Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userKhaos: Dynamically Optimizing Checkpointing for Dependable Distributed Stream Processing
122
0
0.0
(
0
)
Added by
Morgan Geldenhuys
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
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 systems 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 virtual cloud automation 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 steady-state 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.
rate research
Read More
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 Stream Processing (DSP) systems enable processing large streams of continuous data to produce results in near to real time. They are an essential part of many data-intensive applications and analytics platforms. The rate at which events arrive at DSP systems can vary considerably over time, which may be due to trends, cyclic, and seasonal patterns within the data streams. A priori knowledge of incoming workloads enables proactive approaches to resource management and optimization tasks such as dynamic scaling, live migration of resources, and the tuning of configuration parameters during run-times, thus leading to a potentially better Quality of Service. In this paper we conduct a comprehensive evaluation of different load prediction techniques for DSP jobs. We identify three use-cases and formulate requirements for making load predictions specific to DSP jobs. Automatically optimized classical and Deep Learning methods are being evaluated on nine different datasets from typical DSP domains, i.e. the IoT, Web 2.0, and cluster monitoring. We compare model performance with respect to overall accuracy and training duration. Our results show that the Deep Learning methods provide the most accurate load predictions for the majority of the evaluated datasets.
Fine tuning distributed systems is considered to be a craftsmanship, relying on intuition and experience. This becomes even more challenging when the systems need to react in near real time, as streaming engines have to do to maintain pre-agreed service quality metrics. In this article, we present an automated approach that builds on a combination of supervised and reinforcement learning methods to recommend the most appropriate lever configurations based on previous load. With this, streaming engines can be automatically tuned without requiring a human to determine the right way and proper time to deploy them. This opens the door to new configurations that are not being applied today since the complexity of managing these systems has surpassed the abilities of human experts. We show how reinforcement learning systems can find substantially better configurations in less time than their human counterparts and adapt to changing workloads.
We study the problem of load balancing in distributed stream processing engines, which is exacerbated in the presence of skew. We introduce Partial Key Grouping (PKG), a new stream partitioning scheme that adapts the classical power of two choices to a distributed streaming setting by leveraging two novel techniques: key splitting and local load estimation. In so doing, it achieves better load balancing than key grouping while being more scalable than shuffle grouping. We test PKG on several large datasets, both real-world and synthetic. Compared to standard hashing, PKG reduces the load imbalance by up to several orders of magnitude, and often achieves nearly-perfect load balance. This result translates into an improvement of up to 60% in throughput and up to 45% in latency when deployed on a real Storm cluster.
The International Telecommunication Union (ITU) Regional Radio Conference (RRC06) established in 2006 a new frequency plan for the introduction of digital broadcasting in European, African, Arab, CIS countries and Iran. The preparation of the plan involved complex calculations under short deadline and required dependable and efficient computing capability. The ITU designed and deployed in-situ a dedicated PC farm, in parallel to the European Organization for Nuclear Research (CERN) which provided and supported a system based on the EGEE Grid. The planning cycle at the RRC06 required a periodic execution in the order of 200,000 short jobs, using several hundreds of CPU hours, in a period of less than 12 hours. The nature of the problem required dynamic workload-balancing and low-latency access to the computing resources. We present the strategy and key technical choices that delivered a reliable service to the RRC06.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
