Flexible, Efficient Data Storage Platform
For Any Cloud

From the inventors of NVMe over TCP, Lightbits is software‑defined, disaggregated block storage for private, public, hybrid, and AI clouds.

Extensive Integrations and Supported Orchestration Environments to Build Cloud Data Storage Services.

Benefits of Disaggregated Storage for Cloud-Native Applications

Scale compute and storage independently
Uses existing TCP/IP network, runs on any standard hardware
Single storage cluster can service multiple tenants and heterogeneous application environments
High IOPs, consistent low latency
High storage utilization, both capacity and performance
Storage-based replication and recovery
Intelligent Flash Management and rich data services, better flash endurance, lower TCO

Native VMware Support

Certified with VMware vSphere 7 Update 3
Integrated with VMware vCenter for single Pane-Of-Glass management of the entire storage infrastructure directly from vCenter

High Performance and Consistent Low Latency

Ideal primary tier storage for database and analytics workloads
High IOPS and throughput - 4.7M IOPS, 22GB/s
Low latency - 160μs latency, reduced tail latency
High I/O performance for container-based workloads

Rich Data Services

Thin provisioning
Elastic RAID
Data reduction/ compression
Data replication across multiple nodes
Snapshots and clones for persistent volumes

Container-Optimized

Kubernetes CSI plugin; seamless support for microservices
1:100s; Lightbits cluster to Kubernetes clusters
Storage for containers within the same or adjacent cluster to the application
Multi-tenancy

No Speciality Networks Needed

Works on standard Ethernet networks & NICs
No RDMA configuration required on the network switches

Application Scalability

Better database performance and response time
50% reduction in cost compared to local flash
3x increase in flash utilization
Reduce Opex by 10-15x

Native VMware Support

Certified with VMware vSphere 7 Update 3
Integrated with VMware vCenter for single Pane-Of-Glass management of the entire storage infrastructure directly from vCenter

High Performance and Consistent Low Latency

Ideal primary tier storage for database and analytics workloads
High IOPS and throughput – 4.7M IOPS, 22GB/s
Low latency – 160μs latency, reduced tail latency
High I/O performance for container-based workloads

Rich Data Services

Thin provisioning
Elastic RAID
Data reduction/ compression
Data replication across multiple nodes
Snapshots and clones for persistent volumes

Container-Optimized

Kubernetes CSI plugin; seamless support for microservices
1:100s; Lightbits cluster to Kubernetes clusters
Storage for containers within the same or adjacent cluster to the application

No Speciality Networks Needed

Works on standard Ethernet networks & NICs
No RDMA configuration required on the network switches

Application Scalability

Better database performance and response time
50% reduction in cost compared to local flash
3x increase in flash utilization
Reduce Opex by 10-15x

NVMe/TCP Extends NVMe Across the Entire Data Center with TCP/IP Fabric

NVMe® was designed for high-performance direct-attached PCIe SSDs and was later expanded with NVMe over Fabrics (NVMe-oF™) to support a hyperscale remote pool of SSDs. The industry has widely accepted that this new NVMe-oF model will replace Direct Attached Storage (DAS) and become the default protocol for disaggregated storage in cloud infrastructure. NVMe over TCP (NVMe/TCP) is the most powerful NVMe-oF technology, providing high performance with reduced deployment costs and design complexity. NVMe/TCP extends NVMe across the entire data center using simple and efficient TCP/IP fabric.