The main objective of IOStack is to create a Software-Defined Storage (SDS) toolkit for Big Data on top of the OpenStack platform. IOStack enables efficient execution of virtualized analytics applications over virtualized storage resources thanks to flexible, automated, and low cost data management models based on SDS.
The IOStack toolkit is a software stack for analytics infrastructures that achieves the following objectives:
1) Advanced storage management and virtualization: With IOStack, administrators can orchestrate and provision storage pools via high-level policies. This includes both object (OpenStack Swift) and block storage (OpenStack Cinder). The integrated management model of IOStack allows administrators to manage large storage infrastructures investing less time and resources.
2) Extensible SDS services for analytics: The main novelty of IOStack is that it enables administrators to dynamically deploy “data services” and associate them to provisioned storage pools. Such data services are user-defined pieces of logic that intercept storage requests and perform some computation on them. This flexible model enables to develop a variety of storage optimizations, which can also improve efficiency and performance of both storage services and analytics.
3) Policy-driven deployment of analytics services: At the compute side, IOStack offers a fast and simplified virtualization model for analytics frameworks based on Docker containers. IOStack enables administrators to tailor the deployment of applications with user-friendly deployment policies. Moreover, the virtualization layer of IOStack implements advanced scheduling and resource management algorithms to optimize the execution of multi-tenant analytics.
For more information, please visit http://iostack.eu.