KumoScale software (developed by KIOXIA – formerly Toshiba Memory) is a cloud-focused storage solution that delivers high-performance NVMe flash storage volumes via a virtual storage layer between clients and flash devices.
The software implements a fast, networked block storage service based on the NVMe over Fabrics (NVMe-oF) standard.
Focused on speed and scale, KumoScale delivers the flexibility of a shared, clustered storage pool at the similar performance of DAS (Direct Attached Storage) NVMe SSD.
The software is designed to make NVMe flash more efficient, more cost-effective, and easier to deploy at scale.
How KumoScale benefits your business
Key Features
- Born in the cloud – Integrated with Kubernetes, Ansible, Graphite and other cloud-native infrastructure software.
- Any platform – Runs on standard x86-based (including AMD-based) storage platforms.
- Any network – Supports RDMA for highest network performance and TCP/IP for broadest network compatibility.
- Open – Works with standards-compliant NVMe-oF initiator and NVMe drives.
- Resilient – Cross-domain volume replication for legacy applications; simple volumes for cloud-native applications.
- Analytics-driven provisioning – Based on storage classes, QoS and telemetry data.
ApplicationsKumoScale software is designed for deployment at scale in medium to large scale on-premise clouds:
- Cloud services
- Consumer SaaS services
- Marketplaces, clearinghouses (travel, tickets, stock trades)
- Massively multi-player gaming
Benefits
- Save storage CapEx with better flash capacity utilization.
- Increase revenue agility by rapidly adapting stateful workloads during demand peaks.
- Customize storage performance for each application based on its specific requirements.
- Significantly improves query performance for OLTP and analytics databases.
- Simplify procurement and maintenance by consolidating server SKUs.
- Enable stateful applications to be efficiently load-balanced and elastically scaled.
- Perform the same work with fewer compute nodes by blending workloads and eliminating stranded resources.
- Accelerate decision making through faster ingest and analysis.
