Tightly coupled multiprocessor systems with high availability exploiting fault-tolerance features

1987 ◽  
Vol 20 (1-3) ◽  
pp. 11-13
Author(s):  
Riccardo Curti
Author(s):  
Asif Imran ◽  
Alim Ul Gias ◽  
Rayhanur Rahman ◽  
Amit Seal ◽  
Tajkia Rahman ◽  
...  

Author(s):  
В.А. Рудометкин

В настоящее время большинство сервисов переходят в онлайн, что позволяет пользователям получать услугу в любое время. Высокая доступность услуги приводит к росту количества пользователей, что влечет за собой повышение нагрузки на систему, поэтому необходимо уделить особое внимание отказоустойчивости системы перед началом ее разработки. Рассматриваются основные проблемы высоконагруженных систем, способ оптимизации приложения путем распараллеливания задач по ядрам процессора. В данной статье описывается необходимость перехода на микросервисную архитектуру, ее недостатки и способы их устранения. В процессе решения проблем масштабирования, затрагиваются проблемы распределенных транзакций и долгого ответа от сервера. Nowadays, most of the services are moving online, which allows users to receive the service at any time. The high availability of the service leads to an increase in the number of users, which entails an increase in the load on the system, therefore, it is necessary to pay special attention to the fault tolerance of the system before starting its development. The main problems of high-load systems, a way to optimize an application by parallelizing tasks across processor cores are considered. This article describes the need to migrate to a microservice architecture, its weaknesses, and how to fix them. In the process of solving scaling problems, the problems of distributed transactions and long response from the server are addressed.


2020 ◽  
Vol 8 (5) ◽  
pp. 2040-2044

The cloud technologies are gaining boom in the field of information technology. But on the same side cloud computing sometimes results in failures. These failures demand more reliable frameworks with high availability of computers acting as nodes. The request made by the user is replicated and sent to various VMs. If one of the VMs fail, the other can respond to increase the reliability. A lot of research has been done and being carried out to suggest various schemes for fault tolerance thus increasing the reliability. Earlier schemes focus on only one way of dealing with faults but the scheme proposed by the the author in this paper presents an adaptive scheme that deals with the issues related to fault tolerance in various cloud infrastructure. The projected scheme uses adaptive behavior during the selection of replication and fine-grained checkpointing methods for attaining a reliable cloud infrastructure that can handle different client requirements. In addition to it the algorithm also determines the best suited fault tolerance method for every designated virtual node. Zheng, Zhou,. Lyu and I. King (2012).


2009 ◽  
Vol 10 (6) ◽  
pp. 922-926 ◽  
Author(s):  
Shervin Vakili ◽  
Sied Mehdi Fakhraie ◽  
Siamak Mohammadi ◽  
Ali Ahmadi

2015 ◽  
Vol 5 (2) ◽  
pp. 36-52 ◽  
Author(s):  
Sikha Bagui ◽  
Loi Tang Nguyen

In this paper, the authors present an architecture and implementation of a distributed database system using sharding to provide high availability, fault-tolerance, and scalability of large databases in the cloud. Sharding, or horizontal partitioning, is used to disperse the data among the data nodes located on commodity servers for effective management of big data on the cloud.


Sign in / Sign up

Export Citation Format

Share Document