A Cooperative, Self-Configuring High-Availability Solution for Stream Processing

Nowadays production flows are modular, each module in the enterprise being specialized and used to achieve a particular task. In many cases the modules are interconnected and materials are sequentially processed in each module resulting a final, unique product or assembly. One typical such production module is a flexible cell/system using multiple robots. In such complex enterprise environments, providing continuous services for applications is a key component of a successful implementing of robotized manufacturing. High availability (HA) is one of the components contributing to continuous service provision for applications, by masking or eliminating both planned and unplanned downtime of systems and applications. This is achieved by eliminating hardware and software single points of failure (SPOF). The systems configured for high availability are a combination of hardware and software components configured to work together to ensure automated recovery in case of failure with a minimal acceptable downtime. A high availability solution will ensure that the failure of any component of the solution either hardware, software or system management, will not cause the application and its data to become permanently unavailable. High availability solutions should eliminate single points of failure through appropriate design, planning, hardware selection, software configuring, application control, carefully environment control and change management discipline. In short, one can define high availability as the process of ensuring an application is available for use by duplicating and/or sharing hardware resources managed by a specialized software component. A high availability solution in robotized manufacturing provides automated failure detection, diagnosis, application recovery, and node (robot controller) re integration. The chapter discusses the implementing of a high availability solution in a robotized manufacturing structure (cell, line). The solution is based on a High Availability Linux Cluster which is responsible for data availability and preservation on a NFS (Network File System) file system, and a second cluster – Fabrication Cluster (FC) which runs on Adept robot controllers, developed under the V+ programming language.

Real-time big data processing is a crucial need of meteorology today. As a matter of fact, the weather is a determining factor in decision making in different areas such as air or sea transport, so acquiring knowledge of the environment in real time is a consequential question. A promising approach for big data treatment in real time is based on the concept of complex events processing CEP). The CEP aims to identify significant events in a cloud of simple and individually detectable events in real time. The meteorological variables, constituting simple event's spaces, offer significant flow of data to be processed using CEP technologies. This real-time data processing is done by phase of their integration with weather systems. This paper discusses the big data's meteorological aspects, and shows the architectural model for integration of weather data and its processing in real time.

In recent decades, virtualization as an abstraction from physical hardware has become a popular solution to resource isolation and server consolidation. With the surge in adoption of virtualization technologies, ensuring High Availability (HA) for applications hosted in virtualized environments emerges as an important problem and has garnered substantial attention. In this paper, we present a brief comparison of virtualization technologies from a HA perspective. The state-of-the-art HA solutions in two mainstream types of virtualized platforms (i.e., hypervisor-based platform and container-based platform) are respectively investigated in terms of limitations and features such as live migration, failure detection, and checkpoint/ restore. One of our key findings is that, compared with hypervisor-based platforms, HA features in container-based platforms are far from enough. From a HA perspective, extensions on top of container technologies are required.

Working in tandem, the Hadoop Distributed File System (HDFS) plays a crucial role in managing large-scale data across distributed clusters. The basic structure of HDFS comprises the NameNode, which manages the file system namespace and client interactions, and the Data Nodes, which handle storage and data arrangement duties. Although HDFS faces constraints, particularly regarding scaling the NameNode, which is responsible for managing metadata, these constraints impact namespace scalability and performance. Therefore, this paper discusses the two architectures, the Quorum Journal Manager (QJM) components and the active and standby NameNodes, which enable the sharing of edit logs between them. To mitigate the risk of metadata corruption from split-brain scenarios, the system ensures that only a single NameNode writes to the JournalNodes. Through the utilization of the QJM, HDFS attains High Availability (HA), enabling swift failover in the event of machine crashes or scheduled maintenance. Dynamic Federated Metadata Management (DFMM) addresses the limitations of the current Hadoop architecture by distributing metadata management across multiple federated components. It entails dispersing metadata management among various federated components. HDFS can overcome the problems of connected block storage, namespace scalability, and performance bottlenecks by dynamically managing metadata on an exabyte scale. This work summarizes the key findings and presents a comparative analysis of both architectures. QJM performs a vital function that ensures the high availability, reliability, and fault tolerance of the NameNode in Hadoop’s HDFS. DFMM enhances the fault tolerance, scalability, and performance of distributed file systems by distributing metadata across multiple servers or nodes.

In the last chapter, we talked about some basic things about MVCC in PostgreSQL, and what is bloat in the database and how it can be removed. We explained how autovacuum helps in removing bloat and improving performance. We also covered the best practices to execute maintenance activities like vacuum, reindex in detail. In this chapter, we will talk about the importance of High Availability (HA), and what information we need to build an HA solution and the procedures to implement it in PostgreSQL. We will cover some open source and enterprise tools to implement HA. We will also cover the importance of a pooler, and available poolers on the market and their implementation.

Stream processing is widely used by today's applications such as financial data analysis and disaster response. In distributed stream processing systems, machine fail-stop events are handled by either active standby or passive standby. However, existing high availability (HA) schemes have not sufficiently addressed the situation when a machine becomes temporarily unavailable due to data rate spikes, intensive analysis or job sharing, which happens frequently but lasts for short time. It is not clear how well active and passive standby fare against such transient unavailability. In this paper, we first critically examine the suitability of active and passive standby against transient unavailability in a real testbed environment. We find that both approaches have advantages and drawbacks, but neither is ideal to provide fast recovery at low overhead as required to handle transient unavailability. Based on the insights gained, we propose a novel hybrid HA method that switches between active and passive standby modes depending on the occurrence of failure events. It presents a desirable tradeoff that is different from existing HA approaches: low overhead during normal conditions and fast recovery upon transient or permanent failure events. We have implemented our hybrid method and compared it with existing HA designs with comprehensive evaluation. The results show that our hybrid method can reduce two-thirds of the recovery time compared to passive standby and 80% message overhead compared to active standby, allowing applications to enjoy uninterrupted processing without paying a high premium.

The ubiquity of location enabled devices has resulted in a wide proliferation of location based applications and services. To handle the growing scale, database management systems driving such location based services (LBS) must cope with high insert rates for location updates of millions of devices, while supporting efficient real-time analysis on latest location. Traditional DBMSs, equipped with multi-dimensional index structures, can efficiently handle spatio-temporal data. However, popular open source relational database systems are overwhelmed by the high insertion rates, real-time querying requirements, and terabytes of data that these systems must handle. On the other hand, Key-value stores can effectively support large scale operation, but do not natively support multi-attribute accesses needed to support the rich querying functionality essential for the LBSs. We present MD-HBase, a scalable data management system for LBSs that bridges this gap between scale and functionality. Our approach leverages a multi-dimensional index structure layered over a Key-value store. The underlying Key-value store allows the system to sustain high insert throughput and large data volumes, while ensuring fault-tolerance, and high availability. On the other hand, the index layer allows efficient multi-dimensional query processing. We present the design of MD-HBase that builds two standard index structuresâ€"the K-d tree and the Quad treeâ€"over a range partitioned Key-value store. Our prototype implementation using HBase, a standard open-source Key-value store, can handle hundreds of thousands of inserts per second using a modest 16 node cluster, while efficiently processing multidimensional range queries and nearest neighbor queries in real-time with response times as low as hundreds of milliseconds.

Cloud computing has already been adopted in a broad range of application domains and has become an established building block in IT landscapes. During the process of cloud middleware development, the companies have focused mainly on the high availability of data and end-user services, but unfortunately neglected the availability of middleware components. Therefore failures of the middleware components itself usually leads to a partial or even total blackout of the cloud. In this paper, we present the design and implementation of a novel scalable and highly available multi-master pattern for cloud middlewares. In contrast to existing Infrastructure-as-a-Service cloud management frameworks, which are usually designed in a centralized tree topology composed in a three-tiered master worker architecture, we introduce a concept for a multi tree with all tree roots connected in a fully connected mesh topology. In this architecture user requests are load balanced over multiple failover servers. Furthermore, our concept includes an automatic self-healing mechanism for worker nodes of each tree.

A large class of modern distributed file systems treat metadata services as an independent system component, separately from data servers. The availability of the metadata service is key to the availability of the overall system. Given the high rates of failures observed in large-scale data centers, distributed file systems usually incorporate high-availability (HA) features. A typical approach in the development of distributed file systems is to design and develop metadata services from the ground up, at significant cost in terms of complexity and time, often leading to functional shortcomings. Our motivation in this paper was to improve on this state of things by defining a general-purpose architecture for HA metadata services (which we call RMS) that can be easily incorporated and reused in new or existing file systems, reducing development time. Taking two prominent distributed file systems as case studies, PVFS and HDFS, we developed RMS variants that improve on functional shortcomings of the original HA solutions, while being easy to build and test. Our extensive evaluation of the RMS variant of HDFS shows that it does not incur an overall performance or availability penalty compared to the original implementation.

Having both AppFabric and SQL Server installed on a single computer is sufficient for a development environment; however, a production environment will often consist of multiple computers in a server farm, as well as one or more dedicated SQL Server machines. Scaling-out allows you to implement load-balancing solutions, so that the processing of incoming messages is spread across multiple servers. This also enables you to provide increased fault tolerance for workflows that use persistence. Such an environment might also use queues to manage incoming messages destined for your application and SQL Server clustering for high availability.

During the last several years, we have established the symmetric active/active replication model for service-level high availability and implemented several proof- of-concept prototypes. One major deficiency of our model is its inability to deal with dependent services, since its original architecture is based on the client- service model. This paper extends our model to dependent services using its already existing mechanisms and features. The presented concept is based on the idea that a service may also be a client of another service, and multiple services may be clients of each other. A high-level abstraction is used to illustrate dependencies between clients and services, and to decompose dependencies between services into respective client-service dependencies. This abstraction may be used for providing high availability in distributed computing systems with complex service-oriented architectures.

Cloud computing provides virtual resources so that end-users or organizations can buy computing power as a public utility. Cloud service providers however must strive to ensure good QoS by offering highly available services with dynamically scalable resources. HA-OSCAR is an open source High Availability (HA) solution for HPC/cloud that offers component redundancy, failure detection, and automatic fail-over. In this paper, we describe HA-OSCAR as a cloud platform and analyze system availability of two potential cloud computing systems, OSCAR-V cluster and HA-OSCAR-V. We also explore our case study to improve Nimbus, a popular cloud IaaS toolkit. The results show that the system that deploys HA-OSCAR has a significantly higher degree of availability.

It is important for any organization to handle increase in data; normally this is the job of the DBA in organization to take care of this data growth, along with its protection and its availability. High availability of data is also most important for organizations, for that purpose, shared storage is usually the solution, for example, SAN or NAS storage as Microsoft Cluster Database instances. Mostly Organization does not have shared storage in their infrastructure, which was required for Microsoft cluster SQL database instance; due to that they used other native methods to implement like log shipping or database mirroring, which was not efficient method for high-availability and disaster-recovery solution. After that, Microsoft introduced native method called SQL AlwaysOn method that could be implemented without using SAN and NAS storage method to implement high availability and disaster recovery without using shared storage. SQL AlwaysOn option is using only Microsoft cluster service and shared folder between the nodes. This paper written for DBA and System Administrators; and is implementation of Microsoft SQL Database tier step by step.

The rapid growth of e-commerce has brought about challenges in managing traffic loads and ensuring the availability of database servers. One critical issue is what happens when the main database server fails, potentially leading to downtime or data loss. This research aims to address these problems by optimizing server resource distribution and implementing data replication across multiple database servers. The goal is to enhance system efficiency, prevent server overloads, ensure data availability, and minimize downtime or data loss when server failures occur.This research utilizes a multi-stage methodology. First, data collection was conducted to gather relevant information. In the second stage, a needs analysis was performed to identify system requirements. The third stage involved designing the system architecture, including the creation of entity-relationship diagrams (ERD), flowcharts, and network topologies. In the final stage, the system was implemented through database replication and the application of failover methods.The results demonstrate that the failover mechanism operates effectively, ensuring that data is successfully replicated across all database servers. This confirms that the system achieves high availability and minimizes the risk of data loss or service downtime. The implications of this research provide a reliable solution for improving the resilience and performance of e-commerce systems, particularly in managing database server failures.

Today's high performance computing systems have several reliability deficiencies resulting in availability and serviceability issues. Head and service nodes represent a single point of failure and control for an entire system as they render it inaccessible and unmanageable in case of a failure until repair, causing a significant downtime. This paper introduces two distinct replication methods (internal and external) for providing symmetric active/active high availability for multiple head and service nodes running in virtual synchrony. It presents a comparison of both methods in terms of expected correctness, ease-of-use and performance based on early results from ongoing work in providing symmetric active/active high availability for two HPC system services (TORQUE and PVFS metadata server). It continues with a short description of a distributed mutual exclusion algorithm and a brief statement regarding the handling of Byzantine failures. This paper concludes with an overview of past and ongoing work, and a short summary of the presented research.