Distributed Stream Processing (DSP) focuses on the near real-time processing of large streams of unbounded data. To increase processing capacities, DSP systems are able to dynamically scale across a cluster of commodity nodes, ensuring a good Quality of Service despite variable workloads. However, selecting scaleout configurations which maximize resource utilization remains a challenge. This is especially true in environments where workloads change over time and node failures are all but inevitable. Furthermore, configuration parameters such as memory allocation and checkpointing intervals impact performance and resource usage as well. Sub-optimal configurations easily lead to high operational costs, poor performance, or unacceptable loss of service.

To maintain a stable Quality of Service (QoS), these systems require a sufficient allocation of resources. At the same time, over-provisioning can result in wasted energy and high operating costs. Therefore, to maximize resource utilization, autoscaling methods have been proposed that aim to efficiently match the resource allocation with the incoming workload. However, determining when and by how much to scale remains a significant challenge. Given the long-running nature of DSP jobs, scaling actions need to be executed at runtime, and to maintain a good QoS, they should be both accurate and infrequent. To address the challenges of autoscaling, the concept of self-adaptive systems is particularly fitting. These systems monitor themselves and their environment, adapting to changes with minimal need for expert involvement.

Stream processing has become a critical component in the architecture of modern applications. With the exponential growth of data generation from sources such as the Internet of Things, business intelligence, and telecommunications, real-time processing of unbounded data streams has become a necessity. DSP systems provide a solution to this challenge, offering high horizontal scalability, fault-tolerant execution, and the ability to process data streams from multiple sources in a single DSP job. Often enough though, data streams need to be enriched with extra information for correct processing, which introduces additional dependencies and potential bottlenecks.In this paper, we present an in-depth evaluation of data enrichment methods for DSP systems and identify the different use cases for stream processing in modern systems. Using a representative DSP system and conducting the evaluation in a realistic cloud environment, we found that outsourcing enrichment data to the DSP system can improve performance for specific use cases. However, this increased resource consumption highlights the need for stream processing solutions specifically designed for the performance-intensive workloads of cloud-based applications.

Distributed Stream Processing systems are becoming an increasingly essential part of Big Data processing platforms as users grow ever more reliant on their ability to provide fast access to new results.As such, making timely decisions based on these results is dependent on a system's ability to tolerate failure.Typically, these systems achieve fault tolerance and the ability to recover automatically from partial failures by implementing checkpoint and rollback recovery.However, owing to the statistical probability of partial failures occurring in these distributed environments and the variability of workloads upon which jobs are expected to operate, static configurations will often not meet Quality of Service constraints with low overhead.In this paper we present Khaos, a new approach which utilizes the parallel processing capabilities of cloud orchestration technologies for the automatic runtime optimization of fault tolerance configurations in Distributed Stream Processing jobs.Our approach employs three subsequent phases which borrows from the principles of Chaos Engineering: establish the steadystate processing conditions, conduct experiments to better understand how the system performs under failure, and use this knowledge to continuously minimize Quality of Service violations.We implemented Khaos prototypically together with Apache Flink and demonstrate its usefulness experimentally.

Distributed Stream Processing systems have become an essential part of big data processing platforms. They are characterized by the high-throughput processing of near to real-time event streams with the goal of delivering low-latency results and thus enabling time-sensitive decision making. At the same time, results are expected to be consistent even in the presence of partial failures where exactly-once processing guarantees are required for correctness. Stream processing workloads are oftentimes dynamic in nature which makes static configurations highly inefficient as time goes by. Static resource allocations will almost certainly either negatively impact upon the Quality of Service and/or result in higher operational costs.In this paper we present Phoebe, a proactive approach to system auto-tuning for Distributed Stream Processing jobs executing on dynamic workloads. Our approach makes use of parallel profiling runs, QoS modeling, and runtime optimization to provide a general solution whereby configuration parameters are automatically tuned to ensure a stable service as well as alignment with recovery time Quality of Service targets. Phoebe makes use of Time Series Forecasting to gain an insight into future workload requirements thereby delivering scaling decisions which are accurate, long-lived, and reliable. Our experiments demonstrate that Phoebe is able to deliver a stable service while at the same time reducing resource over-provisioning.

The Internet of Things describes a network of physical devices interacting and producing vast streams of sensor data. At present there are a number of general challenges which exist while developing solutions for use cases involving the monitoring and control of urban infrastructures. These include the need for a dependable method for extracting value from these high volume streams of time sensitive data which is adaptive to changing workloads. Low-latency access to the current state for live monitoring is a necessity as well as the ability to perform queries on historical data. At the same time, many design choices need to be made and the number of possible technology options available further adds to the complexity. In this paper we present a dependable IoT data processing platform for the monitoring and control of urban infrastructures. We define requirements in terms of dependability and then select a number of mature open-source technologies to match these requirements. We examine the disparate parts necessary for delivering a holistic overall architecture and describe the dataflows between each of these components. We likewise present generalizable methods for the enrichment and analysis of sensor data applicable across various application areas. We demonstrate the usefulness of this approach by providing an exemplary prototype platform executing on top of Kubernetes and evaluate the effectiveness of jobs processing sensor data in this environment.

Distributed dataflow systems like Spark and Flink enable the use of clusters for scalable data analytics. While runtime prediction models can be used to initially select appropriate cluster resources given target runtimes, the actual runtime performance of dataflow jobs depends on several factors and varies over time. Yet, in many situations, dynamic scaling can be used to meet formulated runtime targets despite significant performance variance.This paper presents Enel, a novel dynamic scaling approach that uses message propagation on an attributed graph to model dataflow jobs and, thus, allows for deriving effective rescaling decisions. For this, Enel incorporates descriptive properties that capture the respective execution context, considers statistics from individual dataflow tasks, and propagates predictions through the job graph to eventually find an optimized new scale-out. Our evaluation of Enel with four iterative Spark jobs shows that our approach is able to identify effective rescaling actions, reacting for instance to node failures, and can be reused across different execution contexts.

Fault tolerance is a property which needs deeper consideration when dealing with streaming jobs requiring high levels of availability and low-latency processing even in case of failures where Quality-of-Service constraints must be adhered to. Typically, systems achieve fault tolerance and the ability to recover automatically from partial failures by implementing Checkpoint and Rollback Recovery. However, this is an expensive operation which impacts negatively on the overall performance of the system and manually optimizing fault tolerance for specific jobs is a difficult and time consuming task.In this paper we introduce Chiron, an approach for automatically optimizing the frequency with which checkpoints are performed in streaming jobs. For any chosen job, parallel profiling runs are performed, each containing a variant of the configurations, with the resulting metrics used to model the impact of checkpoint-based fault tolerance on performance and availability. Understanding these relationships is key to minimizing performance objectives and meeting strict Quality-of-Service constraints. We implemented Chiron prototypically together with Apache Flink and demonstrate its usefulness experimentally.

With weather becoming more extreme both in terms of longer dry periods and more severe rain events, municipal water networks are increasingly under pressure. The effects include damages to the pipes, flash floods on the streets and combined sewer overflows. Retrofitting underground infrastructure is very expensive, thus water infrastructure operators are increasingly looking to deploy IoT solutions that promise to alleviate the problems at a fraction of the cost.In this paper, we report on preliminary results from an ongoing joint research project, specifically on the design and evaluation of its data analytics platform. The overall system consists of energy-efficient sensor nodes that send their observations to a stream processing engine, which analyzes and enriches the data and transmits the results to a GIS-based frontend. As the proposed solution is designed to monitor large and critical infrastructures of cities, several non-functional requirements such as scalability, responsiveness and dependability are factored into the system architecture. We present a scalable stream processing platform and its integration with the other components, as well as the algorithms used for data processing. We discuss significant challenges and design decisions, introduce an efficient data enrichment procedure and present empirical results to validate the compliance with the target requirements. The entire code for deploying our platform and running the data enrichment jobs is made publicly available with this paper.

The emergence of the Internet of Things has seen the introduction of numerous connected devices used for the monitoring and control of even Critical Infrastructures. Distributed stream processing has become key to analyzing data generated by these connected devices and improving our ability to make decisions. However, optimizing these systems towards specific Quality of Service targets is a difficult and time-consuming task, due to the large-scale distributed systems involved, the existence of so many configuration parameters, and the inability to easily determine the impact of tuning these parameters.In this paper we present an approach for the effective testing of system configurations for critical IoT analytics pipelines. We demonstrate our approach with a prototype that we called Timon which is integrated with Kubernetes. This tool allows pipelines to be easily replicated in parallel and evaluated to determine the optimal configuration for specific applications. We demonstrate the usefulness of our approach by investigating different configurations of an exemplary geographically-based traffic monitoring application implemented in Apache Flink.

International audience