Composable Infrastructure – Optimized Resource Usage

//Composable Infrastructure – Optimized Resource Usage
Composable Infrastructure – Optimized Resource Usage2018-10-26T03:30:16-07:00

Disaggregation and Composition: Keys to Cost Savings

Disk-lite servers and JBODs/JBOFs cost less than the same servers with internal disks. Composable Infrastructure increases purchasing options by allowing the purchase of compute and storage resources from different vendors.

DriveScale allows the ability to purchase drives directly from the manufacturer instead of paying a marked-up price from a server vendor. In many cases, low cost 3.5” disk drives can be used instead of expensive 2.5” drives because the limitation on the number of drives that can fit in a server box is removed.

The concern that the compute-to-storage ratio is fixed for a given cluster can push administrators to over-provision processors. This could be a reasonable strategy if more and more workloads are added to a cluster as it matures, but it often results in clusters where the processors are running at low utilization levels.

DriveScale allows the deployment of compute and storage as needed by each workload, without over-provisioning and with the ability to easily add resources later, if necessary.

Upgrading the diskless servers without replacing the storage presents huge savings in money, time and effort. Compute intensive applications benefit from more frequent upgrades as new high-performance processor technologies become available. Upgrading storage can be postponed until the storage is nearing end of life, or as newer and higher capacity storage becomes available.

Implementing DriveScale enables the ability to scale and upgrade compute and storage independently, resulting in significant cost savings.

Add more processors and spread the existing drives across them if more computer power is needed. If more storage is needed, add more drives and attach them to exiting nodes.

DriveScale makes it easy to expand only the constrained resource without paying for unnecessary resources.

In traditional scale-out architectures, once a cluster starts out with a particular storage-to-compute configuration, all additions to that cluster must conform to the same configuration. If there are 8 drives per node in half the cluster and 12 drives per node in the other half, the distribution of the workload among the servers would become chaotic and unpredictable. The only way to address an incorrect and wasteful configuration is to swap out the entire cluster.

DriveScale enables easy reconfiguration of the entire cluster–at any time–in response to changing requirements.

Multiple application clusters are traditionally silo’ed in separate racks, with underutilized resources locked in those silos.

DriveScale enables quick and easy adjustments, allowing IT to shift resources between clusters so that every workload operates at maximum efficiency. Silos are a thing of the past.

Diskless servers and JBODs/JBOFs take up about half the rack space of equivalent servers with internal drives. Without the drives blocking the airflow, compute servers can be more tightly configured with up to 8 servers in a 2u box. Since drives require little cooling, upwards of 100 3.5” drives can be accommodated in a 4u JBOD.

Reduced rack and floor space saves on cooling and power.

In traditional scale-out architectures, decommissioning a cluster provides no assurance that a new cluster could use the configuration of the decommissioned nodes.

DriveScale allows decommissioned clusters to return their hardware components to common pools of compute and storage resources that can easily be re-composed into completely new configurations as needed.

Since a DriveScale user can build many types of server nodes from one compute SKU and one JBOD/JBOF SKU, the number of SKUs required to build out the various clusters in a data center can be drastically reduced, while still optimizing resources for each workload.

DriveScale makes ordering, sparing, managing and inventory tasks easier and can lower spare inventory levels.