As a new computing concept and model, cloud computing is technically to cluster large server clusters, including computing servers, storage servers and network bandwidth resources. Through virtualization of various assignable resources, special software is used to implement The on-demand allocation of resources supports the operation of various applications, so that users only need to pay attention to and provide business-related solutions, without the need for a lot of manpower and material resources in hardware platform, integrated computing, secure storage, and information consistency. And financial resources are conducive to improving the overall efficiency of the system, reducing costs and promoting technological innovation.
Although the computing platform or service based on the cloud computing model has been widely accepted and gradually applied to the application, the research of cloud computing is still in its infancy, and many existing problems have not been completely solved. This paper presents some of the key technologies and research issues of cloud computing.
1 virtual machine migration
Cloud computing enables load balancing across the data center by allowing virtual machine migration. In addition, virtual machine migration improves the robustness and responsiveness of the data center.
Virtual machine migration is a evolution of process migration. Recently, Xen and VMWare have implemented live migration of virtual machines. Literature [1] pointed out that migrating the entire operating system and all its applications as a unit can avoid many difficulties faced by the process-level migration method, and analyzes the advantages of virtual machine live migration.
The main advantage of virtual machine migration is to avoid hot spots, however, this is not simple. Currently, detecting workload hotspots and initiating a migration lack the flexibility to cope with sudden workload changes. In addition, the state of the memory in the virtual machine migration should be consistent and efficient transmission, while also considering the resource load of the application and the physical server.
2 server integration
Server consolidation maximizes resource utilization while minimizing the effective way to consume energy. Virtual machine migration is often used to consolidate virtual machines residing on multiple rarely used servers to one server so that the remaining servers can be set to a power-saving state. Optimizing the integration server in the data center is usually an NP-hard variant. Various heuristic methods have been proposed for this problem.
Server consolidation should not affect the performance of your application. As we all know, the use of a single virtual machine resource is constantly changing. For server resources shared between virtual machines (such as bandwidth, memory cache, and disk I/O), maximizing server consolidation can cause congestion.
Therefore, it is important to observe the fluctuations in virtual machine load and the efficient integration of servers with this information. Finally, when resource congestion occurs, the system must be able to respond quickly.
3 Energy management
Improving energy efficiency is another major issue in cloud computing. It is estimated that energy costs account for 53% of total data center operating expenses. As a result, infrastructure providers are under tremendous pressure to reduce energy consumption. The goal is not only to reduce the energy costs of the data center, but also to meet government regulations and environmental standards.
Designing energy-efficient data centers has recently received increasing attention. This problem can be solved in multiple directions. For example, energy-efficient hardware architecture, slowing down CPU speeds, and shutting down some hardware components have become the consensus of researchers.
Energy-aware job scheduling and server integration can reduce energy consumption. Recent research has also begun to study energy-efficient network protocols and infrastructure.
A key challenge is to achieve a good balance between saving energy and the performance of the application. In this regard, some researchers have recently begun to implement coordinated solutions for performance and energy management in a dynamic cloud environment [3].
4 Traffic Management and Analysis
Analyzing data traffic is important for today's data centers. For example, many web applications rely on analyzing data traffic to optimize the user experience. Network operators also need to know about data traffic for many management and planning decisions. However, extending the existing measurement and analysis methods of Internet Service Providers (ISPs) to cloud computing data centers presents some challenging issues. First, data center links are much denser than ISPs;
Second, most existing methods can calculate the traffic matrix of hundreds of hosts, but a small data center may have thousands of servers; in the end, existing methods are usually based on some ISP traffic patterns, but deployed in data center applications. Programs (such as MapReduce jobs) have dramatically changed the traffic pattern.
In addition, there is a tighter coupling of network usage, computing, and storage resources for applications in cloud computing.
Currently, there is not much work in measuring and analyzing traffic in data centers. Literature [4] reports on the characteristics of data center traffic and the design used to guide the network infrastructure.
5 software framework
Cloud computing provides a platform for large-scale data-intensive applications. Often these applications leverage MapReduce frameworks (such as Hadoop's scalable and fault-tolerant data processing). Studies have shown that the performance and resource consumption of MapReduce jobs is highly dependent on the type of application. For example, the Hadoop task sort is I/O intensive, while grep requires a lot of CPU resources.
In addition, the VMs allocated at each Hadoop node may be heterogeneous. For example, one VM's available bandwidth depends on other VMs configured on the same server.
Therefore, the performance and cost of MapReduce applications can be optimized by carefully selecting its configuration parameter values ​​and designing more efficient scheduling algorithms. By mitigating bottleneck resources, you can significantly increase the execution time of your application. Key challenges include Hadoop performance modeling (both online and offline) and adaptive scheduling under dynamic conditions.
Another related approach is to make the MapReduce framework energy-efficient [5]. The basic idea of ​​this approach is to put the Hadoop node that is working and waiting for a new task into a sleep state. This requires Hadoop and HDFS to be aware of energy savings. In addition, trade-offs between performance and power-saving perception are often made. According to the goal, finding an ideal trade-off point is still a research topic without exploration.
6 Storage technology and data management
The software framework MapReduce and its different implementations (Hadoop and Dryad) are data-intensive tasks for distributed processing. These frameworks typically run on Internet file systems (such as GFS and HDFS). The storage structure, access mode, and application programming interface of these file systems are different from traditional distributed file systems. In particular, they did not implement the standard POSIX interface, thus introducing compatibility issues with traditional file systems and applications. The current solutions mainly include support for the MapReduce framework to use the cluster file system (such as IBM's GPFS) method and support for scalable and concurrent data access based on the new API primitives.
7 Conclusion
Demand-driven, technological advancement and business model transformation have jointly promoted the rapid development of cloud computing, and its core is to build a new information and data storage, processing and service model. This paper summarizes the key technologies and difficulties of this emerging computing model from the perspectives of cloud computing platform construction and management, application construction, etc., and puts forward the problems that need to be solved in the future research and application of cloud computing.
In this range,including Rotary Switch,Door Switch , Push Button Switch, 303 Cord-Line Switch and so on.
Rotary Switch is mostly used in the cooler area,according to different requirement,many function can be met.For example,4 Position,6 Position,3 Position etc.
High Quality and Reseasonal Price,it is very popular.
Push Switch,Toggle Switches,Led Push Switch,Push Button Switch
Ningbo Kara Electronic Co.,Ltd. , https://www.kara-switch.com