Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSinan: Data-Driven, QoS-Aware Cluster Management for Microservices
174
0
0.0
(
0
)
Added by
Christina Delimitrou
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Cloud applications are increasingly shifting from large monolithic services, to large numbers of loosely-coupled, specialized microservices. Despite their advantages in terms of facilitating development, deployment, modularity, and isolation, microservices complicate resource management, as dependencies between them introduce backpressure effects and cascading QoS violations. We present Sinan, a data-driven cluster manager for interactive cloud microservices that is online and QoS-aware. Sinan leverages a set of scalable and validated machine learning models to determine the performance impact of dependencies between microservices, and allocate appropriate resources per tier in a way that preserves the end-to-end tail latency target. We evaluate Sinan both on dedicated local clusters and large-scale deployments on Google Compute Engine (GCE) across representative end-to-end applications built with microservices, such as social networks and hotel reservation sites. We show that Sinan always meets QoS, while also maintaining cluster utilization high, in contrast to prior work which leads to unpredictable performance or sacrifices resource efficiency. Furthermore, the techniques in Sinan are explainable, meaning that cloud operators can yield insights from the ML models on how to better deploy and design their applications to reduce unpredictable performance.
rate research
Read More
Cloud service providers are distributing data centers geographically to minimize energy costs through intelligent workload distribution. With increasing data volumes in emerging cloud workloads, it is critical to factor in the network costs for transferring workloads across data centers. For geo-distributed data centers, many researchers have been exploring strategies for energy cost minimization and intelligent inter-data-center workload distribution separately. However, prior work does not comprehensively and simultaneously consider data center energy costs, data transfer costs, and data center queueing delay. In this paper, we propose a novel game theory-based workload management framework that takes a holistic approach to the cloud operating cost minimization problem by making intelligent scheduling decisions aware of data transfer costs and the data center queueing delay. Our framework performs intelligent workload management that considers heterogeneity in data center compute capability, cooling power, interference effects from task co-location in servers, time-of-use electricity pricing, renewable energy, net metering, peak demand pricing distribution, and network pricing. Our simulations show that the proposed game-theoretic technique can minimize the cloud operating cost more effectively than existing approaches.
The Internet of Things (IoT) paradigm is expected to bring ubiquitous intelligence through new applications in order to enhance living and other environments. Several research and standardization studies are now focused on the Middleware level of the underlying communication system. For this level, several challenges need to be considered, among them the Quality of Service (QoS) issue. The Autonomic Computing paradigm is now recognized as a promising approach to help communication and other systems to self-adapt when the context is changing. With the aim to promote the vision of an autonomic Middleware-level QoS management for IoT-based systems, this paper proposes a set of QoS-oriented mechanisms that can be dynamically executed at the Middleware level to correct QoS degradation. The benefits of the proposed mechanisms are also illustrated for a concrete case of Enhanced Living Environment.
To promote the benefits of the Internet of Things (IoT) in smart communities and smart cities, a real-time data marketplace middleware platform, called the Intelligent IoT Integrator (I3), has been recently proposed. While facilitating the easy exchanges of real-time IoT data streams between device owners and third-party applications through the marketplace, I3 is presently a monolithic, centralized platform for a single community. Although the service oriented architecture (SOA) has been widely adopted in the IoT and cyber-physical systems (CPS), it is difficult for a monolithic architecture to provide scalable, inter-operable and extensible services for large numbers of distributed IoT devices and different application vendors. Traditional security solutions rely on a centralized authority, which can be a performance bottleneck or susceptible to a single point of failure. Inspired by containerized microservices and blockchain technology, this paper proposed a BLockchain-ENabled Secure Microservices for Decentralized Data Marketplaces (BlendSM-DDM). Within a permissioned blockchain network, a microservices based security mechanism is introduced to secure data exchange and payment among participants in the marketplace. BlendSM-DDM is able to offer a decentralized, scalable and auditable data exchanges for the data marketplace.
Future wireless access networks need to support diversified quality of service (QoS) metrics required by various types of Internet-of-Things (IoT) devices, e.g., age of information (AoI) for status generating sources and ultra low latency for safety information in vehicular networks. In this paper, a novel inner-state driven random access (ISDA) framework is proposed based on distributed policy learning, in particular a cross-entropy method. Conventional random access schemes, e.g., $p$-CSMA, assume state-less terminals, and thus assigning equal priorities to all. In ISDA, the inner-states of terminals are described by a time-varying state vector, and the transmission probabilities of terminals in the contention period are determined by their respective inner-states. Neural networks are leveraged to approximate the function mappings from inner-states to transmission probabilities, and an iterative approach is adopted to improve these mappings in a distributed manner. Experiment results show that ISDA can improve the QoS of heterogeneous terminals simultaneously compared to conventional CSMA schemes.
Cloud platform came into existence primarily to accelerate IT delivery and to promote innovation. To this point, it has performed largely well to the expectations of technologists, businesses and customers. The service aspect of this technology has paved the road for a faster set up of infrastructure and related goals for both startups and established organizations. This has further led to quicker delivery of many user-friendly applications to the market while proving to be a commercially viable option to companies with limited resources. On the technology front, the creation and adoption of this ecosystem has allowed easy collection of massive data from various sources at one place, where the place is sometimes referred as just the cloud. Efficient data mining can be performed on raw data to extract potentially useful information, which was not possible at this scale before. Targeted advertising is a common example that can help businesses. Despite these promising offerings, concerns around security and privacy of user information suppressed wider acceptance and an all-encompassing deployment of the cloud platform. In this paper, we discuss security and privacy concerns that occur due to data exchanging hands between a cloud servicer provider (CSP) and the primary cloud user - the data collector, from the content generator. We offer solutions that encompass technology, policy and sound management of the cloud service asserting that this approach has the potential to provide a holistic solution.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
