{"title":"An Introduction to Systems and Control Theory for Computer Scientists and Engineers","authors":"A. Leva","doi":"10.1145/3030207.3053677","DOIUrl":"https://doi.org/10.1145/3030207.3053677","url":null,"abstract":"This paper accompanies a tutorial aimed at introducing the basics of system and control theory so as to foster their utilisation for the management, but most important for the design, of computing systems. The tutorial is divided into three parts. The first one introduces the fundamental concepts of dynamic system and feedback and gives an overview of the properties that a control system has to enjoy, together with the main techniques to prescribe and assess these properties formally. The second part discusses a few computer-related application examples, revisiting the addressed problems from scratch with a system-centric viewpoint, and comparing the solutions - and most important, the way the system is viewed and designed - with state-of-the-art alternatives. This leads to envisage the potentialities of control-based computing systems design, but at the same time to identify open problems, both technological and methodological: an overview of these aspects is the subject of the third part. This companion paper motivates the tutorial, illustrates its rationale, and provides a commented outline.","PeriodicalId":310099,"journal":{"name":"Proceedings of the 8th ACM/SPEC on International Conference on Performance Engineering","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127146535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"SPEC Cloud™ IaaS 2016 Benchmark","authors":"Salman Baset, Márcio Silva, Nicholas Wakou","doi":"10.1145/3030207.3053675","DOIUrl":"https://doi.org/10.1145/3030207.3053675","url":null,"abstract":"The SPEC Cloud (TM) IaaS2016 benchmark is the Standard Performance Evaluation Corporation's (SPEC) first benchmark suite to measure cloud performance. The benchmark suite's use is targeted at cloud providers, cloud consumers, hardware vendors, virtualization software vendors, application software vendors, and academic researchers. The benchmark addresses the performance of infrastructure-as-a-service (IaaS) cloud platforms. IaaS cloud platforms can either be public or private. The key metrics of the benchmark are scalability, elasticity, and mean instance provisioning time.","PeriodicalId":310099,"journal":{"name":"Proceedings of the 8th ACM/SPEC on International Conference on Performance Engineering","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121924496","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
V. Apte, T.V.S. Viswanath, Devidas Gawali, Akhilesh Kommireddy, Anshul Gupta
{"title":"AutoPerf: Automated Load Testing and Resource Usage Profiling of Multi-Tier Internet Applications","authors":"V. Apte, T.V.S. Viswanath, Devidas Gawali, Akhilesh Kommireddy, Anshul Gupta","doi":"10.1145/3030207.3030222","DOIUrl":"https://doi.org/10.1145/3030207.3030222","url":null,"abstract":"A multi-tier Internet server application needs to be analyzed for its performance before it is released. Performance analysis is usually done by (a) load testing of the application on a testbed and (b) building a performance model of the application. While there are a plethora of Web load-generator tools available, there are two problems with these tools: one, the tests have to be configured manually, which can lead to a time-consuming trial-and-error process until the desired performance charts in the appropriate load ranges are obtained; and two, the load generator tools do not produce output that is directly useful for creating a performance model of the application. In this paper, we present AutoPerf, a load generator tool designed to meet two distinct goals, named capacity analysis and profiling. The goal of capacity analysis is to run a comprehensive load test on a Web application, in an appropriately chosen range, at a minimal number of load levels, while still producing an accurate graph of throughput and response time vs load levels. The goal of profiling is to generate a detailed server resource usage profile per request type, without instrumenting the application code. This data (e.g. CPU execution time by Web server for one request) is crucial for parameterizing performance models of the application. AutoPerf intelligently plans and configures its load tests by using analytical results from queuing theory along with some heuristics. Results show that AutoPerf is able to run performance tests very efficiently while still producing an accurate chart of performance metrics.","PeriodicalId":310099,"journal":{"name":"Proceedings of the 8th ACM/SPEC on International Conference on Performance Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129806989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fábio Coelho, J. Paulo, R. Vilaça, J. Pereira, R. Oliveira
{"title":"HTAPBench: Hybrid Transactional and Analytical Processing Benchmark","authors":"Fábio Coelho, J. Paulo, R. Vilaça, J. Pereira, R. Oliveira","doi":"10.1145/3030207.3030228","DOIUrl":"https://doi.org/10.1145/3030207.3030228","url":null,"abstract":"The increasing demand for real-time analytics requires the fusion of Transactional (OLTP) and Analytical (OLAP) systems, eschewing ETL processes and introducing a plethora of proposals for the so-called Hybrid Analytical and Transactional Processing (HTAP) systems. Unfortunately, current benchmarking approaches are not able to comprehensively produce a unified metric from the assessment of an HTAP system. The evaluation of both engine types is done separately, leading to the use of disjoint sets of benchmarks such as TPC-C or TPC-H. In this paper we propose a new benchmark, HTAPBench, providing a unified metric for HTAP systems geared toward the execution of constantly increasing OLAP requests limited by an admissible impact on OLTP performance. To achieve this, a load balancer within HTAPBench regulates the coexistence of OLTP and OLAP workloads, proposing a method for the generation of both new data and requests, so that OLAP requests over freshly modified data are comparable across runs. We demonstrate the merit of our approach by validating it with different types of systems: OLTP, OLAP and HTAP; showing that the benchmark is able to highlight the differences between them, while producing queries with comparable complexity across experiments with negligible variability.","PeriodicalId":310099,"journal":{"name":"Proceedings of the 8th ACM/SPEC on International Conference on Performance Engineering","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128452642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Andreas Schörgenhumer, Peter Hofer, David Gnedt, H. Mössenböck
{"title":"Efficient Sampling-based Lock Contention Profiling for Java","authors":"Andreas Schörgenhumer, Peter Hofer, David Gnedt, H. Mössenböck","doi":"10.1145/3030207.3030234","DOIUrl":"https://doi.org/10.1145/3030207.3030234","url":null,"abstract":"Concurrent code commonly uses locks. Choosing between simpler but less scalable and more sophisticated but error-prone locking mechanisms is difficult during development. Therefore, lock contention analysis at run-time is crucial to aid such decisions. We present a novel sampling-based approach for collecting detailed information on lock contention in Java applications by using the Java Virtual Machine Tool Interface (JVMTI) and bytecode instrumentation. We support both intrinsic locks as well as java.util.concurrent locks. Moreover, we can determine not only where contention occurs but also where it is caused. With a mean run-time overhead of about 5%, we consider our approach suitable for use in production environments.","PeriodicalId":310099,"journal":{"name":"Proceedings of the 8th ACM/SPEC on International Conference on Performance Engineering","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114472180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Tool Supporting the Analytical Evaluation of Service Level Agreements","authors":"Falko Bause, P. Buchholz, Johannes May","doi":"10.1145/3030207.3030215","DOIUrl":"https://doi.org/10.1145/3030207.3030215","url":null,"abstract":"Quantitative aspects of modern IT systems are often specified by service level agreements (SLAs) which relate the maximal load of a system with guaranteed bounds for response times and delays. These quantities are specified for single services which are combined in a service oriented architecture (SOA) to composed services offered to potential users or other service providers. To derive SLAs for composed services and to plan the required capacity to guarantee SLAs, appropriate methods and tools have to be used that compute results based on information given in SLAs. In this paper it is argued that most available approaches are not sufficient to analyze systems based on SLA information. A new method and a tool are presented that support the efficient calculation of bounds for delays in composed systems based on bounds for the load and the delay of the individual components which are specified in the SLAs of the components. Furthermore, the presented tool can be used to generate bounds for the required processing capacity which a provider has to provide in order to guarantee the quality of service defined in the SLAs. The presented approach is in some sense a counterpart to mean value analysis for queueing networks but rather than mean values, worst case bounds for different quantities like response times or departure processes are computed. Analysis is based on min/+ algebra but the mathematical approach is hidden from the user by a graphical interface allowing a simple graphical specification and result representation for networks of composed services.","PeriodicalId":310099,"journal":{"name":"Proceedings of the 8th ACM/SPEC on International Conference on Performance Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129143836","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An Empirical Analysis of Amazon EC2 Spot Instance Features Affecting Cost-effective Resource Procurement","authors":"Cheng Wang, Qianlin Liang, B. Urgaonkar","doi":"10.1145/3030207.3030210","DOIUrl":"https://doi.org/10.1145/3030207.3030210","url":null,"abstract":"Many cost-conscious public cloud workloads (\"tenants\") are turning to Amazon EC2's spot instances because, on average, these instances offer significantly lower prices (up to 10 times lower) than on-demand and reserved instances of comparable advertized resource capacities. To use spot instances effectively, a tenant must carefully weigh the lower costs of these instances against their poorer availability. Towards this, we empirically study four features of EC2 spot instance operation that a cost-conscious tenant may find useful to model. Using extensive evaluation based on both historical and current spot instance data, we show shortcomings in the state-of-the-art modeling of these features that we overcome. Our analysis reveals many novel properties of spot instance operation some of which offer predictive value while others do not. Using these insights, we design predictors for our features that offer a balance between computational efficiency (allowing for online resource procurement) and cost-efficacy. We explore \"case studies\" wherein we implement prototypes of dynamic spot instance procurement advised by our predictors for two types of workloads. Compared to the state-of-the-art, our approach achieves (i) comparable cost but much better performance (fewer bid failures) for a latency-sensitive in-memory Memcached cache, and (ii) an additional 18% cost-savings with comparable (if not better than) performance for a delay-tolerant batch workload.","PeriodicalId":310099,"journal":{"name":"Proceedings of the 8th ACM/SPEC on International Conference on Performance Engineering","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132456715","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Demo: Time Series Online Measurement for Python (TSOMpy)","authors":"M. Menth, F. Hauser","doi":"10.1145/3030207.3053673","DOIUrl":"https://doi.org/10.1145/3030207.3053673","url":null,"abstract":"TSOMpy is a Python library for online measurement of time series, i.e., it provides functions to calculate moving averages, moving histograms, and time-dependent rates. The demo illustrates various methods for these concepts and points out their differences. The tool can be used to apply online measurement to time series randomly generated according to specified stochastic processes or to own data sets. The library furthermore allows the reproduction of the tables and figures presented in [1].","PeriodicalId":310099,"journal":{"name":"Proceedings of the 8th ACM/SPEC on International Conference on Performance Engineering","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121814853","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"DuckTracks: Path-based Object Allocation Tracking","authors":"Stefan Fitzek, Philipp Lengauer, H. Mössenböck","doi":"10.1145/3030207.3030235","DOIUrl":"https://doi.org/10.1145/3030207.3030235","url":null,"abstract":"Efficiently tracking an application's object allocations is of interest for areas such as memory leak detection or memory usage optimization. The state-of-the-art approach of instrumenting every allocation site with a counter introduces considerable overhead. This makes allocation tracking in a production environment unattractive. Our approach reduces this overhead by instrumenting control flow paths instead of allocation sites and dynamically determining the hot path through a method. Our ultimate goal is to reduce the amount of required counter increments by such a degree that using it in production environments becomes feasible. We present an implementation of our approach for the Java HotSpot Virtual Machine. First measurements already show a reduction of required increments of up to 30% compared to the state of the art.","PeriodicalId":310099,"journal":{"name":"Proceedings of the 8th ACM/SPEC on International Conference on Performance Engineering","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125588349","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"HyperStar2: Easy Distribution Fitting of Correlated Data","authors":"Zhihao Shang, Tianhui Meng, K. Wolter","doi":"10.1145/3030207.3030243","DOIUrl":"https://doi.org/10.1145/3030207.3030243","url":null,"abstract":"In this paper, we present HyperStar2, a tool for fitting Markov Arrival Processes (MAPs) to empirical data. HyperStar2 uses a two-step approach, where the first step is cluster-based fitting of phase-type distributions and the second step is the construction of a correlation matrix. In the first step, we use the cluster-based algorithm for Hyper-Erlang distribution fitting from HyperStar hyper2012. Based on the Hyper-Erlang fitting result and the clusters of samples, in the second step we construct the correlation matrix. The tool targets engineers and scientists who need distribution fitting for non-standard distributions but have little interest in the underlying theory. Therefore the tool has a GUI that offers graphical presentation of the data, the fitted distribution and the empirical as well as theoretical autocorrelation. We discuss the use of HyperStar2 in common application scenarios and the fitting algorithms behind it. We provide some numerical examples, which show the abilities and limits of the fitting tool. We find that HyperStar2 can fit distributions very well but for some auto-correlation structures ProFiDo provides better results for auto-correlation.","PeriodicalId":310099,"journal":{"name":"Proceedings of the 8th ACM/SPEC on International Conference on Performance Engineering","volume":"280 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133309119","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}