diff options
Diffstat (limited to 'main.tex')
| -rw-r--r-- | main.tex | 190 |
1 files changed, 116 insertions, 74 deletions
@@ -11,7 +11,7 @@ In result datacenters become extremely complex and hard to operate with millions of CPU's, GPU's etc. \end{tcolorbox} \begin{center} - \includegraphics[width=\linewidth]{images/datacenter_complexity.pdf} + \includegraphics[width=\linewidth]{images/datacenter_complexity.png} \end{center} \tiny \textbf{Figure 1.1:} Society depends on datacenters to keep running, and therefore we cannot afford to let these systems break down or experience significant performance-related issues. @@ -19,7 +19,6 @@ Left to right: a Google datacenter, server racks, Ada Lovelace AD102 GPU architecture. \end{frame} - \begin{frame}\frametitle{Problem Statement} \begin{tcolorbox}[title=DCDT's lack predictive analytics] We need Datacenter Digital Twins (DCDT) to be better able to detect and solve issues in critical ICT infrastructure~\cite{DBLP:journals/computer/AthavaleBBMMPS24}. @@ -33,7 +32,7 @@ \tiny \textbf{Figure 1.2:} Where does our work fit within the field of datacenter digital twinning? There are 5 core elements to any Digital Twin: \myCircled{A} The Digital $\rightarrow$ Physical Twin link, \myCircled{B} the Physical Twin (\emph{e.g.,} the datacenter), \myCircled{C} the Physical $\rightarrow$ Digital Twin link, \myCircled{D} the Digital Twin, \myCircled{E} the features necessary to any Digital Twin. - \textcolor{ForestGreen}{\faHighlighter~Highlighted areas are the contributions from this thesis, which include the autonomous actions resulting from predictive insights \myCircledGreen{A} and the predictive analysis itself within \myCircledGreen{E}.} + \textcolor{Green}{\faHighlighter~Highlighted areas are the contributions from this thesis, which include the autonomous actions resulting from predictive insights \myCircledGreen{A} and the predictive analysis itself within \myCircledGreen{E}.} \end{frame} \begin{frame}\frametitle{Research Questions} @@ -50,18 +49,19 @@ \end{tcolorbox} \begin{tcolorbox}[title=Research Question 3] - How to evaluate and validate a datacenter digital twin architecture in relation to system requirements? + % no "and validate?" + How to validate and evaluate a datacenter digital twin architecture in relation to system requirements? \end{tcolorbox} \end{frame} - \begin{frame}\frametitle{\textbf{RQ1}: Literature Review I} - \begin{tcolorbox}[title=Results] + \begin{tcolorbox}[title=Main Finding I] The literature on DCDTs is scarce. Some systems barely classify as DTs (\emph{e.g.,} Kalibre~\cite{DBLP:conf/sensys/WangZD0TCWZ20}, ChatTwin~\cite{DBLP:conf/sensys/LiW0Z0T23}). Existing deployments specialize in \textcolor{Red}{Cooling and Heat Modelling}, together with \textcolor{Red}{3D visualizations}. - Most lack crucial predictive DC behaviour modelling. + Most lack predictive modelling of DC operations. \end{tcolorbox} + \vspace{-0.1cm} \input{images/table.tex} % Research on DTs for datacenters have been separate, siloed efforts focused on either datacenter cooling, network performance, power consumption or visualization efforts. % CFD usually means Navier-Stokes equations. @@ -72,8 +72,7 @@ % Mandatory: split the figure into 2: top and bottom, and that way you can fill in the entire slide nicely. \begin{tcolorbox}[title=A holistic DCDT system model] - We propose a generic model of datacenter digital twinning that can be mapped to each system from \textbf{Table 1.1}. To answer \textbf{RQ2}, we design a ref. arch. for \emph{Operations Model}. - We introduce the \emph{Digital Thread}: a bridge between software and reality. + We propose a generic model of datacenter digital twinning that can be mapped to each system from \textbf{Table 1.1}. Within this model (see \textbf{Fig. 1.3}) we introduce a concept of the \emph{Digital Thread}: a bridge between the DCDT and the physical DC equipment. \end{tcolorbox} \begin{center} \vspace{-0.1cm} @@ -85,7 +84,7 @@ % Not really a digital twin per se. \tiny - \textbf{Figure 1.3:} To answer \textbf{RQ1} we designed a generic datacenter digital twin system model based on a comprehensive literature review and findings from \textbf{Table 1.1}. The \emph{Infrastructure Model} simulates the structure of the DC and the \emph{Operations model} simulates the behaviour of the DC. + \textbf{Figure 1.3:} To answer \textbf{RQ1} we designed a generic datacenter digital twin system model based on a comprehensive literature review and findings from \textbf{Table 1.1}. The \emph{Infrastructure Model} simulates the structure of the DC and the \emph{Operations Model} simulates the behaviour of the DC. % Consider splitting the figure into 2 a.k.a. top and bottom. % By the AIAA definition, the DT mimicks the structure and behaviour. % Data Lake -> Data Storage @@ -93,19 +92,31 @@ \end{frame} \begin{frame}\frametitle{\textbf{RQ2}: Reference Architecture} + % Make Kafka logos clearly defined --> add a legend with icons? + \hspace{-0.3cm} \begin{minipage}[b]{0.45\linewidth} - \begin{tcolorbox}[title=Use cases] - - \end{tcolorbox} - \vspace{1cm} + \begin{center} + % Change to Datacenter (Physical Twin) + \includegraphics[width=1.15\textwidth]{images/ref_architecture.pdf} + \end{center} + \vspace{-0.15cm} + \tiny + \textbf{Figure 1.4:} The predictive datacenter digital twin reference architecture. + The architecture was designed with the \emph{AtLarge Design Process}~\cite{DBLP:conf/icdcs/IosupVTETBFMT19} over several iterations in the past months. + \vspace{0.2cm} \end{minipage} + \hspace{0.6cm} \begin{minipage}[b]{0.45\linewidth} \begin{center} - \includegraphics[width=1.25\textwidth]{images/ref_architecture.pdf} + \includegraphics[width=1.17\linewidth]{images/implementation.png} \end{center} \vspace{-0.2cm} \tiny - \textbf{Figure 1.4:} The predictive datacenter digital twin reference architecture. \end{minipage} + \textbf{Figure 1.5:} The prototype -- \emph{Sunfish}, and its components based on \textbf{Figure 1.4}. + The time-series data flows first to the \texttt{Grafana} dashboard, \texttt{PostgreSQL} database and \texttt{Redis} cache~\cite{DBLP:conf/sc/TaheriBPRHDEWPM24}. + \vspace{0.1cm} + \end{minipage} + % We decided to use discrete-event simulation, as opposed to computational fluid dynamics because of the high overheads of development time needed for CFD. % CFD simply takes too long to run, making it unfeasible for real-time analytics and simulation. % Citing ExaDigit: [CFD] they are also more computationally expensive, generally making real-time operation unfeasible. @@ -113,37 +124,34 @@ \end{frame} % You should skip \hfill completely or in favour of \hspace very minimally. \begin{frame}\frametitle{\textbf{RQ3}: Experimental Setup} - % The software stack of \emph{Sunfish} includes state-of-the-art software. - %The time-series data flows first to the \texttt{Grafana} dashboard, \texttt{PostgreSQL} database and \texttt{Redis} cache, as advised in~\cite{DBLP:conf/sc/TaheriBPRHDEWPM24}. - + \hspace{-0.3cm} \begin{minipage}[b]{0.45\linewidth} - \begin{tcolorbox}[title=Setup Recipe] - \scriptsize - \textbf{Step 1.} Ensure Redis and PostgreSQL servers are up and alive.\newline - - \textbf{Step 2.} Run a Confluent Kafka setup: Kafka Connect, Schema Registry and a Kafka server.\newline - - \textbf{Step 3.} Start the Python HTTP Server, and the Python Redis Monitor.\newline - - \textbf{Step 4.} Run the (modified) OpenDC (physical twin) with example experiment.\newline - - \textbf{Step 5.} \emph{Sunfish} will automatically start a second OpenDC instance, and start the data analysis. + \begin{tcolorbox}[title=Problem, colbacktitle=red!70!black,colback=red!20!white] + We cannot just go and test digital twins on large systems, because we do not have large systems at hand. + Moreover, real-world experimentation is costly and unsustainable in the long run~\cite{DBLP:conf/ccgrid/MastenbroekAJLB21}. \end{tcolorbox} \vspace{0.5cm} + \begin{tcolorbox}[title=Solution, colbacktitle=Green!70!black, colback=Green!20!white] + \scriptsize + They way we test our reference architecture prototype is by using multiple simulators. + We use an additional OpenDC process to play the role of a real datacenter. + \end{tcolorbox} + \vspace{1cm} \end{minipage} - \hspace{0.35cm} + \hspace{0.25cm} \begin{minipage}[b]{0.45\linewidth} \vspace{-0.2cm} \begin{center} - \includegraphics[width=1.2\linewidth]{images/predictive_analyticsv2.pdf} + \includegraphics[width=1.2\linewidth]{images/predictive_analyticsv3.pdf} \end{center} \tiny - \vspace{-0.4cm} - \textbf{Figure 1.5:} We can't just go and test digital twins on large systems as large systems often aren't at hand. - Answering \textbf{RQ3} we provide a novel way to evaluate datacenter digital twins through discrete-event simulation instead. + \vspace{-0.2cm} + \textbf{Figure 1.6:} The experimental setup. + Answering \textbf{RQ3} we provide a novel way to evaluate datacenter digital twins through discrete-event simulation. \end{minipage} \end{frame} + \begin{frame}\frametitle{\textbf{RQ3}: Experimental Results I} % You have some model, and this can be based on multiple traces. %Get insight from CINECA --> you get a probability of certain hosts failing. @@ -151,59 +159,85 @@ %If you incorporate that? If you can make the case that because of our new digital twin we can incorporate such models, anomaly/failure detection, from CINECA. %If we had that in, we can reach these kinds of gains. % @Mateusz there is really not a possibility to incorporate CINECA's models, so to address Dante's feedback, I created this experiment. - - \begin{tcolorbox}[title=Failure Detection: Main Finding I] - On average, \emph{Sunfish} can detect 14.5\% of unexpected failures in the physical twin. - We show, that digital twinning \emph{can} be used for failure detection. - + % If a single host crashes for the entire workload, that's not really that bad. + % If a lot of hosts suddenly crash but for a really short time, that's terrible. + % Failures that are more intensive are worse than failures with long duration. + \begin{tcolorbox}[title=Main Finding II] + We posit digital twinning can be used for failure detection to the benefit of DC operators. + We replicate an experiment from DyTwin~\cite{DBLP:conf/sc/TaheriBPRHDEWPM24} designed by Milojicic \etal to show our system can reliably detect \emph{unexpected} host failures. \end{tcolorbox} + \hspace{-0.2cm} \begin{minipage}[b]{0.45\linewidth} \begin{center} - \includegraphics[width=1.1\textwidth]{images/23_Jun_2026_102028.pdf} + \includegraphics[width=1.1\textwidth]{images/25_Jun_2026_152341.pdf} + \end{center} + \vspace{-0.3cm} + \tiny + \textbf{Figure 1.7a:} Experiment 1a. In this experiment we use red and yellow alarms to notify datacenter operators of unexpected failures. + We use a threshold based on predictions done by the simulator and a statistical distribution. + \end{minipage} + \hspace{0.6cm} + \begin{minipage}[b]{0.45\linewidth} + \begin{center} + \includegraphics[width=1.1\textwidth]{images/25_Jun_2026_161052.pdf} \end{center} \vspace{-0.3cm} \tiny - \textbf{Figure 1.5:} Experiment 1 Setup: The Digital Twin estimates the failures based on the Normal Distribution \emph{N\textasciitilde($\mu$,$\sigma$)} with $\mu = 1.5$ and $\sigma = 0.5$. - ``Real'' OpenDC failures come from a WhatsApp user reports. + \textbf{Figure 1.7b:} Experiment 1b. The mean failure detection rate is around 15\%. Even though this seems low, if we look at \textbf{Fig. E.1} (see Extra Slides), this simply means around 15\% of failures are unexpected. \end{minipage} % Explain what the axis are in the figure caption. % Talk about the experimental setup in the figure. % Give more reliable results than just numbers -- do statistical testing, i.e., standard deviation, confidence intervals. \end{frame} - \begin{frame}\frametitle{\textbf{RQ3}: Experimental Results II} - \begin{tcolorbox}[title=Failure Prediction: Main Finding II] - Here explain what did you find. + \begin{tcolorbox}[title=Main Finding III] + \emph{Sunfish} is capable of dynamic adjustments to the physical twin at runtime, and can lower the mean number of failed tasks. \end{tcolorbox} - + \hspace{0.2cm} + \begin{minipage}[b]{0.45\linewidth} + \begin{center} + \includegraphics[width=1.1\textwidth]{images/23_Jun_2026_102028.pdf} + \end{center} + \vspace{-0.3cm} + \tiny + \textbf{Figure 1.8a:} Experiment 2a. + \end{minipage} + \begin{minipage}[b]{0.45\linewidth} + \begin{center} + \includegraphics[width=1.1\textwidth]{images/23_Jun_2026_102028.pdf} + \end{center} + \vspace{-0.3cm} + \tiny + \textbf{Figure 1.8b:} Experiment 2b. + \end{minipage} \end{frame} \begin{frame}\frametitle{Key Takeaways} \begin{tcolorbox}[title=What is the societal context?] - + Datacenter manageability is a top-priority for the digital society. + Over 3 million jobs in the Netherlands directly depend on cloud services, which are hosted in datacenters~\cite{DBLP:journals/corr/IosupKLVG22}. \end{tcolorbox} \begin{tcolorbox}[title=What problem did we solve?] - + DCDT's, still under development, lack crucial features such as predictive analytics to manage datacenters well. + The entire DCDT design space remains largely unexplored. \end{tcolorbox} \begin{tcolorbox}[title=How did we solve this problem?] - + Our contributions are: a thorough literature survey with a system model, a DCDT reference architecture, and prototype-based experiments via a novel evaluation method. \end{tcolorbox} - \begin{tcolorbox}[colbacktitle=red!70!black, colback=red!20!white,title=What did we find?] - - \end{tcolorbox} - - \begin{tcolorbox}[title=What do we see in future work?] - + \begin{tcolorbox}[title=What did we find?] + \emph{Sunfish} can reliably detect unexpected failures based on discrete-event predictions, and can serve as a foundation for additional research and future work. \end{tcolorbox} - + % Mandatory to mention here the future work that you see happening. + % Not enough space for another tcolorbox. \end{frame} -\setcounter{framenumber}{4} -\setbeamertemplate{footline}[page number]{ +\setcounter{framenumber}{3} +\setbeamertemplate{footline}[page number]{} + % Unfortunately this must remain here. \setbeamercolor{frametitle}{fg=Brown,bg=Brown!20} @@ -213,28 +247,33 @@ \usebeamerfont{frametitle}\insertframetitle\hfill \end{beamercolorbox} } - \begin{frame}[allowframebreaks]\frametitle{Extra Slides: References} \tiny \bibliographystyle{is-plain} \bibliography{main.bib} \end{frame} -\begin{frame}\frametitle{Extra Slides: Societal Impact} - \begin{tcolorbox}[title=Why is this research important today?] - Over 3 million jobs in the Netherlands directly depend on cloud services, which are hosted in datacenters~\cite{DBLP:journals/corr/IosupKLVG22}. - Already the rapid - expansion of datacenters has increased the presence of service failures across all cloud - services~\cite{DBLP:conf/acsos/TalluriOVTI21}. - We need to act now. +\begin{frame}\frametitle{Extra Slides: Technical Setup } + \begin{tcolorbox}[title=What is the simulation workload?] + The compute workload is BitBrainsSmall. + The failure traces include user reports from Gmail, WhatsApp, Facebook and Twitter. + For predictions we use \texttt{prefabs}~\cite{DBLP:journals/fgcs/VersluisCGLPCUI23}. \end{tcolorbox} - \begin{center} - \includegraphics[height=10em]{images/manageability.pdf} - \end{center} - \tiny - \textbf{Figure E.1:} Horizontally: the most important research areas in computer science in Netherlands. - Vertically: qualities we should ensure across all research areas with the most outstanding impact on society. - Datacenter manageability is a top-priority~\cite{DBLP:journals/corr/IosupKLVG22}. + \begin{tcolorbox}[title=What is the experiment environment?] A commodity laptop: Framework Laptop 13, with 32GB of DDR5 RAM and an AMD Ryzen 7840U processor and an ArchLinux OS with Linux 7.0.13-arch1-1 kernel. + + \end{tcolorbox} + + + \begin{tcolorbox}[title=How did we adjust OpenDC (Physical Twin)?] + We use a SURF~\cite{DBLP:journals/fgcs/VersluisCGLPCUI23} datacenter topology with 277 hosts. + We wrote a custom Kotlin \texttt{ComputeMonitor} to export live-metrics into Kafka, and a custom Kotlin \texttt{HTTPClient} to talk to the digital twin. + We add a new scheduling mechanism, the \texttt{SmartScheduler}. + + \end{tcolorbox} + \begin{tcolorbox}[title=Which metrics do we measure?] + Timestamps, host names, uptime, downtime, CPU utilization \emph{etc.} + \end{tcolorbox} + \end{frame} @@ -267,6 +306,9 @@ \tiny \textbf{Figure E.3:} Real-time control that is tightly-coupled with the IT equipment is a prerequisite for timely predictions within seconds/minutes~\cite{DBLP:journals/computer/AthavaleBBMMPS24}. \end{frame} + + + % Computational Fluid Dynamics (CFD) have high computation overhead, unsuitable for real-time simulation of a dynamic datacenter. %Moreover oftentimes a poorly configured CFD model can lead to high error rates~\cite{DBLP:conf/sensys/WangZD0TCWZ20}. %Data-driven Machine Learning performs poorly by the cases not covered in the training data. |