Chung Sheng Li
Thomas J. Watson Research Center, IBM
Software Defined Environment
Abstract:
Two phenomena are happening simultaneously during the past few years: Enterprises are increasingly aggressive in moving mission critical and performance sensitive applications to the cloud. In addition, many new mobile, social and analytics applications are directly developed and operated on the cloud. These two phenomenon drove the shift of the value proposition of cloud computing from cost reduction to simultaneous agility and optimization. These requirements (agility and optimization) drove the recent disruptive trend on software defined computing where the entire computing infrastructure – compute, storage and network – are becoming software defined and dynamically programmable.
Software defined environment originated from the compute environment where the computing resources are virtualized and managed as virtual machines or containers (including bare metal containers). Software defined network (SDN) moves the network control plane away from the switch to the software running on server for improved programmability, efficiency and extensibility. Software define storage, similar to software defined network, separates the control plane from the data plane of a storage and dynamically leverages heterogeneity of storage to respond to changing workload demands. Software defined environment brings together software defined compute, network and storage and unifies the control planes from each individual software defined component. Unified control planes allow rich resource abstractions to enable assembling purpose fit systems and/or providing programmable infrastructures to enable dynamic optimization in response to business requirements. The key elements within software defined environment include capability based resource abstraction, policy based workload abstraction, and outcome based continuous mapping of the workload to the resources. The logical abstraction of the software defined infrastructure (that includes compute, storage, and network) for the available resources in compute, storage and network across one or more data centers. The available resources can be potentially extended by using hybrid cloud (or cloud broker) technologies to include multiple private and public clouds. This logical model of software defined infrastructure includes pools of computing and storage resources interconnected by networking resources. This abstraction of the data center enables the equivalent of Instruction Set Architecture (ISA) at the data center or multi- data center levels.
In this talk, we will discuss the key ingredients of this disruptive trend on software defined computing, and illustrate the potential benefit in the context of mobile, analytics, and managed service environment.