Piyush Yadav, Dhaval Salwala, B. Sudharsan, E. Curry
{"title":"GNOSIS- query-driven multimodal event processing for unstructured data streams","authors":"Piyush Yadav, Dhaval Salwala, B. Sudharsan, E. Curry","doi":"10.1145/3491086.3492475","DOIUrl":"https://doi.org/10.1145/3491086.3492475","url":null,"abstract":"This paper presents GNOSIS, an event processing engine to detect complex event patterns over multimodal data streams. GNOSIS follows a query-driven approach where users can write complex event queries using Multimodal Event Processing Language (MEPL). The system models incoming multimodal data into an evolving Multimodal Event Knowledge Graph (MEKG) using an ensemble of deep neural network (DNN) and machine learning (ML) models and applies a neuro-symbolic approach for event matching. GNOSIS follows a serverless paradigm where its different components act as independent microservices and can be deployed across different nodes with optimized edge support. The paper demonstrates two multimodal use case queries from Occupational Health and Safety and Accessibility domain.","PeriodicalId":246858,"journal":{"name":"Proceedings of the 22nd International Middleware Conference: Demos and Posters","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122100232","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":"Bricks: a configurable coordination service with multiple consistency models","authors":"S. Maruyama, Xincheng Yang, W. H. Leung","doi":"10.1145/3491086.3492474","DOIUrl":"https://doi.org/10.1145/3491086.3492474","url":null,"abstract":"We present Bricks, a configurable coordination service that provides a set of features as building blocks. The developers then select and integrate those building blocks into components for their distributed applications. For example, multiple consistency models are realized by composing consistency components, which can be dynamically activated and deactivated. Bricks' APIs are backward-compatible with ZooKeeper's APIs.","PeriodicalId":246858,"journal":{"name":"Proceedings of the 22nd International Middleware Conference: Demos and Posters","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121521405","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}
Germán T. Eizaguirre, Marc Sánchez Artigas, P. López
{"title":"A milestone for FaaS pipelines; object storage-vs VM-driven data exchange","authors":"Germán T. Eizaguirre, Marc Sánchez Artigas, P. López","doi":"10.1145/3491086.3492472","DOIUrl":"https://doi.org/10.1145/3491086.3492472","url":null,"abstract":"Serverless functions provide high levels of parallelism, short startup times, and \"pay-as-you-go\" billing. These attributes make them a natural substrate for data analytics workflows. However, the impossibility of direct communication between functions makes the execution of workflows challenging. The current practice to share intermediate data among functions is through remote object storage (e.g., IBM COS). Contrary to conventional wisdom, the performance of object storage is not well understood. For instance, object storage can even be superior to other simpler approaches like the execution of shuffle stages (e.g., GroupBy) inside powerful VMs to avoid all-to-all transfers between functions. Leveraging a genomics pipeline, we show that object storage is a reasonable choice for data passing when the appropriate number of functions is used in shuffling stages.","PeriodicalId":246858,"journal":{"name":"Proceedings of the 22nd International Middleware Conference: Demos and Posters","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117151919","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}
Murtazain Raza, Jawad Tahir, Christoph Doblander, R. Mayer, H. Jacobsen
{"title":"Benchmarking Apache Kafka under network faults","authors":"Murtazain Raza, Jawad Tahir, Christoph Doblander, R. Mayer, H. Jacobsen","doi":"10.1145/3491086.3492470","DOIUrl":"https://doi.org/10.1145/3491086.3492470","url":null,"abstract":"Network faults are often transient and hence hard to detect and difficult to resolve. Our study conducts an analysis of Kafka's network fault tolerance capabilities, one of the widely used distributed stream processing system (DSPS). Across different Kafka configurations, we observed that Kafka is fault-tolerant towards network faults to some degree, and we report observations of its shortcomings. We also define a network fault-tolerance benchmark on which other DSPSs can be evaluated.","PeriodicalId":246858,"journal":{"name":"Proceedings of the 22nd International Middleware Conference: Demos and Posters","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123338713","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":"DyMonD","authors":"Mona Elsaadawy, Aaron Lohner, Ruoyu Wang, Jifeng Wang, Bettina Kemme","doi":"10.1145/3491086.3492471","DOIUrl":"https://doi.org/10.1145/3491086.3492471","url":null,"abstract":"Cloud applications are often implemented as distributed services that call each other, creating complex application call graphs. Tracking such call graphs is crucial to diagnose and resolve performance issues. This paper presents DyMonD, a holistic framework that dynamically monitors the software layer of the cloud network to track dependencies between application components and derive performance metrics. It adapts a deep learning model to identify the service type of each component, and visualizes all information in form of a call graph. Our evaluation results confirm that DyMonD can infer the proper call graph and identify the services at run-time with acceptable overhead and good accuracy.","PeriodicalId":246858,"journal":{"name":"Proceedings of the 22nd International Middleware Conference: Demos and Posters","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125799314","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":"Proceedings of the 22nd International Middleware Conference: Demos and Posters","authors":"","doi":"10.1145/3491086","DOIUrl":"https://doi.org/10.1145/3491086","url":null,"abstract":"","PeriodicalId":246858,"journal":{"name":"Proceedings of the 22nd International Middleware Conference: Demos and Posters","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121009735","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 zero-knowledge proof system for OpenLibra","authors":"Patrick Biel, Shiquan Zhang, H. Jacobsen","doi":"10.1145/3491086.3492469","DOIUrl":"https://doi.org/10.1145/3491086.3492469","url":null,"abstract":"Zero-knowledge proofs (ZKPs) have garnered much attention recently. They have witnessed applicability in anonymizing tokens (e.g., Tornado Cash) and increasing transaction throughput (e.g., ZK-Rollups) for blockchains backing cryptocurrencies. ZKPs are touted to offer great potential for future blockchain applications that operate in a priori trustless environments across administrative boundaries. This short note discusses the integration of the ZK-STARK-based proof system into the OpenLibra blockchain. We generically describe the interaction of the involved ZKP capabilities with OpenLibra and showcase an open-sourced proof-of-concept implementation.","PeriodicalId":246858,"journal":{"name":"Proceedings of the 22nd International Middleware Conference: Demos and Posters","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134402909","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}
Peini Liu, Gusseppe Bravo Rocca, Jordi Guitart, Ajay Dholakia, David Ellison, M. Hodak
{"title":"Scanflow: an end-to-end agent-based autonomic ML workflow manager for clusters","authors":"Peini Liu, Gusseppe Bravo Rocca, Jordi Guitart, Ajay Dholakia, David Ellison, M. Hodak","doi":"10.1145/3491086.3492468","DOIUrl":"https://doi.org/10.1145/3491086.3492468","url":null,"abstract":"Machine Learning (ML) is more than just training models, the whole life-cycle must be considered. Once deployed, a ML model needs to be constantly managed, supervised and debugged to guarantee its availability, validity and robustness in dynamic contexts. This demonstration presents an agent-based ML workflow manager so-called Scanflow1, which enables autonomic management and supervision of the end-to-end life-cycle of ML workflows on distributed clusters. The case study on a MNIST project2 shows that different teams can collaborate using Scanflow within a ML project at different phases, and the effectiveness of agents to maintain the model accuracy and throughput of the model serving while running in production.","PeriodicalId":246858,"journal":{"name":"Proceedings of the 22nd International Middleware Conference: Demos and Posters","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114505443","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":"Benchmarking-as-a-service for cloud-hosted DBMS","authors":"Daniel Seybold, Jörg Domaschka","doi":"10.1145/3491086.3492473","DOIUrl":"https://doi.org/10.1145/3491086.3492473","url":null,"abstract":"Database Management Systems (DBMS) operated on cloud resources are the storage backend for a multitude of data-intensive applications. In the process of finding the optimal cloud and DBMS, benchmarking is the common approach to evaluate the non-functional features. However, benchmarking cloud-hosted DBMS is a complex, error-prone and time-consuming task. The Benchmarking-as-a-Service platform benchANT demonstrates how these challenges are resolved by an end-to-end automated benchmarking process.","PeriodicalId":246858,"journal":{"name":"Proceedings of the 22nd International Middleware Conference: Demos and Posters","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131901046","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}