Exadata: Delivering High Performance with Sustainable Efficiency

The Oracle Exadata Database Machine (Exadata) is an engineered system that seamlessly integrates hardware and software with advanced database-aware algorithms to optimize Oracle Databases for all workloads. Since its introduction, Exadata has consistently increased its hardware capacity across all architectural facets, now scaling to thousands of cores, terabytes of memory, and petabytes of storage. This growth allows customers to efficiently run large-scale databases or consolidate multiple workloads into a single Exadata system. The latest iteration, Exadata X10M, further enhances these capabilities, featuring 192 CPU cores, up to 3TB of memory per database server, and up to 4.2 PB of raw capacity per rack. 

While Exadata's abundant resources enable efficient database operations, it also addresses concerns about the environmental impact of such powerful machines. In this post, we'll examine how Exadata helps increase data center energy efficiency while maintaining top-tier performance across all workloads.

Server Virtualization and Workload Consolidation

One effective strategy for minimizing energy consumption in data centers is to reduce the number of servers and storage systems. Exadata is built to handle OLTP and DW/Analytics workloads with maximum performance, leveraging optimizations in both Oracle Database and Exadata System Software. These include Exadata RDMA Memory, Smart Scan (Storage Offload), Storage Indexes, and Columnar Cache on Storage Servers, among others. Combining these software optimizations with robust hardware, Exadata provides an ideal platform for consolidating Oracle Databases that run various workloads, utilizing resource management features such as IO Resource Manager and Virtualization.

Exadata uniquely consolidates infrastructure, databases, and multiple workloads into one system and database engine. This consolidation reduces the number of servers and storage systems, significantly saving energy and reducing CO2 emissions.

Beyond consolidation, Exadata efficiently virtualizes its servers to isolate different workloads. Exadata X10M can virtualize a physical server into multiple virtual servers, reducing the number of physical servers and their environmental impact.

In summary, Exadata delivers faster performance and higher capacity than other platforms, enabling higher levels of database consolidation. This consolidation replaces numerous servers and storage systems, enhancing energy efficiency in data centers.

CPU Frequency Management

The AMD 4th Generation EPYC processors in Exadata X10M operate at a base frequency of 2.6GHz, scaling up to 3.7GHz. These processors adjust clock speeds in real-time based on database workload changes, conserving energy and reducing heat generation when not under heavy load. This dynamic adjustment allows Exadata X10M to complete tasks efficiently with optimal power consumption.

Oracle Autonomous Databases running on Exadata Public Cloud and Exadata Cloud@Customer use auto-scaling features, automatically adjusting the number of cores needed for a given workload. This results in a more energy-efficient infrastructure and cost savings for customers. 

Dynamic Cooling

Exadata servers dynamically adjust cooling based on the workload. Exadata's co-engineering extends to critical hardware components such as processors and NVMe flash devices, which perform better at lower temperatures. The servers modulate fan speed based on workload demands, ensuring sufficient cooling for maximum performance while reducing cooling needs during lighter workloads, thereby optimizing energy efficiency and lowering costs.

Capacity-on-Demand (CoD)

Exadata's Capacity-on-Demand (CoD) feature allows customers to deactivate some CPU cores initially, controlling database license usage and enabling more cores as workloads increase. This not only optimizes resource utilization but also saves energy by reducing active cores when full capacity isn't required.

Environmental Impact of Exadata X10M Compared to X9M-2

Each Exadata generation enhances performance and energy efficiency. The Exadata X10M Database Server boasts 3x more cores and 1.5x more memory than the X9M-2, with 22% more storage capacity, enabling significantly higher OLTP transactions and analytic queries. This allows customers to do more with fewer systems, reducing energy consumption. The graphic below illustrates the environmental impact of the Exadata X10M compared to the X9M-2, normalized for CPU cores and memory.

Exadata X10M, with 2 Database and 3 Storage servers, consumes 27% less energy than the equivalent Exadata X9M-2 configuration while achieving higher performance metrics.

Exadata is a powerful database machine designed with both performance and sustainability in mind. The Exadata X10M reduces energy consumption, space requirements, and cooling needs compared to previous generations, helping customers minimize their environmental impact while maintaining high-performance workloads. By consolidating the number of database servers and storage systems, Exadata enhances data center efficiency, maximizes Oracle Database performance, and supports a more sustainable future through reduced energy consumption and improved efficiency.

For more information on Exadata and how it can benefit your organization, visit Oracle Exadata.