
Oracle today made generally available a database platform on its cloud service that promises to dramatically reduce the cost of processing high-performance transactions and analytics.
Kothanda Umamageswaran, senior vice president for Exadata and scale-out technologies for Oracle, said Exadata Exascale is based on a virtualized database that can access a common pool of shared compute and storage.
That approach has enabled Oracle to reduce the total cost of online processing transactions (OLTP) and analytics by as much as 95%, in part because there is no additional cost for IOPS, he added. Oracle claims Exadata Exascale delivers 230 times more throughput than other database cloud servicesโ2,880 GB/s compared to up to 21 GB/s for other hyperscalers. It also delivers 50 times lower latency, with 17 microseconds compared to 1,000 microseconds for other cloud providers, the company claims.
Oracle is able to achieve that level of performance because all data is natively stored in a columnar format that can also be used to access data stored in memory in much the same way traditional block storage is accessed, says Umamageswaran.
That capability is then spread across pooled storage servers using an AI Smart Scan capability Oracle has developed to help ensure the most critical data any application needs is made available in memory. IT teams need only specify the number of processors and storage capacity required, with data automatically moved between memory, Flash storage and disk drives as access requirements change.
The overall goal is to make these capabilities available to a wide range of organizations, rather than just larger enterprises that historically have been the only organizations with the financial resources needed to run high-performance applications, noted Umamageswaran.
In addition, Oracle has included an AI Vector Search capability to make it simpler to correlate queries across images and structured data stored in a relational database format. Exadata Exascale runs key vector search operations up to 30 times faster to enable organizations to process thousands of concurrent AI vector searches.
IT teams can also instantly create full copies or thin clones using the Exascale intelligent storage cloud and its redirect-on-write technology. Advanced snapshot capabilities also make creating space-efficient clones of pluggable or container databases that can be used either to build and test applications or to make sure redundant databases are available in the event of, for example, a cybersecurity incident, said Umamageswaran.
Exadata Exascale is now available with the Exadata Database Service on Exascale Infrastructure and Oracle Database 23ai on Oracle Cloud Infrastructure (OCI). It will be available in Exadata Cloud@Customer, OCI Dedicated Region, and multicloud environments in the future.
Ultimately, the goal is to bring as much compute power to where data is already located, said Umamageswaran. Itโs not clear today how much of an organizationโs data resides in the cloud. Each organization will need to decide for itself to what degree they want to either store new data or move existing data in the cloud. However, moving data is, as every IT service management team (ITSM) knows, a major challenge that needs to be carefully considered.