FlashGrid
for Oracle RAC on AWS

Engineered Cloud System designed for database high availability

Infrastructure-as-Code deployment with a few mouse clicks

24/7 support for entire infrastructure stack

Recommended by AWS for running Oracle RAC

Extreme performance configurations

FlashGrid enables extreme performance for Oracle RAC on AWS by using one or more of the following technologies:

Aggregating multiple storage nodes through 100 Gb/s network

Local SSD with persistency through data mirroring

FlashGrid Read-Local™ Technology

Bare-metal instances (up to 224 cores and 24 TB of memory) eliminate any impact of virtualization on performance.

2-node or 3-node clusters

Applications that require very high storage read performance will benefit from using local SSDs with 16 GB/s throughput per node and 2M IOPS per node. FlashGrid Read-Local Technology eliminates storage read overhead and makes the full throughput available to your database.

i3en.metal instances have 60 TB of local SSD capacity. Additional EBS capacity can be added for larger databases.

FlashGrid Storage Fabric provides mechanisms for ensuring persistence of the data placed on the local SSDs by maintaining a mirrored copy on EBS and by automatically reconstructing data in case of a loss of an EC2 instance with local SSDs.

Oracle RAC on AWS diagram: 2-node or 3-node clusters

Extra-large databases

Databases with sizes of 100’s TB can be placed on multiple storage nodes connected via the 100 Gb/s network. Each storage node provides 10 GB/s of throughput. Each database node has up to 7 GB/s of storage throughput. For example, a cluster with 6 RAC nodes and 5 storage nodes will have aggregate storage throughput of 42 GB/s.

Storage management is done through ASM disk groups. Normal or High Redundancy disk groups provide data mirroring and protection against storage node failures.