Are you ready to build a data infrastructure that will support your organization’s analytics efforts, but find yourself with more questions than answers on where to start? What should this architecture look like? Should we consider cloud or an on-premises data center? Analytics or neural networks?
Attend this session, an all-day course focused on architectural designs and topics including modern infrastructures, GPU, memory, storage, cluster scalability to thousands of nodes and management, Lambda architecture for streaming analytics, and data life cycle management with HDFS tiered storage. Learn about different approaches for multitenant Hadoop cluster deployments with Openstack, Cloudera, and MapR, and workload automation topics concerning the deployment of big data clusters. We will cover the application and infrastructure architecture components for each use case with specific focus on deployments. The session goes into details around end-to-end automation for big data. We will also discuss topics related with best practices around data disaster recovery as well as cybersecurity.
You Will Learn
- A high-level overview of big data fundamentals, big data storage, compute, and data networking architecture
- CPU, GPU, in-memory, and disk architecture
- The design and sizing of the compute, network, and storage component of integrated infrastructure for big data
- Business analytics, edge analytics, streaming analytics, and SQL on Hadoop workflow and process
- Data life cycle management for tiered storage of hot, warm, and cold data
- End-to-end automation for big data
- Hadoop-as-a-service on bare metal
- Disaster recovery
It is recommended that a learner have the following knowledge and skills before attending this course:
- Modern data center technologies
- Modern data center virtualization technologies