IBM "Blue Cloud" cloud computing Platform Application Example

IBM's Blue Cloud computing platform is a software and hardware platform that extends the technology used on the Internet to enterprise platforms, enabling data centers to use a computing environment similar to that of the Internet. The blue Cloud uses IBM's advanced large-scale computing technology, combines IBM's own software and hardware systems and service technologies to support open standards and open source software. The blue Cloud is based on the IBM Almaden Research Center's cloud infrastructure, with Xen and POWERVM virtualization software, Linux operating system images, and Hadoop software (Google File system and MapReduce open source implementations). IBM has officially launched a "Blue Cloud" product based on the x86 chip server system.

The Blue Cloud computing platform consists of a data center, IBM Tivoli Deployment Management software (Tivoli Provisioning Manager), Ibmtivoli monitoring software (IBM Tivoli monitoring), IBM WebSphere Application Server, IBM DB2 database, and some open source information processing software and open source virtualization software together. The "Blue Cloud" hardware platform environment is similar to the General x86 server cluster, using blades to increase the computational density. The features of the blue cloud software platform are mainly embodied in the virtual machine and the use of Apache Hadoop for large-scale data processing software. Hadoop is the open-source version of Google File system software and MapReduce programming specification.

Virtualization technology in the "Blue Cloud" computing platform: An important feature of the "Blue Cloud" software is the use of virtualization technology. There are two levels of virtualization in the blue Cloud, one for virtualization at the hardware level, and the other for virtualization through open source software. Hardware-level virtualization can use IBM P-series servers to obtain hardware-logical partition LPARs (logic partition). The CPU resources for logical partitions can be managed through IBM Enterprise workload Manager. This approach, coupled with resource allocation strategies in the actual use process, enables the appropriate allocation of resources to each logical partition. The logical partitioning of P series systems is 1/10 central processing units (CPUs). Xen is virtualization at the software level and can run another operating system on a Linux basis.

Virtual machine is a kind of special software that can simulate the execution of hardware completely, run the complete operating system without modification, and keep a set of operating environment semantics. The way through the virtual machine. The following benefits are available on the cloud computing platform:

(1) The management platform of cloud computing can dynamically locate the computing platform on the required physical nodes without stopping the application running on the virtual machine platform, and the process migration method is more flexible.

(2) reducing the energy consumption of the cluster, merging the compute nodes of the virtual machine with not heavy load into the same physical node, so that the idle physical nodes can be shut down to achieve the purpose of saving the electric energy;

(3) Through dynamic migration of virtual machines on different physical nodes, the whole virtual running environment is migrated, and the load balancing performance is not independent.

(4) More flexible deployment, that is, the virtual machine can be directly deployed to the physical computing platform, and the virtual machine itself includes the corresponding operating system and the corresponding application software, a large number of virtual machine images copied directly to the corresponding physical nodes.

Storage architecture in the "Blue Cloud" computing platform: the storage architecture in the "Blue Cloud" computing platform is also important for cloud computing, with data from the operating system, the service program, and the user's application stored in the storage system. The Blue Cloud storage architecture contains clustered file systems similar to Google File system and storage Area network sans based on block devices.

When designing a storage architecture for a cloud computing platform, it is not just about storage capacity issues that need to be considered. In fact, with the continuous expansion of hard disk capacity and the falling price of hard disk. You can get a lot of disk capacity by combining multiple disks. Compared to the capacity of the disk, the reading and writing speed of disk data is a more important problem in the storage of cloud computing platform, so multiple disks need to be read and write simultaneously. This approach requires that data be allocated to multiple disks of multiple nodes. To achieve this, storage technology has two choices, one is to use a clustered file system similar to Google file systems. Another is a block-device based storage Area Network San System.

On the Blue Cloud computing platform, San Systems and Distributed file systems (such as Google File system) are not competing systems, and Sans provide a block device interface. File systems need to be built on this basis to be used by upper-level applications. And Google file system is just a distributed filesystem that can be built on a SAN. Both provide reliability and scalability, and how to use it also needs to be determined by applications built on the cloud computing platform, which also reflects the interaction between the computing platform and the upper application.