}, - morecomment=[s]{/*}{*/}, - morecomment=[s][\color{blue}]{/**}{*/}, - morecomment=[n]{/+}{+/}, - morecomment=[n][\color{blue}]{/++}{+/}, - % Options - sensitive=true -} - -\lstdefinelanguage{rust}{ - % Keywords - morekeywords=[1]{ - abstract, alignof, as, become, box, - break, const, continue, crate, do, - else, enum, extern, false, final, - fn, for, if, impl, in, - let, loop, macro, match, mod, - move, mut, offsetof, override, priv, - proc, pub, pure, ref, return, - Self, self, sizeof, static, struct, - super, trait, true, type, typeof, - unsafe, unsized, use, virtual, where, - while, yield - }, - % Strings - morestring=[b]{"}, - % Comments - comment=[l]{//}, - morecomment=[s]{/*}{*/}, - % Options - sensitive=true -} - -\lstdefinelanguage{pseudo}{ - morekeywords={string,uint,int,bool,float},% - sensitive=true,% - morecomment=[l]{//},% - morecomment=[s]{/*}{*/},% - morestring=[b]',% - morestring=[b]",% - morestring=[s]{`}{`},% -}% - -\newcommand{\KWC}{K-W C\xspace} - -\lstdefinestyle{pseudoStyle}{ - escapeinside={@@}, - basicstyle=\linespread{0.9}\sf\footnotesize, % reduce line spacing and use typewriter font - keywordstyle=\bfseries\color{blue}, - keywordstyle=[2]\bfseries\color{Plum}, - commentstyle=\itshape\color{OliveGreen}, % green and italic comments - identifierstyle=\color{identifierCol}, - stringstyle=\sf\color{Mahogany}, % use sanserif font - mathescape=true, - columns=fixed, - aboveskip=4pt, % spacing above/below code block - belowskip=3pt, - keepspaces=true, - tabsize=4, - % frame=lines, - literate=, - showlines=true, % show blank lines at end of code - showspaces=false, - showstringspaces=false, - escapechar=\$, - xleftmargin=\parindentlnth, % indent code to paragraph indentation - moredelim=[is][\color{red}\bfseries]{**R**}{**R**}, % red highlighting - % moredelim=* detects keywords, comments, strings, and other delimiters and applies their formatting - % moredelim=** allows cumulative application -} - \lstdefinestyle{defaultStyle}{ escapeinside={@@}, - basicstyle=\linespread{0.9}\tt\footnotesize, % reduce line spacing and use typewriter font - keywordstyle=\bfseries\color{blue}, - keywordstyle=[2]\bfseries\color{Plum}, - commentstyle=\itshape\color{OliveGreen}, % green and italic comments - identifierstyle=\color{identifierCol}, - stringstyle=\sf\color{Mahogany}, % use sanserif font +% basicstyle=\linespread{0.9}\tt\footnotesize, % reduce line spacing and use typewriter font + basicstyle=\linespread{0.9}\sf, % reduce line spacing and use typewriter +% keywordstyle=\bfseries\color{blue}, +% keywordstyle=[2]\bfseries\color{Plum}, +% commentstyle=\itshape\color{OliveGreen}, % green and italic comments +% identifierstyle=\color{identifierCol}, +% stringstyle=\sf\color{Mahogany}, % use sanserif font + stringstyle=\tt, % use sanserif font mathescape=true, - columns=fixed, - aboveskip=4pt, % spacing above/below code block - belowskip=3pt, +% columns=fixed, + columns=fullflexible, +% aboveskip=4pt, % spacing above/below code block +% belowskip=3pt, keepspaces=true, tabsize=4, @@ -149,14 +40,17 @@ \lstdefinestyle{cfaStyle}{ escapeinside={@@}, - basicstyle=\linespread{0.9}\tt\footnotesize, % reduce line spacing and use typewriter font - keywordstyle=\bfseries\color{blue}, - keywordstyle=[2]\bfseries\color{Plum}, - commentstyle=\sf\itshape\color{OliveGreen}, % green and italic comments - identifierstyle=\color{identifierCol}, - stringstyle=\sf\color{Mahogany}, % use sanserif font +% basicstyle=\linespread{0.9}\tt\footnotesize, % reduce line spacing and use typewriter font + basicstyle=\linespread{0.9}\sf, % reduce line spacing and use typewriter font +% keywordstyle=\bfseries\color{blue}, +% keywordstyle=[2]\bfseries\color{Plum}, +% commentstyle=\sf\itshape\color{OliveGreen}, % green and italic comments +% identifierstyle=\color{identifierCol}, +% stringstyle=\sf\color{Mahogany}, % use sanserif font + stringstyle=\tt, % use sanserif font mathescape=true, - columns=fixed, - aboveskip=4pt, % spacing above/below code block - belowskip=3pt, +% columns=fixed, + columns=fullflexible, +% aboveskip=4pt, % spacing above/below code block +% belowskip=3pt, keepspaces=true, tabsize=4, @@ -166,12 +60,11 @@ showspaces=false, showstringspaces=false, + showlines=true, % show blank lines at end of code escapechar=\$, xleftmargin=\parindentlnth, % indent code to paragraph indentation moredelim=[is][\color{red}\bfseries]{**R**}{**R**}, % red highlighting - morekeywords=[2]{accept, signal, signal_block, wait, waitfor}, + morekeywords=[2]{accept, signal, signal_block, wait, waitfor, waituntil}, + abovecaptionskip=5pt, } - -% \lstMakeShortInline[basewidth=0.5em,breaklines=true,basicstyle=\normalsize\ttfamily\color{basicCol}]@ % single-character for \lstinline -% \lstMakeShortInline@ \lstnewenvironment{ccode}[1][]{ @@ -188,13 +81,4 @@ language = CFA, style=cfaStyle, - captionpos=b, - #1 - } -}{} - -\lstnewenvironment{pseudo}[1][]{ - \lstset{ - language = pseudo, - style=pseudoStyle, captionpos=b, #1 @@ -229,40 +113,4 @@ }{} -\lstnewenvironment{scalacode}[1][]{ - \lstset{ - language = scala, - style=defaultStyle, - captionpos=b, - #1 - } -}{} - -\lstnewenvironment{smlcode}[1][]{ - \lstset{ - language = sml, - style=defaultStyle, - captionpos=b, - #1 - } -}{} - -\lstnewenvironment{dcode}[1][]{ - \lstset{ - language = D, - style=defaultStyle, - captionpos=b, - #1 - } -}{} - -\lstnewenvironment{rustcode}[1][]{ - \lstset{ - language = rust, - style=defaultStyle, - captionpos=b, - #1 - } -}{} - \lstnewenvironment{gocode}[1][]{ \lstset{ Index: doc/theses/colby_parsons_MMAth/style/style.tex =================================================================== --- doc/theses/colby_parsons_MMAth/style/style.tex (revision fa6ca1ac779b46c587efb95ae262f52a9c5378e0) +++ doc/theses/colby_parsons_MMAth/style/style.tex (revision 34b6a7b6878154693f83696df612a4adeee0fb87) @@ -1,12 +1,73 @@ -\input{common} % bespoke macros used in the document -\input{cfa-format} +\input{common} -% \CFADefaultStyle +\lstdefinestyle{defaultStyle}{ + escapeinside={@@}, + % basicstyle=\linespread{0.9}\tt\footnotesize, % reduce line spacing and use typewriter font + basicstyle=\linespread{0.9}\sf, % reduce line spacing and use typewriter font + % keywordstyle=\bfseries\color{blue}, + % keywordstyle=[2]\bfseries\color{Plum}, + % commentstyle=\sf\itshape\color{OliveGreen}, % green and italic comments + % identifierstyle=\color{identifierCol}, + % stringstyle=\sf\color{Mahogany}, % use sanserif font + stringstyle=\tt, % use sanserif font + mathescape=true, + % columns=fixed, + columns=fullflexible, + % aboveskip=4pt, % spacing above/below code block + % belowskip=3pt, + keepspaces=true, + tabsize=4, + % frame=lines, + literate=, + showlines=true, % show blank lines at end of code + showspaces=false, + showstringspaces=false, + showlines=true, % show blank lines at end of code + escapechar=\$, + xleftmargin=\parindentlnth, % indent code to paragraph indentation + moredelim=[is][\color{red}\bfseries]{**R**}{**R**}, % red highlighting + morekeywords=[2]{accept, signal, signal_block, wait, waitfor, waituntil}, + abovecaptionskip=5pt, +} -% \lstset{ -% morekeywords=[2]{nomutex,mutex,thread,wait,wait_release,signal,signal_block,accept,monitor,suspend,resume,coroutine}, -% keywordstyle=[2]\color{blue}, % second set of keywords for concurency -% basicstyle=\linespread{0.9}\tt\small, % reduce line spacing and use typewriter font -% stringstyle=\sf\color{Mahogany}, % use sanserif font -% commentstyle=\itshape\color{OliveGreen}, % green and italic comments -% }% +\lstdefinestyle{cfaStyle}{ + escapeinside={@@}, + basicstyle=\linespread{0.9}\sf, % reduce line spacing and use typewriter font + stringstyle=\tt, % use sanserif font + mathescape=true, + columns=fullflexible, + keepspaces=true, + tabsize=4, + literate=, + showlines=true, % show blank lines at end of code + showspaces=false, + showstringspaces=false, + showlines=true, % show blank lines at end of code + escapechar=\$, + xleftmargin=\parindentlnth, % indent code to paragraph indentation + moredelim=[is][\color{red}\bfseries]{**R**}{**R**}, % red highlighting + morekeywords=[2]{accept, signal, signal_block, wait, waitfor, waituntil}, + abovecaptionskip=5pt, +} + +\lstnewenvironment{cfacode}[1][]{ + \lstset{ + language = CFA, + style=cfaStyle, + captionpos=b, + #1 + } +}{} + +\lstnewenvironment{cppcode}[1][]{ + \lstset{ + language = c++, + style=defaultStyle, + captionpos=b, + #1 + } +}{} + +\newcommand{\code}[1]{\lstinline[language=CFA,style=cfaStyle]{#1}} +\newcommand{\uC}{$\mu$\CC} + Index: doc/theses/colby_parsons_MMAth/text/CFA_concurrency.tex =================================================================== --- doc/theses/colby_parsons_MMAth/text/CFA_concurrency.tex (revision fa6ca1ac779b46c587efb95ae262f52a9c5378e0) +++ doc/theses/colby_parsons_MMAth/text/CFA_concurrency.tex (revision 34b6a7b6878154693f83696df612a4adeee0fb87) @@ -1,8 +1,19 @@ \chapter{Concurrency in \CFA}\label{s:cfa_concurrency} -The groundwork for concurrency in \CFA was laid by Thierry Delisle in his Master's Thesis\cite{Delisle18}. In that work he introduced coroutines, user level threading, and monitors. Not listed in that work were the other concurrency features that were needed as building blocks, such as locks, futures, and condition variables which he also added to \CFA. +The groundwork for concurrency in \CFA was laid by Thierry Delisle in his Master's Thesis\cite{Delisle18}. +In that work he introduced coroutines, user level threading, and monitors. +Not listed in that work were the other concurrency features that were needed as building blocks, such as locks, futures, and condition variables which he also added to \CFA. \section{Threading Model}\label{s:threading} -\CFA has user level threading and supports a $M:N$ threading model where $M$ user threads are scheduled on $N$ cores, where both $M$ and $N$ can be explicitly set by the user. Cores are used by a program by creating instances of a \code{processor} struct. User threads types are defined using the \code{thread} keyword, in the place where a \code{struct} keyword is typically used. For each thread type a corresponding main must be defined, which is where the thread starts running once it is created. Listing~\ref{l:cfa_thd_init} shows an example of processor and thread creation. When processors are added, they are added alongside the existing processor given to each program. Thus if you want $N$ processors you need to allocate $N-1$. To join a thread the thread must be deallocated, either deleted if it is allocated on the heap, or go out of scope if stack allocated. The thread performing the deallocation will wait for the thread being deallocated to terminate before the deallocation can occur. A thread terminates by returning from the main routine where it starts. +\CFA has user level threading and supports a $M:N$ threading model where $M$ user threads are scheduled on $N$ cores, where both $M$ and $N$ can be explicitly set by the user. +Cores are used by a program by creating instances of a \code{processor} struct. +User threads types are defined using the \code{thread} keyword, in the place where a \code{struct} keyword is typically used. +For each thread type a corresponding main must be defined, which is where the thread starts running once it is created. +Listing~\ref{l:cfa_thd_init} shows an example of processor and thread creation. +When processors are added, they are added alongside the existing processor given to each program. +Thus if you want $N$ processors you need to allocate $N-1$. +To join a thread the thread must be deallocated, either deleted if it is allocated on the heap, or go out of scope if stack allocated. +The thread performing the deallocation will wait for the thread being deallocated to terminate before the deallocation can occur. +A thread terminates by returning from the main routine where it starts. \begin{cfacode}[tabsize=3,caption={\CFA user thread and processor creation},label={l:cfa_thd_init}] Index: doc/theses/colby_parsons_MMAth/text/CFA_intro.tex =================================================================== --- doc/theses/colby_parsons_MMAth/text/CFA_intro.tex (revision fa6ca1ac779b46c587efb95ae262f52a9c5378e0) +++ doc/theses/colby_parsons_MMAth/text/CFA_intro.tex (revision 34b6a7b6878154693f83696df612a4adeee0fb87) @@ -6,10 +6,18 @@ \section{Overview} -The following serves as an introduction to \CFA. \CFA is a layer over C, is transpiled to C and is largely considered to be an extension of C. Beyond C, it adds productivity features, libraries, a type system, and many other language constructions. However, \CFA stays true to C as a language, with most code revolving around \code{struct}'s and routines, and respects the same rules as C. \CFA is not object oriented as it has no notion of \code{this} and no classes or methods, but supports some object oriented adjacent ideas including costructors, destructors, and limited inheritance. \CFA is rich with interesting features, but a subset that is pertinent to this work will be discussed. +The following serves as an introduction to \CFA. +\CFA is a layer over C, is transpiled to C and is largely considered to be an extension of C. +Beyond C, it adds productivity features, libraries, a type system, and many other language constructions. +However, \CFA stays true to C as a language, with most code revolving around \code{struct}'s and routines, and respects the same rules as C. +\CFA is not object oriented as it has no notion of \code{this} and no classes or methods, but supports some object oriented adjacent ideas including costructors, destructors, and limited inheritance. +\CFA is rich with interesting features, but a subset that is pertinent to this work will be discussed. \section{References} -References in \CFA are similar to references in \CC, however in \CFA references are rebindable, and support multi-level referencing. References in \CFA are a layer of syntactic sugar over pointers to reduce the number of ref/deref operations needed with pointer usage. Some examples of references in \CFA are shown in Listing~\ref{l:cfa_ref}. Another related item to note is that the \CFA equivalent of \CC's \code{nullptr} is \code{0p}. - -\begin{cfacode}[tabsize=3,caption={Example of \CFA references},label={l:cfa_ref}] +References in \CFA are similar to references in \CC, however in \CFA references are rebindable, and support multi-level referencing. +References in \CFA are a layer of syntactic sugar over pointers to reduce the number of ref/deref operations needed with pointer usage. +Some examples of references in \CFA are shown in Listing~\ref{l:cfa_ref}. +Another related item to note is that the \CFA equivalent of \CC's \code{nullptr} is \code{0p}. + +\begin{cfacode}[caption={Example of \CFA references},label={l:cfa_ref}] int i = 2; int & ref_i = i; // declare ref to i @@ -29,8 +37,11 @@ \section{Overloading} -In \CFA routines can be overloaded on parameter type, number of parameters, and return type. Variables can also be overloaded on type, meaning that two variables can have the same name so long as they have different types. The variables will be disambiguated via type, sometimes requiring a cast. The code snippet in Listing~\ref{l:cfa_overload} contains examples of overloading. - - -\begin{cfacode}[tabsize=3,caption={Example of \CFA function overloading},label={l:cfa_overload}] +In \CFA routines can be overloaded on parameter type, number of parameters, and return type. +Variables can also be overloaded on type, meaning that two variables can have the same name so long as they have different types. +The variables will be disambiguated via type, sometimes requiring a cast. +The code snippet in Listing~\ref{l:cfa_overload} contains examples of overloading. + + +\begin{cfacode}[caption={Example of \CFA function overloading},label={l:cfa_overload}] int foo() { printf("A\n"); return 0;} int foo( int bar ) { printf("B\n"); return 1; } @@ -50,5 +61,9 @@ \section{With Statement} -The with statement is a tool for exposing members of aggregate types within a scope in \CFA. It allows users to use fields of aggregate types without using their fully qualified name. This feature is also implemented in Pascal. It can exist as a stand-alone statement or it can be used on routines to expose fields in the body of the routine. An example is shown in Listing~\ref{l:cfa_with}. +The with statement is a tool for exposing members of aggregate types within a scope in \CFA. +It allows users to use fields of aggregate types without using their fully qualified name. +This feature is also implemented in Pascal. +It can exist as a stand-alone statement or it can be used on routines to expose fields in the body of the routine. +An example is shown in Listing~\ref{l:cfa_with}. @@ -89,5 +104,6 @@ \section{Operators} -Operators can be overloaded in \CFA with operator routines. Operators in \CFA are named using the operator symbol and '?' to respresent operands. +Operators can be overloaded in \CFA with operator routines. +Operators in \CFA are named using the operator symbol and '?' to respresent operands. An example is shown in Listing~\ref{l:cfa_operate}. @@ -113,5 +129,7 @@ \section{Constructors and Destructors} -Constructors and destructors in \CFA are two special operator routines that are used for creation and destruction of objects. The default constructor and destructor for a type are called implicitly upon creation and deletion respectively if they are defined. An example is shown in Listing~\ref{l:cfa_ctor}. +Constructors and destructors in \CFA are two special operator routines that are used for creation and destruction of objects. +The default constructor and destructor for a type are called implicitly upon creation and deletion respectively if they are defined. +An example is shown in Listing~\ref{l:cfa_ctor}. @@ -143,8 +161,14 @@ \section{Polymorphism}\label{s:poly} -C does not natively support polymorphism, and requires users to implement polymorphism themselves if they want to use it. \CFA extends C with two styles of polymorphism that it supports, parametric polymorphism and nominal inheritance. +C does not natively support polymorphism, and requires users to implement polymorphism themselves if they want to use it. +\CFA extends C with two styles of polymorphism that it supports, parametric polymorphism and nominal inheritance. \subsection{Parametric Polymorphism} -\CFA provides parametric polymorphism in the form of \code{forall}, and \code{trait}s. A \code{forall} takes in a set of types and a list of constraints. The declarations that follow the \code{forall} are parameterized over the types listed that satisfy the constraints. Sometimes the list of constraints can be long, which is where a \code{trait} can be used. A \code{trait} is a collection of constraints that is given a name and can be reused in foralls. An example of the usage of parametric polymorphism in \CFA is shown in Listing~\ref{l:cfa_poly}. +\CFA provides parametric polymorphism in the form of \code{forall}, and \code{trait}s. +A \code{forall} takes in a set of types and a list of constraints. +The declarations that follow the \code{forall} are parameterized over the types listed that satisfy the constraints. +Sometimes the list of constraints can be long, which is where a \code{trait} can be used. +A \code{trait} is a collection of constraints that is given a name and can be reused in foralls. +An example of the usage of parametric polymorphism in \CFA is shown in Listing~\ref{l:cfa_poly}. \begin{cfacode}[tabsize=3,caption={Example of \CFA polymorphism},label={l:cfa_poly}] @@ -194,5 +218,7 @@ \subsection{Inheritance} -Inheritance in \CFA copies its style from Plan-9 C nominal inheritance. In \CFA structs can \code{inline} another struct type to gain its fields and to be able to be passed to routines that require a parameter of the inlined type. An example of \CFA inheritance is shown in Listing~\ref{l:cfa_inherit}. +Inheritance in \CFA copies its style from Plan-9 C nominal inheritance. +In \CFA structs can \code{inline} another struct type to gain its fields and to be able to be passed to routines that require a parameter of the inlined type. +An example of \CFA inheritance is shown in Listing~\ref{l:cfa_inherit}. \begin{cfacode}[tabsize=3,caption={Example of \CFA inheritance},label={l:cfa_inherit}] Index: doc/theses/colby_parsons_MMAth/text/actors.tex =================================================================== --- doc/theses/colby_parsons_MMAth/text/actors.tex (revision fa6ca1ac779b46c587efb95ae262f52a9c5378e0) +++ doc/theses/colby_parsons_MMAth/text/actors.tex (revision 34b6a7b6878154693f83696df612a4adeee0fb87) @@ -6,11 +6,23 @@ % C_TODO: add citations throughout chapter -Actors are a concurrent feature that abstracts threading away from a user, and instead provides \newterm{actors} and \newterm{messages} as building blocks for concurrency. Actors are another message passing concurrency feature, similar to channels, but with more abstraction. Actors enter the realm of what is called \newterm{implicit concurrency}, where programmers can write concurrent code without having to worry about explicit thread synchronization and mutual exclusion. The study of actors can be broken into two concepts, the \newterm{actor model}, which describes the model of computation and the \newterm{actor system}, which refers to the implementation of the model in practice. Before discussing \CFA's actor system in detail, it is important to first describe the actor model, and the classic approach to implementing an actor system. +Actors are a concurrent feature that abstracts threading away from a user, and instead provides \gls{actor}s and messages as building blocks for concurrency. +Actors are another message passing concurrency feature, similar to channels, but with more abstraction. +Actors enter the realm of what is called \gls{impl_concurrency}, where programmers can write concurrent code without having to worry about explicit thread synchronization and mutual exclusion. +The study of actors can be broken into two concepts, the \gls{actor_model}, which describes the model of computation and the \gls{actor_system}, which refers to the implementation of the model in practice. +Before discussing \CFA's actor system in detail, it is important to first describe the actor model, and the classic approach to implementing an actor system. \section{The Actor Model} -The actor model is a paradigm of concurrent computation, where tasks are broken into units of work that are distributed to actors in the form of messages \cite{Hewitt73}. Actors execute asynchronously upon receiving a message and can modify their own state, make decisions, spawn more actors, and send messages to other actors. The actor model is an implicit model of concurrency. As such, one strength of the actor model is that it abstracts away many considerations that are needed in other paradigms of concurrent computation. Mutual exclusion, and locking are rarely relevant concepts to users of an actor model, as actors typically operate on local state. +The actor model is a paradigm of concurrent computation, where tasks are broken into units of work that are distributed to actors in the form of messages \cite{Hewitt73}. +Actors execute asynchronously upon receiving a message and can modify their own state, make decisions, spawn more actors, and send messages to other actors. +The actor model is an implicit model of concurrency. +As such, one strength of the actor model is that it abstracts away many considerations that are needed in other paradigms of concurrent computation. +Mutual exclusion, and locking are rarely relevant concepts to users of an actor model, as actors typically operate on local state. \section{Classic Actor System} -An implementation of the actor model with a community of actors is called an actor system. Actor systems largely follow the actor model, but differ in some ways. While the definition of the actor model provides no restrictions on message ordering, actor systems tend to guarantee that messages sent from a given actor $i$ to actor $j$ will arrive at actor $j$ in the order they were sent. Another way an actor system varies from the model is that actors are often allowed to access non-local state. When this occurs it can complicate the implementation as this will break any mutual exclusion guarantees given by accessing only local state. +An implementation of the actor model with a community of actors is called an actor system. +Actor systems largely follow the actor model, but differ in some ways. +While the definition of the actor model provides no restrictions on message ordering, actor systems tend to guarantee that messages sent from a given actor $i$ to actor $j$ will arrive at actor $j$ in the order they were sent. +Another way an actor system varies from the model is that actors are often allowed to access non-local state. +When this occurs it can complicate the implementation as this will break any mutual exclusion guarantees given by accessing only local state. \begin{figure} @@ -23,8 +35,21 @@ \section{\CFA Actors} -Actor systems \cite{} have often been implemented as an actor-centric system. As such they are constructed as a set of actors that are scheduled and run on some underlying threads. Each actor has their own queue for receiving messages, sometimes called a mailbox. When they receive messages in their mailbox, actors are moved from idle to ready queues and then scheduled on a thread to run their unit of work. This approach can be implemented with a global queue of actors, but is often implemented as each worker thread owning a queue of actors. This is known as sharding the actor queue, which is done to decrease contention across worker threads. A diagram of an actor-centric system with a sharded actor queue is shown in Figure \ref{f:standard_actor}. +Actor systems \cite{} have often been implemented as an actor-centric system. +As such they are constructed as a set of actors that are scheduled and run on some underlying threads. +Each actor has their own queue for receiving messages, sometimes called a mailbox. +When they receive messages in their mailbox, actors are moved from idle to ready queues and then scheduled on a thread to run their unit of work. +This approach can be implemented with a global queue of actors, but is often implemented as each worker thread owning a queue of actors. +This is known as sharding the actor queue, which is done to decrease contention across worker threads. +A diagram of an actor-centric system with a sharded actor queue is shown in Figure \ref{f:standard_actor}. % cite parallel theatre and our paper -The actor system in \CFA is instead message-centric, an uses what is called an inverted actor system \cite{}. In this inverted actor system instead of each worker thread owning a queue of actors, they each own a queue of messages. This system is called inverted since in this scheme, actors belong to a message queue, whereas in the classic approach a message queue belongs to each actor. Since multiple actors belong to each message queue, messages to each actor are interleaved in the queue. In this scheme work is consumed from their queue and executed by underlying threads. In High-Performance Extended Actors \cite{} this inverted model is taken a step further and the message queues are sharded, so that each worker now instead owns a set of queues. A diagram of an inverted actor scheme with a sharded message queue is shown in Figure \ref{f:inverted_actor}. The arrows from the message queues to the actors in the diagram indicate interleaved messages addressed to each actor. +The actor system in \CFA is instead message-centric, an uses what is called an inverted actor system \cite{}. +In this inverted actor system instead of each worker thread owning a queue of actors, they each own a queue of messages. +This system is called inverted since in this scheme, actors belong to a message queue, whereas in the classic approach a message queue belongs to each actor. +Since multiple actors belong to each message queue, messages to each actor are interleaved in the queue. +In this scheme work is consumed from their queue and executed by underlying threads. +In High-Performance Extended Actors \cite{} this inverted model is taken a step further and the message queues are sharded, so that each worker now instead owns a set of queues. +A diagram of an inverted actor scheme with a sharded message queue is shown in Figure \ref{f:inverted_actor}. +The arrows from the message queues to the actors in the diagram indicate interleaved messages addressed to each actor. The actor system in \CFA builds on top of the architecture laid out in High-Performance Extended Actors \cite{} and adds the following contributions: @@ -32,8 +57,16 @@ \begin{enumerate}[topsep=5pt,itemsep=3pt,parsep=0pt] \item -Provides insight into the impact of envelope allocation in actor systems. In all actor systems dynamic allocation is needed to ensure that the lifetime of a unit of work persists from its creation until the unit of work is executed. This allocation is often called an envelope as it "packages" the information needed to run the unit of work, alongside any other information needed to send the unit of work, such as an actor's address or link fields for a list. This dynamic allocation occurs once per message sent. This is a large source of contention on the memory allocator since all these allocations occur concurrently. A novel data structure is used to consolidate allocations to improve performance by minimizing contention on the allocator. - -\item -Introduces work stealing in the inverted actor system. Work stealing in actor-centric systems tends to involve stealing one or more actors. In the inverted system the notion of stealing queues is introduced. The queue stealing is implemented such that the act of stealing work does not contend with non-stealing actors that are saturated with work. +Provides insight into the impact of envelope allocation in actor systems. +In all actor systems dynamic allocation is needed to ensure that the lifetime of a unit of work persists from its creation until the unit of work is executed. +This allocation is often called an envelope as it "packages" the information needed to run the unit of work, alongside any other information needed to send the unit of work, such as an actor's address or link fields for a list. +This dynamic allocation occurs once per message sent. +This is a large source of contention on the memory allocator since all these allocations occur concurrently. +A novel data structure is used to consolidate allocations to improve performance by minimizing contention on the allocator. + +\item +Introduces work stealing in the inverted actor system. +Work stealing in actor-centric systems tends to involve stealing one or more actors. +In the inverted system the notion of stealing queues is introduced. +The queue stealing is implemented such that the act of stealing work does not contend with non-stealing actors that are saturated with work. \item @@ -48,5 +81,10 @@ \section{\CFA Actor Syntax} -\CFA is not an object oriented language and it does not have run-time type information (RTTI). As such all message sends and receives between actors occur using exact type matching. To use actors in \CFA you must \code{\#include }. To create an actor type one must define a struct which inherits from the base \code{actor} struct via the \code{inline} keyword. This is the Plan-9 C-style nominal inheritance discussed in Section \ref{s:poly}. Similarly to create a message type a user must define a struct which \code{inline}'s the base \code{message} struct. +\CFA is not an object oriented language and it does not have run-time type information (RTTI). +As such all message sends and receives between actors occur using exact type matching. +To use actors in \CFA you must \code{\#include }. +To create an actor type one must define a struct which inherits from the base \code{actor} struct via the \code{inline} keyword. +This is the Plan-9 C-style nominal inheritance discussed in Section \ref{s:poly}. +Similarly to create a message type a user must define a struct which \code{inline}'s the base \code{message} struct. \begin{cfacode} @@ -82,13 +120,21 @@ \end{cfacode} -The above code is a simple actor program in \CFA. There is one derived actor type and one derived message type. A single message containing a string is sent from the program main to an actor. Key things to highlight include the \code{receive} signature, and calls to \code{start_actor_system}, and \code{stop_actor_system}. To define a behaviour for some derived actor and derived message type, one must declare a routine with the signature: +The above code is a simple actor program in \CFA. +There is one derived actor type and one derived message type. +A single message containing a string is sent from the program main to an actor. +Key things to highlight include the \code{receive} signature, and calls to \code{start_actor_system}, and \code{stop_actor_system}. +To define a behaviour for some derived actor and derived message type, one must declare a routine with the signature: \begin{cfacode} Allocation receive( derived_actor & receiver, derived_msg & msg ) \end{cfacode} -Where \code{derived_actor} and \code{derived_msg} can be any derived actor and derived message types respectively. The return value of \code{receive} must be a value from the \code{Allocation} enum: +Where \code{derived_actor} and \code{derived_msg} can be any derived actor and derived message types respectively. +The return value of \code{receive} must be a value from the \code{Allocation} enum: \begin{cfacode} enum Allocation { Nodelete, Delete, Destroy, Finished }; \end{cfacode} -The \code{Allocation} enum is a set of actions that dictate what the executor should do with a message or actor after a given behaviour has been completed. In the case of an actor, the \code{receive} routine returns the \code{Allocation} status to the executor which sets the status on the actor and takes the appropriate action. For messages, they either default to \code{Nodelete}, or they can be passed an \code{Allocation} via the \code{message} constructor. Message state can be updated via a call to: +The \code{Allocation} enum is a set of actions that dictate what the executor should do with a message or actor after a given behaviour has been completed. +In the case of an actor, the \code{receive} routine returns the \code{Allocation} status to the executor which sets the status on the actor and takes the appropriate action. +For messages, they either default to \code{Nodelete}, or they can be passed an \code{Allocation} via the \code{message} constructor. +Message state can be updated via a call to: \begin{cfacode} void set_allocation( message & this, Allocation state ) @@ -99,37 +145,61 @@ \begin{description} \item[\LstBasicStyle{\textbf{Nodelete}}] -tells the executor that no action is to be taken with regard to a message or actor with this status. This indicates that the actor will receive future behaviours, and that a message may be reused. +tells the executor that no action is to be taken with regard to a message or actor with this status. +This indicates that the actor will receive future behaviours, and that a message may be reused. \item[\LstBasicStyle{\textbf{Delete}}] -tells the executor to call the appropriate destructor and then deallocate the respective actor or message. This status is typically used with dynamically allocated actors and messages. +tells the executor to call the appropriate destructor and then deallocate the respective actor or message. +This status is typically used with dynamically allocated actors and messages. \item[\LstBasicStyle{\textbf{Destroy}}] -tells the executor to call the object's destructor. The executor will not deallocate the respective actor or message. This status is typically used with dynamically allocated actors and messages whose storage will be reused. +tells the executor to call the object's destructor. +The executor will not deallocate the respective actor or message. +This status is typically used with dynamically allocated actors and messages whose storage will be reused. \item[\LstBasicStyle{\textbf{Finished}}] -tells the executor to mark the respective actor as being finished executing. In this case the executor will not call any destructors or deallocate any objects. This status is used when the actors are stack allocated or if the user wants to manage deallocation of actors themselves. In the case of messages, \code{Finished} is no different than \code{Nodelete} since the executor does not need to track if messages are done work. As such \code{Finished} is not supported for messages and is used internally by the executor to track if messages have been used for debugging purposes. +tells the executor to mark the respective actor as being finished executing. +In this case the executor will not call any destructors or deallocate any objects. +This status is used when the actors are stack allocated or if the user wants to manage deallocation of actors themselves. +In the case of messages, \code{Finished} is no different than \code{Nodelete} since the executor does not need to track if messages are done work. +As such \code{Finished} is not supported for messages and is used internally by the executor to track if messages have been used for debugging purposes. \end{description} -For the actor system to gracefully terminate, all actors must have returned a status other than \code{Nodelete}. Once an actor's allocation status has been set to something other than \code{Nodelete}, it is erroneous for the actor to receive a message. Similarly messages cannot be safely reused after their related behaviour if their status is not \code{Nodelete}. Note, it is safe to construct a message with a non-\code{Nodelete} status since the executor will only take the appropriate allocation action after a message has been delivered. - -The calls to \code{start_actor_system}, and \code{stop_actor_system} mark the start and end of a \CFA actor system. The call to \code{start_actor_system} sets up the executor and worker threads for the actor system. \code{start_actor_system} has three overloaded signatures which all start the actor system, but vary in executor configuration: +For the actor system to gracefully terminate, all actors must have returned a status other than \code{Nodelete}. +Once an actor's allocation status has been set to something other than \code{Nodelete}, it is erroneous for the actor to receive a message. +Similarly messages cannot be safely reused after their related behaviour if their status is not \code{Nodelete}. +Note, it is safe to construct a message with a non-\code{Nodelete} status since the executor will only take the appropriate allocation action after a message has been delivered. + +The calls to \code{start_actor_system}, and \code{stop_actor_system} mark the start and end of a \CFA actor system. +The call to \code{start_actor_system} sets up the executor and worker threads for the actor system. +\code{start_actor_system} has three overloaded signatures which all start the actor system, but vary in executor configuration: \noindent\code{void start_actor_system()} configures the executor with one underlying worker thread and processor. -\noindent\code{void start_actor_system( size_t num_thds )} configures the executor with \code{num_thds} underlying processors and \code{num_thds} worker threads. It chooses amount of queue sharding as a function of \code{num_thds}. - -\noindent\code{void start_actor_system( executor & this )} allows the user to allocate, configure, and pass an executor so that they have full control of executor parameterization. Executor configuration options include number of worker threads, number of queues, number of processors, and a few other toggles. +\noindent\code{void start_actor_system( size_t num_thds )} configures the executor with \code{num_thds} underlying processors and \code{num_thds} worker threads. +It chooses amount of queue sharding as a function of \code{num_thds}. + +\noindent\code{void start_actor_system( executor & this )} allows the user to allocate, configure, and pass an executor so that they have full control of executor parameterization. +Executor configuration options include number of worker threads, number of queues, number of processors, and a few other toggles. All actors must be created after calling \code{start_actor_system} so that the executor can keep track of the number of actors that have been allocated but have not yet terminated. -All message sends are done using the left shift operater, \ie <<, similar to the syntax of \CC's output. The signature of the left shift operator is: +All message sends are done using the left shift operater, \ie <<, similar to the syntax of \CC's output. +The signature of the left shift operator is: \begin{cfacode} Allocation ?< 1$ swaps occuring that form a single directed connected graph. At least one swap is guaranteed to suceed if and only if the graph does not contain a cycle. +Given a set of $M > 1$ swaps occuring that form a single directed connected graph. +At least one swap is guaranteed to suceed if and only if the graph does not contain a cycle. \end{theorem}\label{t:vic_cycle} Representations of cyclic and acylic swap graphs discussed in this theorem are presented in Figures~\ref{f:cyclic_swap} and \ref{f:acyclic_swap}. \\ -First the reverse direction is proven. If the graph does not contain a cycle, then there must be at least one successful swap. Since the graph contains no cycles and is finite in size, then there must be a vertex $A$ with no outgoing edges. The graph can then be formulated as a tree with $A$ at the top since each node only has at most one outgoing edge and there are no cycles. The forward direction is proven by contradiction in a similar fashion to \ref{t:vic_chain}. Assume no swaps occur. Similar to \ref{t:vic_chain}, this graph can be inductively split into subgraphs of the same type by failure at step 1, so the proof proceeds without loss of generality. Similar to \ref{t:vic_chain} the conclusion is drawn that all thieves must successfully complete step 2 for no swaps to occur, since for step 2 to fail, a different thief has to successfully complete step 3, which would imply a successful swap. Hence, the only way forward is to assume all thieves successfully complete step 2. Hence for there to be no swaps all thieves must fail step 3. However, since $A$ has no outgoing edges, since the graph is connected there must be some $K$ such that $K < M - 1$ thieves are attempting to swap with $A$. Since all $K$ thieves have passed step 2, similar to \ref{t:one_vic} the first one of the $K$ thieves to attempt step 3 is guaranteed to succeed. Thus, by contradiction with the earlier assumption that no swaps occur, if the graph does not contain a cycle, at least one swap must succeed. - -The forward direction is proven by contrapositive. If the graph contains a cycle then there exists a situation where no swaps occur. This situation is constructed. Since all vertices have at most one outgoing edge the cycle must be directed. Furthermore, since the graph contains a cycle all vertices in the graph must have exactly one outgoing edge. This is shown through construction of an aribtrary cyclic graph. The graph contains a directed cycle by definition, so the construction starts with $T$ vertices in a directed cycle. Since the graph is connected, and each vertex has at most one outgoing edge, none of the vertices in the cycle have available outgoing edges to accomodate new vertices with no outgoing edges. Any vertices added to the graph must have an outgoing edge to connect, leaving the resulting graph with no available outgoing edges. Thus, by induction all vertices in the graph must have exactly one outgoing edge. Hence all vertices are thief queues. Now consider the case where all thieves successfully complete step 0-1, and then they all complete step 2. At this point all thieves are attempting to swap with a queue pointer whose value has changed to \code{0p}. If all thieves attempt the \code{CAS} before any write backs, then they will all fail. Thus, by contrapositive, if the graph contains a cycle then there exists a situation where no swaps occur. Hence, at least one swap is guaranteed to suceed if and only if the graph does not contain a cycle. +First the reverse direction is proven. +If the graph does not contain a cycle, then there must be at least one successful swap. +Since the graph contains no cycles and is finite in size, then there must be a vertex $A$ with no outgoing edges. +The graph can then be formulated as a tree with $A$ at the top since each node only has at most one outgoing edge and there are no cycles. +The forward direction is proven by contradiction in a similar fashion to \ref{t:vic_chain}. +Assume no swaps occur. +Similar to \ref{t:vic_chain}, this graph can be inductively split into subgraphs of the same type by failure at step 1, so the proof proceeds without loss of generality. +Similar to \ref{t:vic_chain} the conclusion is drawn that all thieves must successfully complete step 2 for no swaps to occur, since for step 2 to fail, a different thief has to successfully complete step 3, which would imply a successful swap. +Hence, the only way forward is to assume all thieves successfully complete step 2. +Hence for there to be no swaps all thieves must fail step 3. +However, since $A$ has no outgoing edges, since the graph is connected there must be some $K$ such that $K < M - 1$ thieves are attempting to swap with $A$. +Since all $K$ thieves have passed step 2, similar to \ref{t:one_vic} the first one of the $K$ thieves to attempt step 3 is guaranteed to succeed. +Thus, by contradiction with the earlier assumption that no swaps occur, if the graph does not contain a cycle, at least one swap must succeed. + +The forward direction is proven by contrapositive. +If the graph contains a cycle then there exists a situation where no swaps occur. +This situation is constructed. +Since all vertices have at most one outgoing edge the cycle must be directed. +Furthermore, since the graph contains a cycle all vertices in the graph must have exactly one outgoing edge. +This is shown through construction of an aribtrary cyclic graph. +The graph contains a directed cycle by definition, so the construction starts with $T$ vertices in a directed cycle. +Since the graph is connected, and each vertex has at most one outgoing edge, none of the vertices in the cycle have available outgoing edges to accomodate new vertices with no outgoing edges. +Any vertices added to the graph must have an outgoing edge to connect, leaving the resulting graph with no available outgoing edges. +Thus, by induction all vertices in the graph must have exactly one outgoing edge. +Hence all vertices are thief queues. +Now consider the case where all thieves successfully complete step 0-1, and then they all complete step 2. +At this point all thieves are attempting to swap with a queue pointer whose value has changed to \code{0p}. +If all thieves attempt the \code{CAS} before any write backs, then they will all fail. +Thus, by contrapositive, if the graph contains a cycle then there exists a situation where no swaps occur. +Hence, at least one swap is guaranteed to suceed if and only if the graph does not contain a cycle. % C_TODO: go through and use \paragraph to format to make it look nicer \subsection{Victim Selection}\label{s:victimSelect} -In any work stealing algorithm thieves have some heuristic to determine which victim to choose from. Choosing this algorithm is difficult and can have implications on performance. There is no one selection heuristic that is known to be the best on all workloads. Recent work focuses on locality aware scheduling in actor systems\cite{barghi18}\cite{wolke17}. However, while locality aware scheduling provides good performance on some workloads, something as simple as randomized selection performs better on other workloads\cite{barghi18}. Since locality aware scheduling has been explored recently, this work introduces a heuristic called \newterm{longest victim} and compares it to randomized work stealing. The longest victim heuristic maintains a timestamp per worker thread that is updated every time a worker attempts to steal work. Thieves then attempt to steal from the thread with the oldest timestamp. This means that if two thieves look to steal at the same time, they likely will attempt to steal from the same victim. This does increase the chance at contention between thieves, however given that workers have multiple queues under them, often in the tens or hundreds of queues per worker it is rare for two queues to attempt so steal the same queue. Furthermore in the case they attempt to steal the same queue at least one of them is guaranteed to successfully steal the queue as shown in Theorem \ref{t:one_vic}. Additonally, the longest victim heuristic makes it very improbable that the no swap scenario presented in Theorem \ref{t:vic_cycle} manifests. Given the longest victim heuristic, for a cycle to manifest it would require all workers to attempt to steal in a short timeframe. This is the only way that more than one thief could choose another thief as a victim, since timestamps are only updated upon attempts to steal. In this case, the probability of lack of any successful swaps is a non issue, since it is likely that these steals were not important if all workers are trying to steal. +In any work stealing algorithm thieves have some heuristic to determine which victim to choose from. +Choosing this algorithm is difficult and can have implications on performance. +There is no one selection heuristic that is known to be the best on all workloads. +Recent work focuses on locality aware scheduling in actor systems\cite{barghi18}\cite{wolke17}. +However, while locality aware scheduling provides good performance on some workloads, something as simple as randomized selection performs better on other workloads\cite{barghi18}. +Since locality aware scheduling has been explored recently, this work introduces a heuristic called \textbf{longest victim} and compares it to randomized work stealing. +The longest victim heuristic maintains a timestamp per worker thread that is updated every time a worker attempts to steal work. +Thieves then attempt to steal from the thread with the oldest timestamp. +This means that if two thieves look to steal at the same time, they likely will attempt to steal from the same victim. +This does increase the chance at contention between thieves, however given that workers have multiple queues under them, often in the tens or hundreds of queues per worker it is rare for two queues to attempt so steal the same queue. +Furthermore in the case they attempt to steal the same queue at least one of them is guaranteed to successfully steal the queue as shown in Theorem \ref{t:one_vic}. +Additonally, the longest victim heuristic makes it very improbable that the no swap scenario presented in Theorem \ref{t:vic_cycle} manifests. +Given the longest victim heuristic, for a cycle to manifest it would require all workers to attempt to steal in a short timeframe. +This is the only way that more than one thief could choose another thief as a victim, since timestamps are only updated upon attempts to steal. +In this case, the probability of lack of any successful swaps is a non issue, since it is likely that these steals were not important if all workers are trying to steal. \section{Safety and Productivity} -\CFA's actor system comes with a suite of safety and productivity features. Most of these features are present in \CFA's debug mode, but are removed when code is compiled in nodebug mode. The suit of features include the following. +\CFA's actor system comes with a suite of safety and productivity features. +Most of these features are present in \CFA's debug mode, but are removed when code is compiled in nodebug mode. +The suit of features include the following. \begin{itemize} -\item Static-typed message sends. If an actor does not support receiving a given message type, the actor program is rejected at compile time, allowing unsupported messages to never be sent to actors. -\item Detection of message sends to Finished/Destroyed/Deleted actors. All actors have a ticket that assigns them to a respective queue. The maximum integer value of the ticket is reserved to indicate that an actor is dead, and subsequent message sends result in an error. -\item Actors made before the executor can result in undefined behaviour since an executor needs to be created beforehand so it can give out the tickets to actors. As such, this is detected and an error is printed. -\item When an executor is created, the queues are handed out to worker threads in round robin order. If there are fewer queues than worker threads, then some workers will spin and never do any work. There is no reasonable use case for this behaviour so an error is printed if the number of queues is fewer than the number of worker threads. -\item A warning is printed when messages are deallocated without being sent. Since the \code{Finished} allocation status is unused for messages, it is used internally to detect if a message has been sent. Deallocating a message without sending it could indicate to a user that they are touching freed memory later, or it could point out extra allocations that could be removed. +\item Static-typed message sends. +If an actor does not support receiving a given message type, the actor program is rejected at compile time, allowing unsupported messages to never be sent to actors. +\item Detection of message sends to Finished/Destroyed/Deleted actors. +All actors have a ticket that assigns them to a respective queue. +The maximum integer value of the ticket is reserved to indicate that an actor is dead, and subsequent message sends result in an error. +\item Actors made before the executor can result in undefined behaviour since an executor needs to be created beforehand so it can give out the tickets to actors. +As such, this is detected and an error is printed. +\item When an executor is created, the queues are handed out to worker threads in round robin order. +If there are fewer queues than worker threads, then some workers will spin and never do any work. +There is no reasonable use case for this behaviour so an error is printed if the number of queues is fewer than the number of worker threads. +\item A warning is printed when messages are deallocated without being sent. +Since the \code{Finished} allocation status is unused for messages, it is used internally to detect if a message has been sent. +Deallocating a message without sending it could indicate to a user that they are touching freed memory later, or it could point out extra allocations that could be removed. \end{itemize} -In addition to these features, \CFA's actor system comes with a suite of statistics that can be toggled on and off. These statistics have minimal impact on the actor system's performance since they are counted on a per worker thread basis. During shutdown of the actor system they are aggregated, ensuring that the only atomic instructions used by the statistics counting happen at shutdown. The statistics measured are as follows. +In addition to these features, \CFA's actor system comes with a suite of statistics that can be toggled on and off. +These statistics have minimal impact on the actor system's performance since they are counted on a per worker thread basis. +During shutdown of the actor system they are aggregated, ensuring that the only atomic instructions used by the statistics counting happen at shutdown. +The statistics measured are as follows. \begin{description} \item[\LstBasicStyle{\textbf{Actors Created}}] -Actors created. Includes both actors made by the main and ones made by other actors. +Actors created. +Includes both actors made by the main and ones made by other actors. \item[\LstBasicStyle{\textbf{Messages Sent}}] -Messages sent and received. Includes termination messages send to the worker threads. +Messages sent and received. +Includes termination messages send to the worker threads. \item[\LstBasicStyle{\textbf{Gulps}}] Gulps that occured across the worker threads. @@ -359,4 +647,5 @@ \item[\LstBasicStyle{\textbf{Steal attempts}}] Worker threads attempts to steal work. + \item[\LstBasicStyle{\textbf{Steal failures (no candidates)}}] Work stealing failures due to selected victim not having any non empty or non-being-processed queues. @@ -369,13 +658,25 @@ \end{description} -These statistics enable a user of \CFA's actor system to make informed choices about how to configure their executor, or how to structure their actor program. For example, if there is a lot of messages being stolen relative to the number of messages sent, it could indicate to a user that their workload is heavily imbalanced across worker threads. In another example, if the average gulp size is very high, it could indicate that the executor could use more queue sharding. +These statistics enable a user of \CFA's actor system to make informed choices about how to configure their executor, or how to structure their actor program. +For example, if there is a lot of messages being stolen relative to the number of messages sent, it could indicate to a user that their workload is heavily imbalanced across worker threads. +In another example, if the average gulp size is very high, it could indicate that the executor could use more queue sharding. % C_TODO cite poison pill messages and add languages -Another productivity feature that is included is a group of poison-pill messages. Poison-pill messages are common across actor systems, including Akka and ProtoActor \cite{}. Poison-pill messages inform an actor to terminate. In \CFA, due to the allocation of actors and lack of garbage collection, there needs to be a suite of poison-pills. The messages that \CFA provides are \code{DeleteMsg}, \code{DestroyMsg}, and \code{FinishedMsg}. These messages are supported on all actor types via inheritance and when sent to an actor, the actor takes the corresponding allocation action after receiving the message. Note that any pending messages to the actor will still be sent. It is still the user's responsibility to ensure that an actor does not receive any messages after termination. +Another productivity feature that is included is a group of poison-pill messages. +Poison-pill messages are common across actor systems, including Akka and ProtoActor \cite{}. +Poison-pill messages inform an actor to terminate. +In \CFA, due to the allocation of actors and lack of garbage collection, there needs to be a suite of poison-pills. +The messages that \CFA provides are \code{DeleteMsg}, \code{DestroyMsg}, and \code{FinishedMsg}. +These messages are supported on all actor types via inheritance and when sent to an actor, the actor takes the corresponding allocation action after receiving the message. +Note that any pending messages to the actor will still be sent. +It is still the user's responsibility to ensure that an actor does not receive any messages after termination. \section{Performance}\label{s:actor_perf} The performance of \CFA's actor system is tested using a suite of microbenchmarks, and compared with other actor systems. -Most of the benchmarks are the same as those presented in \ref{}, with a few additions. % C_TODO cite actor paper -At the time of this work the versions of the actor systems are as follows. \CFA 1.0, \uC 7.0.0, Akka Typed 2.7.0, CAF 0.18.6, and ProtoActor-Go v0.0.0-20220528090104-f567b547ea07. Akka Classic is omitted as Akka Typed is their newest version and seems to be the direction they are headed in. +Most of the benchmarks are the same as those presented in \ref{}, with a few additions. +% C_TODO cite actor paper +At the time of this work the versions of the actor systems are as follows. +\CFA 1.0, \uC 7.0.0, Akka Typed 2.7.0, CAF 0.18.6, and ProtoActor-Go v0.0.0-20220528090104-f567b547ea07. +Akka Classic is omitted as Akka Typed is their newest version and seems to be the direction they are headed in. The experiments are run on \begin{list}{\arabic{enumi}.}{\usecounter{enumi}\topsep=5pt\parsep=5pt\itemsep=0pt} @@ -386,7 +687,14 @@ \end{list} -The benchmarks are run on up to 48 cores. On the Intel, when going beyond 24 cores there is the choice to either hop sockets or to use hyperthreads. Either choice will cause a blip in performance trends, which can be seen in the following performance figures. On the Intel the choice was made to hyperthread instead of hopping sockets for experiments with more than 24 cores. - -All benchmarks presented are run 5 times and the median is taken. Error bars showing the 95\% confidence intervals are drawn on each point on the graphs. If the confidence bars are small enough, they may be obscured by the point. In this section \uC will be compared to \CFA frequently, as the actor system in \CFA was heavily based off \uC's actor system. As such the peformance differences that arise are largely due to the contributions of this work. +The benchmarks are run on up to 48 cores. +On the Intel, when going beyond 24 cores there is the choice to either hop sockets or to use hyperthreads. +Either choice will cause a blip in performance trends, which can be seen in the following performance figures. +On the Intel the choice was made to hyperthread instead of hopping sockets for experiments with more than 24 cores. + +All benchmarks presented are run 5 times and the median is taken. +Error bars showing the 95\% confidence intervals are drawn on each point on the graphs. +If the confidence bars are small enough, they may be obscured by the point. +In this section \uC will be compared to \CFA frequently, as the actor system in \CFA was heavily based off \uC's actor system. +As such the peformance differences that arise are largely due to the contributions of this work. \begin{table}[t] @@ -420,12 +728,27 @@ \subsection{Message Sends} -Message sending is the key component of actor communication. As such latency of a single message send is the fundamental unit of fast-path performance for an actor system. The following two microbenchmarks evaluate the average latency for a static actor/message send and a dynamic actor/message send. Static and dynamic refer to the allocation of the message and actor. In the static send benchmark a message and actor are allocated once and then the message is sent to the same actor repeatedly until it has been sent 100 million (100M) times. The average latency per message send is then calculated by dividing the duration by the number of sends. This benchmark evaluates the cost of message sends in the actor use case where all actors and messages are allocated ahead of time and do not need to be created dynamically during execution. The CAF static send benchmark only sends a message 10M times to avoid extensively long run times. - -In the dynamic send benchmark the same experiment is performed, with the change that with each send a new actor and message is allocated. This evaluates the cost of message sends in the other common actor pattern where actors and message are created on the fly as the actor program tackles a workload of variable or unknown size. Since dynamic sends are more expensive, this benchmark repeats the actor/message creation and send 20M times (\uC, \CFA), or 2M times (Akka, CAF, ProtoActor), to give an appropriate benchmark duration. - -The results from the static/dynamic send benchmarks are shown in Figures~\ref{t:StaticActorMessagePerformance} and \ref{t:DynamicActorMessagePerformance} respectively. \CFA leads the charts in both benchmarks, largely due to the copy queue removing the majority of the envelope allocations. In the static send benchmark all systems except CAF have static send costs that are in the same ballpark, only varying by ~70ns. In the dynamic send benchmark all systems experience slower message sends, as expected due to the extra allocations. However, Akka and ProtoActor, slow down by a more significant margin than the \uC and \CFA. This is likely a result of Akka and ProtoActor's garbage collection, which can suffer from hits in performance for allocation heavy workloads, whereas \uC and \CFA have explicit allocation/deallocation. +Message sending is the key component of actor communication. +As such latency of a single message send is the fundamental unit of fast-path performance for an actor system. +The following two microbenchmarks evaluate the average latency for a static actor/message send and a dynamic actor/message send. +Static and dynamic refer to the allocation of the message and actor. +In the static send benchmark a message and actor are allocated once and then the message is sent to the same actor repeatedly until it has been sent 100 million (100M) times. +The average latency per message send is then calculated by dividing the duration by the number of sends. +This benchmark evaluates the cost of message sends in the actor use case where all actors and messages are allocated ahead of time and do not need to be created dynamically during execution. +The CAF static send benchmark only sends a message 10M times to avoid extensively long run times. + +In the dynamic send benchmark the same experiment is performed, with the change that with each send a new actor and message is allocated. +This evaluates the cost of message sends in the other common actor pattern where actors and message are created on the fly as the actor program tackles a workload of variable or unknown size. +Since dynamic sends are more expensive, this benchmark repeats the actor/message creation and send 20M times (\uC, \CFA), or 2M times (Akka, CAF, ProtoActor), to give an appropriate benchmark duration. + +The results from the static/dynamic send benchmarks are shown in Figures~\ref{t:StaticActorMessagePerformance} and \ref{t:DynamicActorMessagePerformance} respectively. +\CFA leads the charts in both benchmarks, largely due to the copy queue removing the majority of the envelope allocations. +In the static send benchmark all systems except CAF have static send costs that are in the same ballpark, only varying by ~70ns. +In the dynamic send benchmark all systems experience slower message sends, as expected due to the extra allocations. +However, Akka and ProtoActor, slow down by a more significant margin than the \uC and \CFA. +This is likely a result of Akka and ProtoActor's garbage collection, which can suffer from hits in performance for allocation heavy workloads, whereas \uC and \CFA have explicit allocation/deallocation. \subsection{Work Stealing} -\CFA's actor system has a work stealing mechanism which uses the longest victim heuristic, introduced in Section~ref{s:victimSelect}. In this performance section, \CFA with the longest victim heuristic is compared with other actor systems on the benchmark suite, and is separately compared with vanilla non-stealing \CFA and \CFA with randomized work stealing. +\CFA's actor system has a work stealing mechanism which uses the longest victim heuristic, introduced in Section~ref{s:victimSelect}. +In this performance section, \CFA with the longest victim heuristic is compared with other actor systems on the benchmark suite, and is separately compared with vanilla non-stealing \CFA and \CFA with randomized work stealing. \begin{figure} @@ -463,12 +786,33 @@ \end{figure} -There are two benchmarks in which \CFA's work stealing is solely evaluated. The main goal of introducing work stealing to \CFA's actor system is to eliminate the pathological unbalanced cases that can present themselves in a system without some form of load balancing. The following two microbenchmarks construct two such pathological cases, and compare the work stealing variations of \CFA. The balance benchmarks adversarily takes advantage of the round robin assignment of actors to load all actors that will do work on specific cores and create 'dummy' actors that terminate after a single message send on all other cores. The workload on the loaded cores is the same as the executor benchmark described in \ref{s:executorPerf}, but with fewer rounds. The balance-one benchmark loads all the work on a single core, whereas the balance-multi loads all the work on half the cores (every other core). Given this layout, one expects the ideal speedup of work stealing in the balance-one case to be $N / N - 1$ where $N$ is the number of threads. In the balance-multi case the ideal speedup is 0.5. Note that in the balance-one benchmark the workload is fixed so decreasing runtime is expected. In the balance-multi experiment, the workload increases with the number of cores so an increasing or constant runtime is expected. - -On both balance microbenchmarks slightly less than ideal speedup compared to the non stealing variation is achieved by both the random and longest victim stealing heuristics. On the balance-multi benchmark \ref{f:BalanceMultiAMD},\ref{f:BalanceMultiIntel} the random heuristic outperforms the longest victim. This is likely a result of the longest victim heuristic having a higher stealing cost as it needs to maintain timestamps and look at all timestamps before stealing. Additionally, a performance cost can be observed when hyperthreading kicks in in Figure~\ref{f:BalanceMultiIntel}. - -In the balance-one benchmark on AMD \ref{f:BalanceOneAMD}, the performance bottoms out at 32 cores onwards likely due to the amount of work becoming less than the cost to steal it and move it across cores and cache. On Intel \ref{f:BalanceOneIntel}, above 32 cores the performance gets worse for all variants due to hyperthreading. Note that the non stealing variation of balance-one will slow down marginally as the cores increase due to having to create more dummy actors on the inactive cores during startup. +There are two benchmarks in which \CFA's work stealing is solely evaluated. +The main goal of introducing work stealing to \CFA's actor system is to eliminate the pathological unbalanced cases that can present themselves in a system without some form of load balancing. +The following two microbenchmarks construct two such pathological cases, and compare the work stealing variations of \CFA. +The balance benchmarks adversarily takes advantage of the round robin assignment of actors to load all actors that will do work on specific cores and create 'dummy' actors that terminate after a single message send on all other cores. +The workload on the loaded cores is the same as the executor benchmark described in \ref{s:executorPerf}, but with fewer rounds. +The balance-one benchmark loads all the work on a single core, whereas the balance-multi loads all the work on half the cores (every other core). +Given this layout, one expects the ideal speedup of work stealing in the balance-one case to be $N / N - 1$ where $N$ is the number of threads. +In the balance-multi case the ideal speedup is 0.5. +Note that in the balance-one benchmark the workload is fixed so decreasing runtime is expected. +In the balance-multi experiment, the workload increases with the number of cores so an increasing or constant runtime is expected. + +On both balance microbenchmarks slightly less than ideal speedup compared to the non stealing variation is achieved by both the random and longest victim stealing heuristics. +On the balance-multi benchmark \ref{f:BalanceMultiAMD},\ref{f:BalanceMultiIntel} the random heuristic outperforms the longest victim. +This is likely a result of the longest victim heuristic having a higher stealing cost as it needs to maintain timestamps and look at all timestamps before stealing. +Additionally, a performance cost can be observed when hyperthreading kicks in in Figure~\ref{f:BalanceMultiIntel}. + +In the balance-one benchmark on AMD \ref{f:BalanceOneAMD}, the performance bottoms out at 32 cores onwards likely due to the amount of work becoming less than the cost to steal it and move it across cores and cache. +On Intel \ref{f:BalanceOneIntel}, above 32 cores the performance gets worse for all variants due to hyperthreading. +Note that the non stealing variation of balance-one will slow down marginally as the cores increase due to having to create more dummy actors on the inactive cores during startup. \subsection{Executor}\label{s:executorPerf} -The microbenchmarks in this section are designed to stress the executor. The executor is the scheduler of an actor system and is responsible for organizing the interaction of worker threads to service the needs of a workload. In the executor benchmark, 40'000 actors are created and assigned a group. Each group of actors is a group of 100 actors who send and receive 100 messages from all other actors in their group. Each time an actor completes all their sends and receives, they are done a round. After all groups have completed 400 rounds the system terminates. This microbenchmark is designed to flood the executor with a large number of messages flowing between actors. Given there is no work associated with each message, other than sending more messages, the intended bottleneck of this experiment is the executor message send process. +The microbenchmarks in this section are designed to stress the executor. +The executor is the scheduler of an actor system and is responsible for organizing the interaction of worker threads to service the needs of a workload. +In the executor benchmark, 40'000 actors are created and assigned a group. +Each group of actors is a group of 100 actors who send and receive 100 messages from all other actors in their group. +Each time an actor completes all their sends and receives, they are done a round. +After all groups have completed 400 rounds the system terminates. +This microbenchmark is designed to flood the executor with a large number of messages flowing between actors. +Given there is no work associated with each message, other than sending more messages, the intended bottleneck of this experiment is the executor message send process. \begin{figure} @@ -489,5 +833,9 @@ \end{figure} -The results of the executor benchmark in Figures~\ref{f:ExecutorIntel} and \ref{f:ExecutorAMD} show \CFA with the lowest runtime relative to its peers. The difference in runtime between \uC and \CFA is largely due to the usage of the copy queue described in Section~\ref{s:copyQueue}. The copy queue both reduces and consolidates allocations, heavily reducing contention on the memory allocator. Additionally, due to the static typing in \CFA's actor system, it is able to get rid of expensive dynamic casts that occur in \uC to disciminate messages by type. Note that dynamic casts are ususally not very expensive, but relative to the high performance of the rest of the implementation of the \uC actor system, the cost is significant. +The results of the executor benchmark in Figures~\ref{f:ExecutorIntel} and \ref{f:ExecutorAMD} show \CFA with the lowest runtime relative to its peers. +The difference in runtime between \uC and \CFA is largely due to the usage of the copy queue described in Section~\ref{s:copyQueue}. +The copy queue both reduces and consolidates allocations, heavily reducing contention on the memory allocator. +Additionally, due to the static typing in \CFA's actor system, it is able to get rid of expensive dynamic casts that occur in \uC to disciminate messages by type. +Note that dynamic casts are ususally not very expensive, but relative to the high performance of the rest of the implementation of the \uC actor system, the cost is significant. \begin{figure} @@ -523,5 +871,12 @@ \end{figure} -The repeat microbenchmark also evaluates the executor. It stresses the executor's ability to withstand contention on queues, as it repeatedly fans out messages from a single client to 100000 servers who then all respond to the client. After this scatter and gather repeats 200 times the benchmark terminates. The messages from the servers to the client will likely all come in on the same queue, resulting in high contention. As such this benchmark will not scale with the number of processors, since more processors will result in higher contention. In Figure~\ref{f:RepeatAMD} we can see that \CFA performs well compared to \uC, however by less of a margin than the executor benchmark. One factor in this result is that the contention on the queues poses a significant bottleneck. As such the gains from using the copy queue are much less apparent. +The repeat microbenchmark also evaluates the executor. +It stresses the executor's ability to withstand contention on queues, as it repeatedly fans out messages from a single client to 100000 servers who then all respond to the client. +After this scatter and gather repeats 200 times the benchmark terminates. +The messages from the servers to the client will likely all come in on the same queue, resulting in high contention. +As such this benchmark will not scale with the number of processors, since more processors will result in higher contention. +In Figure~\ref{f:RepeatAMD} we can see that \CFA performs well compared to \uC, however by less of a margin than the executor benchmark. +One factor in this result is that the contention on the queues poses a significant bottleneck. +As such the gains from using the copy queue are much less apparent. \begin{figure} @@ -541,8 +896,19 @@ In Figure~\ref{f:RepeatIntel} \uC and \CFA are very comparable. -In comparison with the other systems \uC does well on the repeat benchmark since it does not have work stealing. The client of this experiment is long running and maintains a lot of state, as it needs to know the handles of all the servers. When stealing the client or its respective queue (in \CFA's inverted model), moving the client incurs a high cost due to cache invalidation. As such stealing the client can result in a hit in performance. +In comparison with the other systems \uC does well on the repeat benchmark since it does not have work stealing. +The client of this experiment is long running and maintains a lot of state, as it needs to know the handles of all the servers. +When stealing the client or its respective queue (in \CFA's inverted model), moving the client incurs a high cost due to cache invalidation. +As such stealing the client can result in a hit in performance. + This result is shown in Figure~\ref{f:cfaRepeatAMD} and \ref{f:cfaRepeatIntel} where the no-stealing version of \CFA performs better than both stealing variations. -In particular on the Intel machine in Figure~\ref{f:cfaRepeatIntel}, the cost of stealing is higher, which can be seen in the vertical shift of Akka, CAF and CFA results in Figure~\ref{f:RepeatIntel} (\uC and ProtoActor do not have work stealing). The shift for CAF is particularly large, which further supports the hypothesis that CAF's work stealing is particularly eager. -In both the executor and the repeat benchmark CAF performs poorly. It is hypothesized that CAF has an aggressive work stealing algorithm, that eagerly attempts to steal. This results in poor performance in benchmarks with small messages containing little work per message. On the other hand, in \ref{f:MatrixAMD} CAF performs much better since each message has a large amount of work, and few messages are sent, so the eager work stealing allows for the clean up of loose ends to occur faster. This hypothesis stems from experimentation with \CFA. CAF uses a randomized work stealing heuristic. In \CFA if the system is tuned so that it steals work much more eagerly with a randomized it was able to replicate the results that CAF achieves in the matrix benchmark, but this tuning performed much worse on all other microbenchmarks that we present, since they all perform a small amount of work per message. +In particular on the Intel machine in Figure~\ref{f:cfaRepeatIntel}, the cost of stealing is higher, which can be seen in the vertical shift of Akka, CAF and CFA results in Figure~\ref{f:RepeatIntel} (\uC and ProtoActor do not have work stealing). +The shift for CAF is particularly large, which further supports the hypothesis that CAF's work stealing is particularly eager. +In both the executor and the repeat benchmark CAF performs poorly. +It is hypothesized that CAF has an aggressive work stealing algorithm, that eagerly attempts to steal. +This results in poor performance in benchmarks with small messages containing little work per message. +On the other hand, in \ref{f:MatrixAMD} CAF performs much better since each message has a large amount of work, and few messages are sent, so the eager work stealing allows for the clean up of loose ends to occur faster. +This hypothesis stems from experimentation with \CFA. +CAF uses a randomized work stealing heuristic. +In \CFA if the system is tuned so that it steals work much more eagerly with a randomized it was able to replicate the results that CAF achieves in the matrix benchmark, but this tuning performed much worse on all other microbenchmarks that we present, since they all perform a small amount of work per message. \begin{table}[t] @@ -562,8 +928,11 @@ \end{table} -Figure~\ref{t:ExecutorMemory} shows the high memory watermark of the actor systems when running the executor benchmark on 48 cores. \CFA has a high watermark relative to the other non-garbage collected systems \uC, and CAF. This is a result of the copy queue data structure, as it will overallocate storage and not clean up eagerly, whereas the per envelope allocations will always allocate exactly the amount of storage needed. +Figure~\ref{t:ExecutorMemory} shows the high memory watermark of the actor systems when running the executor benchmark on 48 cores. +\CFA has a high watermark relative to the other non-garbage collected systems \uC, and CAF. +This is a result of the copy queue data structure, as it will overallocate storage and not clean up eagerly, whereas the per envelope allocations will always allocate exactly the amount of storage needed. \subsection{Matrix Multiply} -The matrix benchmark evaluates the actor systems in a practical application, where actors concurrently multiplies two matrices. The majority of the computation in this benchmark involves computing the final matrix, so this benchmark stresses the actor systems' ability to have actors run work, rather than stressing the executor or message sending system. +The matrix benchmark evaluates the actor systems in a practical application, where actors concurrently multiplies two matrices. +The majority of the computation in this benchmark involves computing the final matrix, so this benchmark stresses the actor systems' ability to have actors run work, rather than stressing the executor or message sending system. Given $Z_{m,r} = X_{m,n} \cdot Y_{n,r}$, the matrix multiply is defined as: @@ -572,7 +941,12 @@ \end{displaymath} -The benchmark uses input matrices $X$ and $Y$ that are both $3072$ by $3072$ in size. An actor is made for each row of $X$ and is passed via message the information needed to calculate a row of the result matrix $Z$. - -Given that the bottleneck of the benchmark is the computation of the result matrix, it follows that the results in Figures~\ref{f:MatrixAMD} and \ref{f:MatrixIntel} are clustered closer than other experiments. In Figure~\ref{f:MatrixAMD} \uC and \CFA have identical performance and in Figure~\ref{f:MatrixIntel} \uC pulls ahead og \CFA after 24 cores likely due to costs associated with work stealing while hyperthreading. As mentioned in \ref{s:executorPerf}, it is hypothesized that CAF performs better in this benchmark compared to others due to its eager work stealing implementation. In Figures~\ref{f:cfaMatrixAMD} and \ref{f:cfaMatrixIntel} there is little negligible performance difference across \CFA stealing heuristics. +The benchmark uses input matrices $X$ and $Y$ that are both $3072$ by $3072$ in size. +An actor is made for each row of $X$ and is passed via message the information needed to calculate a row of the result matrix $Z$. + + +Given that the bottleneck of the benchmark is the computation of the result matrix, it follows that the results in Figures~\ref{f:MatrixAMD} and \ref{f:MatrixIntel} are clustered closer than other experiments. +In Figure~\ref{f:MatrixAMD} \uC and \CFA have identical performance and in Figure~\ref{f:MatrixIntel} \uC pulls ahead og \CFA after 24 cores likely due to costs associated with work stealing while hyperthreading. +As mentioned in \ref{s:executorPerf}, it is hypothesized that CAF performs better in this benchmark compared to others due to its eager work stealing implementation. +In Figures~\ref{f:cfaMatrixAMD} and \ref{f:cfaMatrixIntel} there is little negligible performance difference across \CFA stealing heuristics. \begin{figure} Index: doc/theses/colby_parsons_MMAth/text/channels.tex =================================================================== --- doc/theses/colby_parsons_MMAth/text/channels.tex (revision fa6ca1ac779b46c587efb95ae262f52a9c5378e0) +++ doc/theses/colby_parsons_MMAth/text/channels.tex (revision 34b6a7b6878154693f83696df612a4adeee0fb87) @@ -5,40 +5,116 @@ % ====================================================================== -Channels were first introduced by Hoare in his paper Communicating Sequentual Processes~\cite{Hoare78}, where he proposes a concurrent language that communicates across processes using input/output channels to send data. Channels are a concurrent language feature used to perform message passing concurrency, a model of concurrency where threads communicate by sending data as messages, and synchronizing via the message passing mechanism. This is an alternative to shared memory concurrency, where threads can communicate directly by changing shared memory state. Most modern concurrent programming languages do not subscribe to just one style of communication between threads, and provide features that support both. Channels as a programming language feature has been popularized in recent years due to the language Go, which encourages the use of channels as its fundamental concurrent feature. +Channels were first introduced by Hoare in his paper Communicating Sequentual Processes~\cite{Hoare78}, where he proposes a concurrent language that communicates across processes using input/output channels to send data. +Channels are a concurrent language feature used to perform message passing concurrency, a model of concurrency where threads communicate by sending data as messages, and synchronizing via the message passing mechanism. +This is an alternative to shared memory concurrency, where threads can communicate directly by changing shared memory state. +Most modern concurrent programming languages do not subscribe to just one style of communication between threads, and provide features that support both. +Channels as a programming language feature has been popularized in recent years due to the language Go, which encourages the use of channels as its fundamental concurrent feature. \section{Producer-Consumer Problem} -Most channels in modern programming languages are built on top of a shared memory buffer. While it is possible to create a channel that contains an unbounded buffer, most implementations opt to only support a fixed size channel, where the size is given at the time of channel creation. This turns the implementation of a channel into the producer-consumer problem. The producer-consumer problem, also known as the bounded buffer problem, was introduced by Dijkstra in his book Cooperating Sequential Processes\cite{Dijkstra65}. In the problem threads interact with the buffer in two ways, either consuming values by removing them from the buffer, or producing values and inserting them in the buffer. The buffer needs to be protected from concurrent access since each item in the buffer should only be produced and consumed once. Additionally, a consumer can only remove from a non-empty buffer and a producer can only insert into a non-full buffer. +Most channels in modern programming languages are built on top of a shared memory buffer. +While it is possible to create a channel that contains an unbounded buffer, most implementations opt to only support a fixed size channel, where the size is given at the time of channel creation. +This turns the implementation of a channel into the producer-consumer problem. +The producer-consumer problem, also known as the bounded buffer problem, was introduced by Dijkstra in his book Cooperating Sequential Processes\cite{Dijkstra65}. +In the problem threads interact with the buffer in two ways, either consuming values by removing them from the buffer, or producing values and inserting them in the buffer. +The buffer needs to be protected from concurrent access since each item in the buffer should only be produced and consumed once. +Additionally, a consumer can only remove from a non-empty buffer and a producer can only insert into a non-full buffer. \section{First-Come First-Served} -The channel implementations that will be discussed are \newterm{First-Come First-Served} (FCFS). This term was defined by Lamport~\cite{Lamport74}. FCFS is defined in relation to a \newterm{doorway}~\cite[p.~330]{Lamport86II}, which is the point at which an ordering among threads can be established. Given this doorway, a critical section is said to be FCFS, if threads access the shared resource in the order they proceed through the doorway. FCFS is a fairness property which prevents unequal access to the shared resource and prevents starvation, however it can come at a cost. Implementing an algorithm with FCFS can lead to \newterm{double blocking}, where entering threads may need to block to allow other threads to proceed first, resulting in blocking both inside and outside the doorway. As such algorithms that are not FCFS may be more performant but that performance comes with the downside of likely introducing starvation and unfairness. +The channel implementations that will be discussed are \gls{fcfs}. +This term was defined by Lamport~\cite{Lamport74}. +\gls{fcfs} is defined in relation to a doorway~\cite[p.~330]{Lamport86II}, which is the point at which an ordering among threads can be established. +Given this doorway, a critical section is said to be \gls{fcfs}, if threads access the shared resource in the order they proceed through the doorway. +\gls{fcfs} is a fairness property which prevents unequal access to the shared resource and prevents starvation, however it can come at a cost. +Implementing an algorithm with \gls{fcfs} can lead to double blocking, where entering threads may need to block to allow other threads to proceed first, resulting in blocking both inside and outside the doorway. +As such algorithms that are not \gls{fcfs} may be more performant but that performance comes with the downside of likely introducing starvation and unfairness. \section{Channel Implementation} -The channel implementation in \CFA is a near carbon copy of the Go implementation. Experimentation was conducted that varied the producer-consumer problem algorithm and lock type used inside the channel. With the exception of non-FCFS algorithms, no algorithm or lock usage in the channel implementation was found to be consistently more performant that Go's choice of algorithm and lock implementation. As such the research contributions added by \CFA's channel implementation lie in the realm of safety and productivity features. +The channel implementation in \CFA is a near carbon copy of the Go implementation. +Experimentation was conducted that varied the producer-consumer problem algorithm and lock type used inside the channel. +With the exception of non-\gls{fcfs} algorithms, no algorithm or lock usage in the channel implementation was found to be consistently more performant that Go's choice of algorithm and lock implementation. +As such the research contributions added by \CFA's channel implementation lie in the realm of safety and productivity features. \section{Safety and Productivity} -Channels in \CFA come with safety and productivity features to aid users. The features include the following. +Channels in \CFA come with safety and productivity features to aid users. +The features include the following. \begin{itemize} -\item Toggle-able statistic collection on channel behvaiour that counts channel operations, and the number of the operations that block. Tracking blocking operations helps users tune their channel size or channel usage when the channel is used for buffering, where the aim is to have as few blocking operations as possible. -\item Deadlock detection on deallocation of the channel. If any threads are blocked inside the channel when it terminates it is detected and informs the user, as this would cause a deadlock. -\item A \code{flush} routine that delivers copies of an element to all waiting consumers, flushing the buffer. Programmers can use this to easily to broadcast data to multiple consumers. Additionally, the \code{flush} routine is more performant then looping around the \code{insert} operation since it can deliver the elements without having to reaquire mutual exclusion for each element sent. +\item Toggle-able statistic collection on channel behvaiour that counts channel operations, and the number of the operations that block. +Tracking blocking operations helps users tune their channel size or channel usage when the channel is used for buffering, where the aim is to have as few blocking operations as possible. +\item Deadlock detection on deallocation of the channel. +If any threads are blocked inside the channel when it terminates it is detected and informs the user, as this would cause a deadlock. +\item A \code{flush} routine that delivers copies of an element to all waiting consumers, flushing the buffer. +Programmers can use this to easily to broadcast data to multiple consumers. +Additionally, the \code{flush} routine is more performant then looping around the \code{insert} operation since it can deliver the elements without having to reaquire mutual exclusion for each element sent. \end{itemize} -The other safety and productivity feature of \CFA channels deals with concurrent termination. Terminating concurrent programs is often one of the most difficult parts of writing concurrent code, particularly if graceful termination is needed. The difficulty of graceful termination often arises from the usage of synchronization primitives which need to be handled carefully during shutdown. It is easy to deadlock during termination if threads are left behind on synchronization primitives. Additionally, most synchronization primitives are prone to time-of-check to time-of-use (TOCTOU) issues where there is race between one thread checking the state of a concurrent object and another thread changing the state. TOCTOU issues with synchronization primitives often involve a race between one thread checking the primitive for blocked threads and another thread blocking on it. Channels are a particularly hard synchronization primitive to terminate since both sending and receiving off a channel can block. Thus, improperly handled TOCTOU issues with channels often result in deadlocks as threads trying to perform the termination may end up unexpectedly blocking in their attempt to help other threads exit the system. +The other safety and productivity feature of \CFA channels deals with concurrent termination. +Terminating concurrent programs is often one of the most difficult parts of writing concurrent code, particularly if graceful termination is needed. +The difficulty of graceful termination often arises from the usage of synchronization primitives which need to be handled carefully during shutdown. +It is easy to deadlock during termination if threads are left behind on synchronization primitives. +Additionally, most synchronization primitives are prone to \gls{toctou} issues where there is race between one thread checking the state of a concurrent object and another thread changing the state. +\gls{toctou} issues with synchronization primitives often involve a race between one thread checking the primitive for blocked threads and another thread blocking on it. +Channels are a particularly hard synchronization primitive to terminate since both sending and receiving off a channel can block. +Thus, improperly handled \gls{toctou} issues with channels often result in deadlocks as threads trying to perform the termination may end up unexpectedly blocking in their attempt to help other threads exit the system. % C_TODO: add reference to select chapter, add citation to go channels info -Go channels provide a set of tools to help with concurrent shutdown. Channels in Go have a \code{close} operation and a \code{select} statement that both can be used to help threads terminate. The \code{select} statement will be discussed in \ref{}, where \CFA's \code{waituntil} statement will be compared with the Go \code{select} statement. The \code{close} operation on a channel in Go changes the state of the channel. When a channel is closed, sends to the channel will panic and additional calls to \code{close} will panic. Receives are handled differently where receivers will never block on a closed channel and will continue to remove elements from the channel. Once a channel is empty, receivers can continue to remove elements, but will receive the zero-value version of the element type. To aid in avoiding unwanted zero-value elements, Go provides the ability to iterate over a closed channel to remove the remaining elements. These design choices for Go channels enforce a specific interaction style with channels during termination, where careful thought is needed to ensure that additional \code{close} calls don't occur and that no sends occur after channels are closed. These design choices fit Go's paradigm of error management, where users are expected to explicitly check for errors, rather than letting errors occur and catching them. If errors need to occur in Go, return codes are used to pass error information where they are needed. Note that panics in Go can be caught, but it is not considered an idiomatic way to write Go programs. - -While Go's channel closing semantics are powerful enough to perform any concurrent termination needed by a program, their lack of ease of use leaves much to be desired. Since both closing and sending panic, once a channel is closed, a user often has to synchronize the senders to a channel before the channel can be closed to avoid panics. However, in doing so it renders the \code{close} operation nearly useless, as the only utilities it provides are the ability to ensure that receivers no longer block on the channel, and will receive zero-valued elements. This can be useful if the zero-typed element is recognized as a sentinel value, but if another sentinel value is preferred, then \code{close} only provides its non-blocking feature. To avoid TOCTOU issues during shutdown, a busy wait with a \code{select} statement is often used to add or remove elements from a channel. Due to Go's asymmetric approach to channel shutdown, separate synchronization between producers and consumers of a channel has to occur during shutdown. - -In \CFA, exception handling is an encouraged paradigm and has full language support \cite{}. -% \cite{Beach21}. TODO: this citation breaks when compiled. Need to fix and insert above +Go channels provide a set of tools to help with concurrent shutdown. +Channels in Go have a \code{close} operation and a \code{select} statement that both can be used to help threads terminate. +The \code{select} statement will be discussed in \ref{}, where \CFA's \code{waituntil} statement will be compared with the Go \code{select} statement. +The \code{close} operation on a channel in Go changes the state of the channel. +When a channel is closed, sends to the channel will panic and additional calls to \code{close} will panic. +Receives are handled differently where receivers will never block on a closed channel and will continue to remove elements from the channel. +Once a channel is empty, receivers can continue to remove elements, but will receive the zero-value version of the element type. +To aid in avoiding unwanted zero-value elements, Go provides the ability to iterate over a closed channel to remove the remaining elements. +These design choices for Go channels enforce a specific interaction style with channels during termination, where careful thought is needed to ensure that additional \code{close} calls don't occur and that no sends occur after channels are closed. +These design choices fit Go's paradigm of error management, where users are expected to explicitly check for errors, rather than letting errors occur and catching them. +If errors need to occur in Go, return codes are used to pass error information where they are needed. +Note that panics in Go can be caught, but it is not considered an idiomatic way to write Go programs. + +While Go's channel closing semantics are powerful enough to perform any concurrent termination needed by a program, their lack of ease of use leaves much to be desired. +Since both closing and sending panic, once a channel is closed, a user often has to synchronize the senders to a channel before the channel can be closed to avoid panics. +However, in doing so it renders the \code{close} operation nearly useless, as the only utilities it provides are the ability to ensure that receivers no longer block on the channel, and will receive zero-valued elements. +This can be useful if the zero-typed element is recognized as a sentinel value, but if another sentinel value is preferred, then \code{close} only provides its non-blocking feature. +To avoid \gls{toctou} issues during shutdown, a busy wait with a \code{select} statement is often used to add or remove elements from a channel. +Due to Go's asymmetric approach to channel shutdown, separate synchronization between producers and consumers of a channel has to occur during shutdown. + +In \CFA, exception handling is an encouraged paradigm and has full language support \cite{Beach21}. As such \CFA uses an exception based approach to channel shutdown that is symmetric for both producers and consumers, and supports graceful shutdown.Exceptions in \CFA support both termination and resumption.Termination exceptions operate in the same way as exceptions seen in many popular programming languages such as \CC, Python and Java. Resumption exceptions are a style of exception that when caught run the corresponding catch block in the same way that termination exceptions do. -The difference between the exception handling mechanisms arises after the exception is handled. In termination handling, the control flow continues into the code following the catch after the exception is handled. In resumption handling, the control flow returns to the site of the \code{throw}, allowing the control to continue where it left off. Note that in resumption, since control can return to the point of error propagation, the stack is not unwound during resumption propagation. In \CFA if a resumption is not handled, it is reraised as a termination. This mechanism can be used to create a flexible and robust termination system for channels. - -When a channel in \CFA is closed, all subsequent calls to the channel will throw a resumption exception at the caller. If the resumption is handled, then the caller will proceed to attempt to complete their operation. If the resumption is not handled it is then rethrown as a termination exception. Or, if the resumption is handled, but the subsequent attempt at an operation would block, a termination exception is thrown. These termination exceptions allow for non-local transfer that can be used to great effect to eagerly and gracefully shut down a thread. When a channel is closed, if there are any blocked producers or consumers inside the channel, they are woken up and also have a resumption thrown at them. The resumption exception, \code{channel_closed}, has a couple fields to aid in handling the exception. The exception contains a pointer to the channel it was thrown from, and a pointer to an element. In exceptions thrown from remove the element pointer will be null. In the case of insert the element pointer points to the element that the thread attempted to insert. This element pointer allows the handler to know which operation failed and also allows the element to not be lost on a failed insert since it can be moved elsewhere in the handler. Furthermore, due to \CFA's powerful exception system, this data can be used to choose handlers based which channel and operation failed. Exception handlers in \CFA have an optional predicate after the exception type which can be used to optionally trigger or skip handlers based on the content of an exception. It is worth mentioning that the approach of exceptions for termination may incur a larger performance cost during termination that the approach used in Go. This should not be an issue, since termination is rarely an fast-path of an application and ensuring that termination can be implemented correctly with ease is the aim of the exception approach. - -To highlight the differences between \CFA's and Go's close semantics, an example program is presented. The program is a barrier implemented using two channels shown in Listings~\ref{l:cfa_chan_bar} and \ref{l:go_chan_bar}. Both of these exaples are implmented using \CFA syntax so that they can be easily compared. Listing~\ref{l:go_chan_bar} uses go-style channel close semantics and Listing~\ref{l:cfa_chan_bar} uses \CFA close semantics. In this problem it is infeasible to use the Go \code{close} call since all tasks are both potentially producers and consumers, causing panics on close to be unavoidable. As such in Listing~\ref{l:go_chan_bar} to implement a flush routine for the buffer, a sentinel value of $-1$ has to be used to indicate to threads that they need to leave the barrier. This sentinel value has to be checked at two points. Furthermore, an additional flag \code{done} is needed to communicate to threads once they have left the barrier that they are done. This use of an additional flag or communication method is common in Go channel shutdown code, since to avoid panics on a channel, the shutdown of a channel often has to be communicated with threads before it occurs. In the \CFA version~\ref{l:cfa_chan_bar}, the barrier shutdown results in an exception being thrown at threads operating on it, which informs the threads that they must terminate. This avoids the need to use a separate communication method other than the barrier, and avoids extra conditional checks on the fast path of the barrier implementation. Also note that in the Go version~\ref{l:go_chan_bar}, the size of the barrier channels has to be larger than in the \CFA version to ensure that the main thread does not block when attempting to clear the barrier. +The difference between the exception handling mechanisms arises after the exception is handled. +In termination handling, the control flow continues into the code following the catch after the exception is handled. +In resumption handling, the control flow returns to the site of the \code{throw}, allowing the control to continue where it left off. +Note that in resumption, since control can return to the point of error propagation, the stack is not unwound during resumption propagation. +In \CFA if a resumption is not handled, it is reraised as a termination. +This mechanism can be used to create a flexible and robust termination system for channels. + +When a channel in \CFA is closed, all subsequent calls to the channel will throw a resumption exception at the caller. +If the resumption is handled, then the caller will proceed to attempt to complete their operation. +If the resumption is not handled it is then rethrown as a termination exception. +Or, if the resumption is handled, but the subsequent attempt at an operation would block, a termination exception is thrown. +These termination exceptions allow for non-local transfer that can be used to great effect to eagerly and gracefully shut down a thread. +When a channel is closed, if there are any blocked producers or consumers inside the channel, they are woken up and also have a resumption thrown at them. +The resumption exception, \code{channel_closed}, has a couple fields to aid in handling the exception. +The exception contains a pointer to the channel it was thrown from, and a pointer to an element. +In exceptions thrown from remove the element pointer will be null. +In the case of insert the element pointer points to the element that the thread attempted to insert. +This element pointer allows the handler to know which operation failed and also allows the element to not be lost on a failed insert since it can be moved elsewhere in the handler. +Furthermore, due to \CFA's powerful exception system, this data can be used to choose handlers based which channel and operation failed. +Exception handlers in \CFA have an optional predicate after the exception type which can be used to optionally trigger or skip handlers based on the content of an exception. +It is worth mentioning that the approach of exceptions for termination may incur a larger performance cost during termination that the approach used in Go. +This should not be an issue, since termination is rarely an fast-path of an application and ensuring that termination can be implemented correctly with ease is the aim of the exception approach. + +To highlight the differences between \CFA's and Go's close semantics, an example program is presented. +The program is a barrier implemented using two channels shown in Listings~\ref{l:cfa_chan_bar} and \ref{l:go_chan_bar}. +Both of these exaples are implmented using \CFA syntax so that they can be easily compared. +Listing~\ref{l:go_chan_bar} uses go-style channel close semantics and Listing~\ref{l:cfa_chan_bar} uses \CFA close semantics. +In this problem it is infeasible to use the Go \code{close} call since all tasks are both potentially producers and consumers, causing panics on close to be unavoidable. +As such in Listing~\ref{l:go_chan_bar} to implement a flush routine for the buffer, a sentinel value of $-1$ has to be used to indicate to threads that they need to leave the barrier. +This sentinel value has to be checked at two points. +Furthermore, an additional flag \code{done} is needed to communicate to threads once they have left the barrier that they are done. +This use of an additional flag or communication method is common in Go channel shutdown code, since to avoid panics on a channel, the shutdown of a channel often has to be communicated with threads before it occurs. +In the \CFA version~\ref{l:cfa_chan_bar}, the barrier shutdown results in an exception being thrown at threads operating on it, which informs the threads that they must terminate. +This avoids the need to use a separate communication method other than the barrier, and avoids extra conditional checks on the fast path of the barrier implementation. +Also note that in the Go version~\ref{l:go_chan_bar}, the size of the barrier channels has to be larger than in the \CFA version to ensure that the main thread does not block when attempting to clear the barrier. \begin{cfacode}[tabsize=3,caption={\CFA channel barrier termination},label={l:cfa_chan_bar}] @@ -163,5 +239,8 @@ \end{cfacode} -In Listing~\ref{l:cfa_resume} an example of channel closing with resumption is used. This program uses resumption in the \code{Consumer} thread main to ensure that all elements in the channel are removed before the consumer thread terminates. The producer only has a \code{catch} so the moment it receives an exception it terminates, whereas the consumer will continue to remove from the closed channel via handling resumptions until the buffer is empty, which then throws a termination exception. If the same program was implemented in Go it would require explicit synchronization with both producers and consumers by some mechanism outside the channel to ensure that all elements were removed before task termination. +In Listing~\ref{l:cfa_resume} an example of channel closing with resumption is used. +This program uses resumption in the \code{Consumer} thread main to ensure that all elements in the channel are removed before the consumer thread terminates. +The producer only has a \code{catch} so the moment it receives an exception it terminates, whereas the consumer will continue to remove from the closed channel via handling resumptions until the buffer is empty, which then throws a termination exception. +If the same program was implemented in Go it would require explicit synchronization with both producers and consumers by some mechanism outside the channel to ensure that all elements were removed before task termination. \begin{cfacode}[tabsize=3,caption={\CFA channel resumption usage},label={l:cfa_resume}] @@ -205,5 +284,12 @@ \section{Performance} -Given that the base implementation of the \CFA channels is very similar to the Go implementation, this section aims to show that the performance of the two implementations are comparable. One microbenchmark is conducted to compare Go and \CFA. The benchmark is a ten second experiment where producers and consumers operate on a channel in parallel and throughput is measured. The number of cores is varied to measure how throughtput scales. The cores are divided equally between producers and consumers, with one producer or consumer owning each core. The results of the benchmark are shown in Figure~\ref{f:chanPerf}. The performance of Go and \CFA channels on this microbenchmark is comparable. Note, it is expected for the performance to decline as the number of cores increases as the channel operations all occur in a critical section so an increase in cores results in higher contention with no increase in parallelism. +Given that the base implementation of the \CFA channels is very similar to the Go implementation, this section aims to show that the performance of the two implementations are comparable. +One microbenchmark is conducted to compare Go and \CFA. +The benchmark is a ten second experiment where producers and consumers operate on a channel in parallel and throughput is measured. +The number of cores is varied to measure how throughtput scales. +The cores are divided equally between producers and consumers, with one producer or consumer owning each core. +The results of the benchmark are shown in Figure~\ref{f:chanPerf}. +The performance of Go and \CFA channels on this microbenchmark is comparable. +Note, it is expected for the performance to decline as the number of cores increases as the channel operations all occur in a critical section so an increase in cores results in higher contention with no increase in parallelism. Index: doc/theses/colby_parsons_MMAth/text/frontpgs.tex =================================================================== --- doc/theses/colby_parsons_MMAth/text/frontpgs.tex (revision fa6ca1ac779b46c587efb95ae262f52a9c5378e0) +++ doc/theses/colby_parsons_MMAth/text/frontpgs.tex (revision 34b6a7b6878154693f83696df612a4adeee0fb87) @@ -1,7 +1,7 @@ % T I T L E P A G E % ------------------- -% Last updated May 24, 2011, by Stephen Carr, IST-Client Services +% Last updated August 16, 2022, by IST-Client Services % The title page is counted as page `i' but we need to suppress the -% page number. We also don't want any headers or footers. +% page number. Also, we don't want any headers or footers. \pagestyle{empty} \pagenumbering{roman} @@ -30,5 +30,5 @@ \normalsize A thesis \\ - presented to the University of Waterloo \\ + presented to the University of Waterloo \\ in fulfillment of the \\ thesis requirement for the degree of \\ @@ -53,34 +53,39 @@ \cleardoublepage % Ends the current page and causes all figures and tables that have so far appeared in the input to be printed. % In a two-sided printing style, it also makes the next page a right-hand (odd-numbered) page, producing a blank page if necessary. - - +\phantomsection % allows hyperref to link to the correct page % D E C L A R A T I O N P A G E % ------------------------------- - % The following is the sample Delaration Page as provided by the GSO + % The following is a sample Declaration Page as provided by the GSO % December 13th, 2006. It is designed for an electronic thesis. + \addcontentsline{toc}{chapter}{Author's Declaration} + \begin{center}\textbf{Author's Declaration}\end{center} + + \noindent +I hereby declare that I am the sole author of this thesis. This is a true copy of the thesis, including any required final revisions, as accepted by my examiners. + + \bigskip + \noindent - I hereby declare that I am the sole author of this thesis. This is a true copy of the thesis, including any required final revisions, as accepted by my examiners. - \bigskip - - \noindent - I understand that my thesis may be made electronically available to the public. +I understand that my thesis may be made electronically available to the public. \cleardoublepage -%\newpage +\phantomsection % allows hyperref to link to the correct page % A B S T R A C T % --------------- - +\addcontentsline{toc}{chapter}{Abstract} \begin{center}\textbf{Abstract}\end{center} -Concurrent programs are notoriously hard to program and even harder to debug. Furthermore concurrent programs must be performant, as the introduction of concurrency into a program is often done to achieve some form of speedup. This thesis presents a suite of high level concurrent language features in \CFA, all of which are implemented with the aim of improving the performance, productivity, and safety of concurrent programs. \CFA is a non object-oriented programming language that extends C. The foundation for concurrency in \CFA was laid by Thierry Delisle, who implemented coroutines, user-level threads, and monitors\cite{Delisle18}. This thesis builds upon that groundwork and introduces a suite of concurrent features as its main contribution. The features include Go-like channels, mutex statements (similar to \CC scoped locks or Java synchronized statement), an actor system, and a Go-like select statement. The root idea behind these features are not new, but the \CFA implementations improve upon the original ideas in performance, productivity, and safety. +Concurrent programs are notoriously hard to program and even harder to debug. Furthermore concurrent programs must be performant, as the introduction of concurrency into a program is often done to achieve some form of speedup. + +This thesis presents a suite of high-level concurrent-language features in the new programming language \CFA, all of which are implemented with the aim of improving the performance, productivity, and safety of concurrent programs. \CFA is a non object-oriented programming language that extends C. The foundation for concurrency in \CFA was laid by Thierry Delisle~\cite{Delisle18}, who implemented coroutines, user-level threads, and monitors. This thesis builds upon that work and introduces a suite of new concurrent features as its main contribution. The features include Go-like channels, mutex statements (similar to \CC scoped locks or Java synchronized statement), an actor system, and a Go-like select statement. The root ideas behind these features are not new, but the \CFA implementations extends the original ideas in performance, productivity, and safety. \cleardoublepage -%\newpage +\phantomsection % allows hyperref to link to the correct page % A C K N O W L E D G E M E N T S % ------------------------------- - +\addcontentsline{toc}{chapter}{Acknowledgements} \begin{center}\textbf{Acknowledgements}\end{center} @@ -99,16 +104,15 @@ \noindent Finally, this work could not have happened without the financial support of David R. Cheriton School of Computer Science and the corporate partnership with Huawei Ltd. - \cleardoublepage -%\newpage +\phantomsection % allows hyperref to link to the correct page % % D E D I C A T I O N % % ------------------- - +% \addcontentsline{toc}{chapter}{Dedication} % \begin{center}\textbf{Dedication}\end{center} -% +% This is dedicated to the one I love. % \cleardoublepage -% %\newpage +% \phantomsection % allows hyperref to link to the correct page % T A B L E O F C O N T E N T S @@ -117,6 +121,12 @@ \tableofcontents \cleardoublepage -\phantomsection -%\newpage +\phantomsection % allows hyperref to link to the correct page + +% L I S T O F F I G U R E S +% ----------------------------- +\addcontentsline{toc}{chapter}{List of Figures} +\listoffigures +\cleardoublepage +\phantomsection % allows hyperref to link to the correct page % L I S T O F T A B L E S @@ -126,38 +136,18 @@ \cleardoublepage \phantomsection % allows hyperref to link to the correct page -%\newpage -% L I S T O F F I G U R E S -% ----------------------------- -\addcontentsline{toc}{chapter}{List of Figures} -\listoffigures +% L I S T O F A B B R E V I A T I O N S +% --------------------------- +\renewcommand*{\abbreviationsname}{List of Abbreviations} +\printglossary[type=abbreviations] \cleardoublepage \phantomsection % allows hyperref to link to the correct page -%\newpage -% L I S T O F L I S T I N G S -% ----------------------------- -\addcontentsline{toc}{chapter}{List of Listings} -\lstlistoflistings -\cleardoublepage -\phantomsection % allows hyperref to link to the correct page -%\newpage +% % L I S T O F S Y M B O L S +% % --------------------------- +% \printglossary[type=symbols] +% \cleardoublepage +% \phantomsection % allows hyperref to link to the correct page -% L I S T O F S Y M B O L S -% ----------------------------- -% To include a Nomenclature section -% \addcontentsline{toc}{chapter}{\textbf{Nomenclature}} -% \renewcommand{\nomname}{Nomenclature} -% \printglossary -% \cleardoublepage -% \phantomsection % allows hyperref to link to the correct page -% \newpage - -% L I S T O F T A B L E S -% ----------------------------- -\addcontentsline{toc}{chapter}{List of Acronyms} -\printglossary[type=\acronymtype,title={List of Acronyms}] -\cleardoublepage -\phantomsection % allows hyperref to link to the correct page % Change page numbering back to Arabic numerals Index: doc/theses/colby_parsons_MMAth/text/intro.tex =================================================================== --- doc/theses/colby_parsons_MMAth/text/intro.tex (revision fa6ca1ac779b46c587efb95ae262f52a9c5378e0) +++ doc/theses/colby_parsons_MMAth/text/intro.tex (revision 34b6a7b6878154693f83696df612a4adeee0fb87) @@ -1,7 +1,15 @@ % ====================================================================== % ====================================================================== -\chapter{Introduction}\label{s:cfa} +\chapter{Introduction}\label{s:intro} % ====================================================================== % ====================================================================== -Concurrent programs are the wild west of programming. Determinism and simple ordering of program operations go out the window. To seize the reins and write performant and safe concurrent code, concurrent language features are needed. Like any other craftsmen, programmers are only as good as their tools, and concurrent tooling and features are no exception. This thesis presents a set of concurrent features implemened in \CFA. These features aim to improve the performance of concurrent programs, aid in writing safe programs, and assist user productivity by improving the ease of concurrent programming. The groundwork for concurrent features in \CFA was implemented by Thierry Delisle, who contributed the threading system, coroutines, monitors and other tools\cite{Delisle18}. This thesis builds on top of that foundation by providing a suite of high-level concurrent features. These features include mutex statements, channels, an actor system and a waituntil statement. All of these features exist in other programming in some shape or form, however this thesis contributes upon the original ideas by improving performance, productivity, and safety. +Concurrent programs are the wild west of programming because determinism and simple ordering of program operations go out the window. +To seize the reins and write performant and safe concurrent code, high-level concurrent-language features are needed. +Like any other craftsmen, programmers are only as good as their tools, and concurrent tooling and features are no exception. +This thesis presents a set of concurrent features implemented in the new programming-language \CFA. +These features aim to improve the performance of concurrent programs, aid in writing safe programs, and assist user productivity by improving the ease of concurrent programming. +The groundwork for concurrent features in \CFA was implemented by Thierry Delisle~\cite{Delisle18}, who contributed the threading system, coroutines, monitors and other tools. +This thesis builds on top of that foundation by providing a suite of high-level concurrent features. +These features include mutex statements, channels, an actor system and a waituntil statement. +All of these features exist in other programming in some shape or form, however this thesis extends the original ideas by improving performance, productivity, and safety. Index: doc/theses/colby_parsons_MMAth/text/mutex_stmt.tex =================================================================== --- doc/theses/colby_parsons_MMAth/text/mutex_stmt.tex (revision fa6ca1ac779b46c587efb95ae262f52a9c5378e0) +++ doc/theses/colby_parsons_MMAth/text/mutex_stmt.tex (revision 34b6a7b6878154693f83696df612a4adeee0fb87) @@ -5,5 +5,10 @@ % ====================================================================== -The mutex statement is a concurrent language feature that aims to support easy lock usage. The mutex statement is in the form of a clause and following statement, similar to a loop or conditional statement. In the clause the mutex statement accepts a number of \newterm{lockable} objects, and then locks them for the duration of the following statement. The locks are acquired in a deadlock free manner and released using RAII. The mutex statement provides an avenue for easy lock usage in the common case where locks are used to wrap a critical section. Additionally, it provides the safety guarantee of deadlock-freedom, both by acquiring the locks in a deadlock-free manner, and by ensuring that the locks release on error, or normal program execution via RAII. +The mutex statement is a concurrent language feature that aims to support easy lock usage. +The mutex statement is in the form of a clause and following statement, similar to a loop or conditional statement. +In the clause the mutex statement accepts a number of lockable objects, and then locks them for the duration of the following statement. +The locks are acquired in a deadlock free manner and released using \gls{raii}. +The mutex statement provides an avenue for easy lock usage in the common case where locks are used to wrap a critical section. +Additionally, it provides the safety guarantee of deadlock-freedom, both by acquiring the locks in a deadlock-free manner, and by ensuring that the locks release on error, or normal program execution via \gls{raii}. \begin{cfacode}[tabsize=3,caption={\CFA mutex statement usage},label={l:cfa_mutex_ex}] @@ -18,5 +23,12 @@ \section{Other Languages} -There are similar concepts to the mutex statement that exist in other languages. Java has a feature called a synchronized statement, which looks identical to \CFA's mutex statement, but it has some differences. The synchronized statement only accepts a single object in its clause. Any object can be passed to the synchronized statement in Java since all objects in Java are monitors, and the synchronized statement acquires that object's monitor. In \CC there is a feature in the standard library \code{} header called scoped\_lock, which is also similar to the mutex statement. The scoped\_lock is a class that takes in any number of locks in its constructor, and acquires them in a deadlock-free manner. It then releases them when the scoped\_lock object is deallocated, thus using RAII. An example of \CC scoped\_lock usage is shown in Listing~\ref{l:cc_scoped_lock}. +There are similar concepts to the mutex statement that exist in other languages. +Java has a feature called a synchronized statement, which looks identical to \CFA's mutex statement, but it has some differences. +The synchronized statement only accepts a single object in its clause. +Any object can be passed to the synchronized statement in Java since all objects in Java are monitors, and the synchronized statement acquires that object's monitor. +In \CC there is a feature in the standard library \code{} header called scoped\_lock, which is also similar to the mutex statement. +The scoped\_lock is a class that takes in any number of locks in its constructor, and acquires them in a deadlock-free manner. +It then releases them when the scoped\_lock object is deallocated, thus using \gls{raii}. +An example of \CC scoped\_lock usage is shown in Listing~\ref{l:cc_scoped_lock}. \begin{cppcode}[tabsize=3,caption={\CC scoped\_lock usage},label={l:cc_scoped_lock}] @@ -29,7 +41,20 @@ \section{\CFA implementation} -The \CFA mutex statement takes some ideas from both the Java and \CC features. The mutex statement can acquire more that one lock in a deadlock-free manner, and releases them via RAII like \CC, however the syntax is identical to the Java synchronized statement. This syntactic choice was made so that the body of the mutex statement is its own scope. Compared to the scoped\_lock, which relies on its enclosing scope, the mutex statement's introduced scope can provide visual clarity as to what code is being protected by the mutex statement, and where the mutual exclusion ends. \CFA's mutex statement and \CC's scoped\_lock both use parametric polymorphism to allow user defined types to work with the feature. \CFA's implementation requires types to support the routines \code{lock()} and \code{unlock()}, whereas \CC requires those routines, plus \code{try_lock()}. The scoped\_lock requires an additional routine since it differs from the mutex statement in how it implements deadlock avoidance. +The \CFA mutex statement takes some ideas from both the Java and \CC features. +The mutex statement can acquire more that one lock in a deadlock-free manner, and releases them via \gls{raii} like \CC, however the syntax is identical to the Java synchronized statement. +This syntactic choice was made so that the body of the mutex statement is its own scope. +Compared to the scoped\_lock, which relies on its enclosing scope, the mutex statement's introduced scope can provide visual clarity as to what code is being protected by the mutex statement, and where the mutual exclusion ends. +\CFA's mutex statement and \CC's scoped\_lock both use parametric polymorphism to allow user defined types to work with the feature. +\CFA's implementation requires types to support the routines \code{lock()} and \code{unlock()}, whereas \CC requires those routines, plus \code{try_lock()}. +The scoped\_lock requires an additional routine since it differs from the mutex statement in how it implements deadlock avoidance. -The parametric polymorphism allows for locking to be defined for types that may want convenient mutual exclusion. An example of one such use case in \CFA is \code{sout}. The output stream in \CFA is called \code{sout}, and functions similarly to \CC's \code{cout}. \code{sout} has routines that satisfy the mutex statement trait, so the mutex statement can be used to lock the output stream while producing output. In this case, the mutex statement allows the programmer to acquire mutual exclusion over an object without having to know the internals of the object or what locks need to be acquired. The ability to do so provides both improves safety and programmer productivity since it abstracts away the concurrent details and provides an interface for optional thread-safety. This is a commonly used feature when producing output from a concurrent context, since producing output is not thread safe by default. This use case is shown in Listing~\ref{l:sout}. +The parametric polymorphism allows for locking to be defined for types that may want convenient mutual exclusion. +An example of one such use case in \CFA is \code{sout}. +The output stream in \CFA is called \code{sout}, and functions similarly to \CC's \code{cout}. +\code{sout} has routines that satisfy the mutex statement trait, so the mutex statement can be used to lock the output stream while producing output. +In this case, the mutex statement allows the programmer to acquire mutual exclusion over an object without having to know the internals of the object or what locks need to be acquired. +The ability to do so provides both improves safety and programmer productivity since it abstracts away the concurrent details and provides an interface for optional thread-safety. +This is a commonly used feature when producing output from a concurrent context, since producing output is not thread safe by default. +This use case is shown in Listing~\ref{l:sout}. \begin{cfacode}[tabsize=3,caption={\CFA sout with mutex statement},label={l:sout}] @@ -39,7 +64,11 @@ \section{Deadlock Avoidance} -The mutex statement uses the deadlock prevention technique of lock ordering, where the circular-wait condition of a deadlock cannot occur if all locks are acquired in the same order. The scoped\_lock uses a deadlock avoidance algorithm where all locks after the first are acquired using \code{try_lock} and if any of the attempts to lock fails, all locks so far are released. This repeats until all locks are acquired successfully. The deadlock avoidance algorithm used by scoped\_lock is shown in Listing~\ref{l:cc_deadlock_avoid}. The algorithm presented is taken directly from the source code of the \code{} header, with some renaming and comments for clarity. +The mutex statement uses the deadlock prevention technique of lock ordering, where the circular-wait condition of a deadlock cannot occur if all locks are acquired in the same order. +The scoped\_lock uses a deadlock avoidance algorithm where all locks after the first are acquired using \code{try_lock} and if any of the attempts to lock fails, all locks so far are released. +This repeats until all locks are acquired successfully. +The deadlock avoidance algorithm used by scoped\_lock is shown in Listing~\ref{l:cc_deadlock_avoid}. +The algorithm presented is taken directly from the source code of the \code{} header, with some renaming and comments for clarity. -\begin{cppcode}[tabsize=3,caption={\CC scoped\_lock deadlock avoidance algorithm},label={l:cc_deadlock_avoid}] +\begin{cppcode}[caption={\CC scoped\_lock deadlock avoidance algorithm},label={l:cc_deadlock_avoid}] int first = 0; // first lock to attempt to lock do { @@ -59,7 +88,21 @@ \end{cppcode} -The algorithm in \ref{l:cc_deadlock_avoid} successfully avoids deadlock, however there is a potential livelock scenario. Given two threads $A$ and $B$, who create a scoped\_lock with two locks $L1$ and $L2$, a livelock can form as follows. Thread $A$ creates a scoped\_lock with $L1$, $L2$, and $B$ creates a scoped lock with the order $L2$, $L1$. Both threads acquire the first lock in their order and then fail the try\_lock since the other lock is held. They then reset their start lock to be their 2nd lock and try again. This time $A$ has order $L2$, $L1$, and $B$ has order $L1$, $L2$. This is identical to the starting setup, but with the ordering swapped among threads. As such, if they each acquire their first lock before the other acquires their second, they can livelock indefinitely. +The algorithm in \ref{l:cc_deadlock_avoid} successfully avoids deadlock, however there is a potential livelock scenario. +Given two threads $A$ and $B$, who create a scoped\_lock with two locks $L1$ and $L2$, a livelock can form as follows. +Thread $A$ creates a scoped\_lock with $L1$, $L2$, and $B$ creates a scoped lock with the order $L2$, $L1$. +Both threads acquire the first lock in their order and then fail the try\_lock since the other lock is held. +They then reset their start lock to be their 2nd lock and try again. +This time $A$ has order $L2$, $L1$, and $B$ has order $L1$, $L2$. +This is identical to the starting setup, but with the ordering swapped among threads. +As such, if they each acquire their first lock before the other acquires their second, they can livelock indefinitely. -The lock ordering algorithm used in the mutex statement in \CFA is both deadlock and livelock free. It sorts the locks based on memory address and then acquires them. For locks fewer than 7, it sorts using hard coded sorting methods that perform the minimum number of swaps for a given number of locks. For 7 or more locks insertion sort is used. These sorting algorithms were chosen since it is rare to have to hold more than a handful of locks at a time. It is worth mentioning that the downside to the sorting approach is that it is not fully compatible with usages of the same locks outside the mutex statement. If more than one lock is held by a mutex statement, if more than one lock is to be held elsewhere, it must be acquired via the mutex statement, or else the required ordering will not occur. Comparitively, if the scoped\_lock is used and the same locks are acquired elsewhere, there is no concern of the scoped\_lock deadlocking, due to its avoidance scheme, but it may livelock. +The lock ordering algorithm used in the mutex statement in \CFA is both deadlock and livelock free. +It sorts the locks based on memory address and then acquires them. +For locks fewer than 7, it sorts using hard coded sorting methods that perform the minimum number of swaps for a given number of locks. +For 7 or more locks insertion sort is used. +These sorting algorithms were chosen since it is rare to have to hold more than a handful of locks at a time. +It is worth mentioning that the downside to the sorting approach is that it is not fully compatible with usages of the same locks outside the mutex statement. +If more than one lock is held by a mutex statement, if more than one lock is to be held elsewhere, it must be acquired via the mutex statement, or else the required ordering will not occur. +Comparitively, if the scoped\_lock is used and the same locks are acquired elsewhere, there is no concern of the scoped\_lock deadlocking, due to its avoidance scheme, but it may livelock. \begin{figure} @@ -102,5 +145,23 @@ \section{Performance} -Performance is compared between \CC's scoped\_lock and \CFA's mutex statement. Comparison with Java is omitted, since it only takes a single lock. To ensure that the comparison between \CC and \CFA exercises the implementation of each feature, an identical spinlock is implemented in each language using a set of builtin atomics available in both \CFA and \CC. Each feature is evaluated on a benchmark which acquires a fixed number of locks in a random order and then releases them. A baseline is included that acquires the locks directly without a mutex statement or scoped\_lock in a fixed ordering and then releases them. The baseline helps highlight the cost of the deadlock avoidance/prevention algorithms for each implementation. The benchmarks are run for a fixed duration of 10 seconds and then terminate and return the total number of times the group of locks were acquired. Each variation is run 11 times on a variety up to 32 cores and with 2, 4, and 8 locks being acquired. The median is calculated and is plotted alongside the 95\% confidence intervals for each point. +Performance is compared between \CC's scoped\_lock and \CFA's mutex statement. +Comparison with Java is omitted, since it only takes a single lock. +To ensure that the comparison between \CC and \CFA exercises the implementation of each feature, an identical spinlock is implemented in each language using a set of builtin atomics available in both \CFA and \CC. +Each feature is evaluated on a benchmark which acquires a fixed number of locks in a random order and then releases them. +A baseline is included that acquires the locks directly without a mutex statement or scoped\_lock in a fixed ordering and then releases them. +The baseline helps highlight the cost of the deadlock avoidance/prevention algorithms for each implementation. +The benchmarks are run for a fixed duration of 10 seconds and then terminate and return the total number of times the group of locks were acquired. +Each variation is run 11 times on a variety up to 32 cores and with 2, 4, and 8 locks being acquired. +The median is calculated and is plotted alongside the 95\% confidence intervals for each point. -Figure~\ref{f:mutex_bench} shows the results of the benchmark. The baseline runs for both languages are mostly comparable, except for the 8 locks results in \ref{f:mutex_bench8_AMD} and \ref{f:mutex_bench8_Intel}, where the \CFA baseline is slower. \CFA's mutex statement achieves throughput that is magnitudes higher than \CC's scoped\_lock. This is likely due to the scoped\_lock deadlock avoidance implementation. Since it uses a retry based mechanism, it can take a long time for threads to progress. Additionally the potential for livelock in the algorithm can result in very little throughput under high contention. It was observed on the AMD machine that with 32 threads and 8 locks the benchmarks would occasionally livelock indefinitely, with no threads making any progress for 3 hours before the experiment was terminated manually. It is likely that shorter bouts of livelock occured in many of the experiments, which would explain large confidence intervals for some of the data points in the \CC data. In Figures~\ref{f:mutex_bench8_AMD} and \ref{f:mutex_bench8_Intel} the mutex statement performs better than the baseline. At 7 locks and above the mutex statement switches from a hard coded sort to insertion sort. It is likely that the improvement in throughput compared to baseline is due to the time spent in the insertion sort, which decreases contention on the locks. +Figure~\ref{f:mutex_bench} shows the results of the benchmark. +The baseline runs for both languages are mostly comparable, except for the 8 locks results in \ref{f:mutex_bench8_AMD} and \ref{f:mutex_bench8_Intel}, where the \CFA baseline is slower. +\CFA's mutex statement achieves throughput that is magnitudes higher than \CC's scoped\_lock. +This is likely due to the scoped\_lock deadlock avoidance implementation. +Since it uses a retry based mechanism, it can take a long time for threads to progress. +Additionally the potential for livelock in the algorithm can result in very little throughput under high contention. +It was observed on the AMD machine that with 32 threads and 8 locks the benchmarks would occasionally livelock indefinitely, with no threads making any progress for 3 hours before the experiment was terminated manually. +It is likely that shorter bouts of livelock occured in many of the experiments, which would explain large confidence intervals for some of the data points in the \CC data. +In Figures~\ref{f:mutex_bench8_AMD} and \ref{f:mutex_bench8_Intel} the mutex statement performs better than the baseline. +At 7 locks and above the mutex statement switches from a hard coded sort to insertion sort. +It is likely that the improvement in throughput compared to baseline is due to the time spent in the insertion sort, which decreases contention on the locks. Index: doc/theses/colby_parsons_MMAth/thesis.tex =================================================================== --- doc/theses/colby_parsons_MMAth/thesis.tex (revision fa6ca1ac779b46c587efb95ae262f52a9c5378e0) +++ doc/theses/colby_parsons_MMAth/thesis.tex (revision 34b6a7b6878154693f83696df612a4adeee0fb87) @@ -1,116 +1,190 @@ -% requires tex packages: texlive-base texlive-latex-base tex-common texlive-humanities texlive-latex-extra texlive-fonts-recommended - -% inline code �...� (copyright symbol) emacs: C-q M-) -% red highlighting �...� (registered trademark symbol) emacs: C-q M-. -% blue highlighting �...� (sharp s symbol) emacs: C-q M-_ -% green highlighting �...� (cent symbol) emacs: C-q M-" -% LaTex escape �...� (section symbol) emacs: C-q M-' -% keyword escape �...� (pilcrow symbol) emacs: C-q M-^ -% math escape $...$ (dollar symbol) - +%====================================================================== +% University of Waterloo Thesis Template for LaTeX +% Last Updated August 2022 +% by IST Client Services, +% University of Waterloo, 200 University Ave. W., Waterloo, Ontario, Canada +% FOR ASSISTANCE, please send mail to helpdesk@uwaterloo.ca + +% DISCLAIMER +% To the best of our knowledge, this template satisfies the current uWaterloo thesis requirements. +% However, it is your responsibility to assure that you have met all requirements of the University and your particular department. + +% Many thanks for the feedback from many graduates who assisted the development of this template. +% Also note that there are explanatory comments and tips throughout this template. +%====================================================================== +% Some important notes on using this template and making it your own... + +% The University of Waterloo has required electronic thesis submission since October 2006. +% See the uWaterloo thesis regulations at +% https://uwaterloo.ca/graduate-studies/thesis. +% This thesis template is geared towards generating a PDF version optimized for viewing on an electronic display, including hyperlinks within the PDF. + +% DON'T FORGET TO ADD YOUR OWN NAME AND TITLE in the "hyperref" package configuration below. +% Search for: PDFTITLE, PDFAUTHOR, PDFSUBJECT, and PDFKEYWORDS. +% THIS INFORMATION GETS EMBEDDED IN THE FINAL PDF DOCUMENT. +% You can view the information if you view properties of the PDF document. + +% Many faculties/departments also require one or more printed copies. +% This template attempts to satisfy both types of output. +% See additional notes below. +% It is based on the standard "book" document class which provides all necessary sectioning structures and allows multi-part theses. + +% If you are using this template in Overleaf (cloud-based collaboration service), then it is automatically processed and previewed for you as you edit. + +% For people who prefer to install their own LaTeX distributions on their own computers, and process the source files manually, the following notes provide the sequence of tasks: + +% E.g. to process a thesis called "mythesis.tex" based on this template, run: + +% pdflatex mythesis -- first pass of the pdflatex processor +% bibtex mythesis -- generates bibliography from .bib data file(s) +% makeindex -- should be run only if an index is used +% pdflatex mythesis -- fixes numbering in cross-references, bibliographic references, glossaries, index, etc. +% pdflatex mythesis -- it takes a couple of passes to completely process all cross-references + +% If you use the recommended LaTeX editor, Texmaker, you would open the mythesis.tex file, then click the PDFLaTeX button. Then run BibTeX (under the Tools menu). +% Then click the PDFLaTeX button two more times. +% If you have an index as well,you'll need to run MakeIndex from the Tools menu as well, before running pdflatex +% the last two times. + +% N.B. The "pdftex" program allows graphics in the following formats to be included with the "\includegraphics" command: PNG, PDF, JPEG, TIFF +% Tip: Generate your figures and photos in the size you want them to appear in your thesis, rather than scaling them with \includegraphics options. +% Tip: Any drawings you do should be in scalable vector graphic formats: SVG, PNG, WMF, EPS and then converted to PNG or PDF, so they are scalable in the final PDF as well. +% Tip: Photographs should be cropped and compressed so as not to be too large. + +% To create a PDF output that is optimized for double-sided printing: +% 1) comment-out the \documentclass statement in the preamble below, and un-comment the second \documentclass line. +% 2) change the value assigned below to the boolean variable "PrintVersion" from " false" to "true". + +%====================================================================== +% D O C U M E N T P R E A M B L E +% Specify the document class, default style attributes, and page dimensions, etc. +% For hyperlinked PDF, suitable for viewing on a computer, use this: \documentclass[letterpaper,12pt,titlepage,oneside,final]{book} - -%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% - -% Latex packages used in the document. -\usepackage[T1]{fontenc} % allow Latin1 (extended ASCII) characters + +% For PDF, suitable for double-sided printing, change the PrintVersion variable below to "true" and use this \documentclass line instead of the one above: +%\documentclass[letterpaper,12pt,titlepage,openright,twoside,final]{book} + +% Some LaTeX commands I define for my own nomenclature. +% If you have to, it's easier to make changes to nomenclature once here than in a million places throughout your thesis! +\newcommand{\package}[1]{\textbf{#1}} % package names in bold text +\newcommand{\cmmd}[1]{\textbackslash\texttt{#1}} % command name in tt font +\newcommand{\href}[1]{#1} % does nothing, but defines the command so the print-optimized version will ignore \href tags (redefined by hyperref pkg). +%\newcommand{\texorpdfstring}[2]{#1} % does nothing, but defines the command +% Anything defined here may be redefined by packages added below... + +% This package allows if-then-else control structures. +\usepackage{ifthen} +\newboolean{PrintVersion} +\setboolean{PrintVersion}{false} +% CHANGE THIS VALUE TO "true" as necessary, to improve printed results for hard copies by overriding some options of the hyperref package, called below. + +%\usepackage{nomencl} % For a nomenclature (optional; available from ctan.org) +\usepackage{amsmath,amssymb,amstext} % Lots of math symbols and environments + +\usepackage{tikz} % for diagrams and figures +\def\checkmark{\tikz\fill[scale=0.4](0,.35) -- (.25,0) -- (1,.7) -- (.25,.15) -- cycle;} +\usepackage{subcaption} +\usepackage{fullpage,times,comment} \usepackage{textcomp} -\usepackage[latin1]{inputenc} -\usepackage{fullpage,times,comment} -\usepackage{epic,eepic} -\usepackage{upquote} % switch curled `'" to straight -\usepackage{dirtytalk} -\usepackage{calc} -\usepackage{xspace} -% \usepackage[labelformat=simple]{subfig} -% \renewcommand{\thesubfigure}{(\alph{subfigure})} -\usepackage{subcaption} -% \usepackage{subfigure} \usepackage{graphicx} \usepackage{tabularx} -\usepackage{multicol} -\usepackage[acronym]{glossaries} -\usepackage{varioref} -\usepackage{listings} % format program code -\usepackage[flushmargin]{footmisc} % support label/reference in footnote -\usepackage{latexsym} % \Box glyph -\usepackage{mathptmx} % better math font with "times" -\usepackage[usenames]{color} -\usepackage[pagewise]{lineno} -\renewcommand{\linenumberfont}{\scriptsize\sffamily} -\usepackage{fancyhdr} -\usepackage{float} -\usepackage{siunitx} -\sisetup{ binary-units=true } -\input{style} % bespoke macros used in the document -\usepackage{url} -\usepackage[dvips,plainpages=false,pdfpagelabels,pdfpagemode=UseNone,colorlinks=true,pagebackref=true,linkcolor=blue,citecolor=blue,urlcolor=blue,pagebackref=true,breaklinks=true]{hyperref} -\usepackage{breakurl} -\urlstyle{rm} - -\usepackage{tikz} -\def\checkmark{\tikz\fill[scale=0.4](0,.35) -- (.25,0) -- (1,.7) -- (.25,.15) -- cycle;} - -\setlength{\topmargin}{-0.45in} % move running title into header -\setlength{\headsep}{0.25in} - -\newsavebox{\myboxA} % used with subfigure -\newsavebox{\myboxB} - -%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% - -% Names used in the document. - -\newcommand{\Version}{1.0.0} -\newcommand{\CS}{C\raisebox{-0.9ex}{\large$^\sharp$}\xspace} - -\newcommand{\Textbf}[2][red]{{\color{#1}{\textbf{#2}}}} -\newcommand{\Emph}[2][red]{{\color{#1}\textbf{\emph{#2}}}} -\newcommand{\R}[1]{\Textbf{#1}} -\newcommand{\B}[1]{{\Textbf[blue]{#1}}} -\newcommand{\G}[1]{{\Textbf[OliveGreen]{#1}}} -\newcommand{\uC}{$\mu$\CC} -\newcommand{\cit}{\textsuperscript{[Citation Needed]}\xspace} -\newcommand{\TODO}{{\Textbf{TODO}}} - +\input{style} + +% Hyperlinks make it very easy to navigate an electronic document. +% In addition, this is where you should specify the thesis title and author as they appear in the properties of the PDF document. +% Use the "hyperref" package +% N.B. HYPERREF MUST BE THE LAST PACKAGE LOADED; ADD ADDITIONAL PKGS ABOVE +\usepackage[dvips,pagebackref=false]{hyperref} % with basic options +\hypersetup{ + plainpages=false, % needed if Roman numbers in frontpages + unicode=false, % non-Latin characters in Acrobat’s bookmarks + pdftoolbar=true, % show Acrobat’s toolbar? + pdfmenubar=true, % show Acrobat’s menu? + pdffitwindow=false, % window fit to page when opened + pdfstartview={FitH}, % fits the width of the page to the window + pdftitle={High Level Concurrency in \CFA}, + pdfauthor={Colby Parsons}, + pdfsubject={Cforall}, +% pdfkeywords={keyword1} {key2} {key3}, % list of keywords, and uncomment this line if desired + pdfnewwindow=true, % links in new window + colorlinks=true, % false: boxed links; true: colored links + linkcolor=blue, % color of internal links + citecolor=green, % color of links to bibliography + filecolor=magenta, % color of file links + urlcolor=cyan % color of external links +} +\ifthenelse{\boolean{PrintVersion}}{ % for improved print quality, change some hyperref options +\hypersetup{ % override some previously defined hyperref options +% colorlinks,% + citecolor=black,% + filecolor=black,% + linkcolor=black,% + urlcolor=black} +}{} % end of ifthenelse (no else) + +% \usepackage[acronym]{glossaries} +\usepackage[automake,toc,abbreviations]{glossaries-extra} % Exception to the rule of hyperref being the last add-on package +% If glossaries-extra is not in your LaTeX distribution, get it from CTAN (http://ctan.org/pkg/glossaries-extra), +% although it's supposed to be in both the TeX Live and MikTeX distributions. There are also documentation and +% installation instructions there. + +% Setting up the page margins... +% uWaterloo thesis requirements specify a minimum of 1 inch (72pt) margin at the +% top, bottom, and outside page edges and a 1.125 in. (81pt) gutter margin (on binding side). +% While this is not an issue for electronic viewing, a PDF may be printed, and so we have the same page layout for both printed and electronic versions, we leave the gutter margin in. +% Set margins to minimum permitted by uWaterloo thesis regulations: +\setlength{\marginparwidth}{0pt} % width of margin notes +% N.B. If margin notes are used, you must adjust \textwidth, \marginparwidth +% and \marginparsep so that the space left between the margin notes and page +% edge is less than 15 mm (0.6 in.) +\setlength{\marginparsep}{0pt} % width of space between body text and margin notes +\setlength{\evensidemargin}{0.125in} % Adds 1/8 in. to binding side of all +% even-numbered pages when the "twoside" printing option is selected +\setlength{\oddsidemargin}{0.125in} % Adds 1/8 in. to the left of all pages when "oneside" printing is selected, and to the left of all odd-numbered pages when "twoside" printing is selected +\setlength{\textwidth}{6.375in} % assuming US letter paper (8.5 in. x 11 in.) and side margins as above +\raggedbottom + +% The following statement specifies the amount of space between paragraphs. Other reasonable specifications are \bigskipamount and \smallskipamount. +\setlength{\parskip}{\medskipamount} + +% The following statement controls the line spacing. +% The default spacing corresponds to good typographic conventions and only slight changes (e.g., perhaps "1.2"), if any, should be made. +\renewcommand{\baselinestretch}{1} % this is the default line space setting + +% By default, each chapter will start on a recto (right-hand side) page. +% We also force each section of the front pages to start on a recto page by inserting \cleardoublepage commands. +% In many cases, this will require that the verso (left-hand) page be blank, and while it should be counted, a page number should not be printed. +% The following statements ensure a page number is not printed on an otherwise blank verso page. +\let\origdoublepage\cleardoublepage +\newcommand{\clearemptydoublepage}{% + \clearpage{\pagestyle{empty}\origdoublepage}} +\let\cleardoublepage\clearemptydoublepage + +% Define Glossary terms (This is properly done here, in the preamble and could also be \input{} from a separate file...) \input{glossary} - -\newsavebox{\LstBox} - -%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% - -\setcounter{secnumdepth}{2} % number subsubsections -\setcounter{tocdepth}{2} % subsubsections in table of contents -% \linenumbers % comment out to turn off line numbering -\makeindex -\pagestyle{fancy} -\fancyhf{} -\cfoot{\thepage} -\rfoot{v\input{version}} - - - -%====================================================================== -% L O G I C A L D O C U M E N T -- the content of your thesis +\makeglossaries + +%====================================================================== +% L O G I C A L D O C U M E N T +% The logical document contains the main content of your thesis. +% Being a large document, it is a good idea to divide your thesis into several files, each one containing one chapter or other significant chunk of content, so you can easily shuffle things around later if desired. %====================================================================== \begin{document} \newtheorem{theorem}{Theorem} -% For a large document, it is a good idea to divide your thesis -% into several files, each one containing one chapter. -% To illustrate this idea, the "front pages" (i.e., title page, -% declaration, borrowers' page, abstract, acknowledgements, -% dedication, table of contents, list of tables, list of figures, -% nomenclature) are contained within the file "thesis-frontpgs.tex" which is -% included into the document by the following statement. %---------------------------------------------------------------------- % FRONT MATERIAL -%---------------------------------------------------------------------- -\input{frontpgs} +% title page,declaration, borrowers' page, abstract, acknowledgements, +% dedication, table of contents, list of tables, list of figures, nomenclature, etc. +%---------------------------------------------------------------------- +\input{frontpgs} %---------------------------------------------------------------------- % MAIN BODY -%---------------------------------------------------------------------- - +% We suggest using a separate file for each chapter of your thesis. +% Start each chapter file with the \chapter command. +% Only use \documentclass or \begin{document} and \end{document} commands in this master document. +% Tip: Putting each sentence on a new line is a way to simplify later editing. +%---------------------------------------------------------------------- \input{intro} @@ -125,21 +199,50 @@ \input{actors} -\clearpage - -% B I B L I O G R A P H Y +%---------------------------------------------------------------------- +% END MATERIAL +% Bibliography, Appendices, Index, etc. +%---------------------------------------------------------------------- + +% Bibliography + +% The following statement selects the style to use for references. +% It controls the sort order of the entries in the bibliography and also the formatting for the in-text labels. +\bibliographystyle{plain} +% This specifies the location of the file containing the bibliographic information. +% It assumes you're using BibTeX to manage your references (if not, why not?). +\cleardoublepage % This is needed if the "book" document class is used, to place the anchor in the correct page, because the bibliography will start on its own page. +% Use \clearpage instead if the document class uses the "oneside" argument +\phantomsection % With hyperref package, enables hyperlinking from the table of contents to bibliography +% The following statement causes the title "References" to be used for the bibliography section: +\renewcommand*{\bibname}{References} + +% Add the References to the Table of Contents +\addcontentsline{toc}{chapter}{\textbf{References}} + +\bibliography{pl,local} +% Tip: You can create multiple .bib files to organize your references. +% Just list them all in the \bibliogaphy command, separated by commas (no spaces). + +% The following statement causes the specified references to be added to the bibliography even if they were not cited in the text. +% The asterisk is a wildcard that causes all entries in the bibliographic database to be included (optional). +% \nocite{*} +%---------------------------------------------------------------------- + +% Appendices + +% The \appendix statement indicates the beginning of the appendices. +% \appendix +% % Add an un-numbered title page before the appendices and a line in the Table of Contents +% \chapter*{APPENDICES} +% \addcontentsline{toc}{chapter}{APPENDICES} +% % Appendices are just more chapters, with different labeling (letters instead of numbers). +% \input{appendix-matlab_plots.tex} + +% GLOSSARIES (Lists of definitions, abbreviations, symbols, etc. provided by the glossaries-extra package) % ----------------------------- -\addcontentsline{toc}{chapter}{Bibliography} -\bibliographystyle{plain} -\bibliography{pl,local} -\cleardoublepage -\phantomsection % allows hyperref to link to the correct page - -% G L O S S A R Y -% ----------------------------- -\addcontentsline{toc}{chapter}{Glossary} \printglossary \cleardoublepage \phantomsection % allows hyperref to link to the correct page - -\end{document} +%---------------------------------------------------------------------- +\end{document} % end of logical document Index: doc/theses/colby_parsons_MMAth/version =================================================================== --- doc/theses/colby_parsons_MMAth/version (revision fa6ca1ac779b46c587efb95ae262f52a9c5378e0) +++ doc/theses/colby_parsons_MMAth/version (revision 34b6a7b6878154693f83696df612a4adeee0fb87) @@ -1,1 +1,1 @@ -0.0.0 +0.0.15 Index: tests/concurrent/channels/churn.cfa =================================================================== --- tests/concurrent/channels/churn.cfa (revision fa6ca1ac779b46c587efb95ae262f52a9c5378e0) +++ tests/concurrent/channels/churn.cfa (revision 34b6a7b6878154693f83696df612a4adeee0fb87) @@ -3,8 +3,8 @@ #include #include -#include "channel.hfa" +#include #include #include -#include + size_t Processors = 1, Channels = 4, Producers = 2, Consumers = 2, ChannelSize = 128;