Storage · SNS Rack Series

NetBytes SNS Rack Series — 2U to 8U, 8 to 60 bays

Enterprise rack storage for backup, archive, virtualisation, file services and big data. SNS Storage OS on ZFS, with block and file services, snapshots and replication.

• 2U to 8U — 8 to 60 bays
• ZFS integrity — Checksums, self-healing
• Block and file — iSCSI, NFS, SMB
• Snapshots — And replication
• NVMe cache — U.3 options

About the SNS Rack Series

From an 8-bay entry system to petabyte scale

The SNS Rack Series is built for scalability, durability and performance, combining proven hardware with SNS Storage OS — an enterprise ZFS platform that exposes iSCSI block targets and NFS or SMB file shares, with snapshots, clones, compression and remote replication built in.

It runs behind backup and archive repositories, virtualisation datastores, file services, HCI nodes and big data clusters — the workloads where the storage is expected to still be there, intact, years after it was specified.

ZFS is the reason for that expectation. End-to-end checksums and copy-on-write mean silent corruption is detected rather than discovered later, which is the failure mode that matters most in an archive.

The platform

What the specification covers

• Chassis — 2U, 3U, 4U, 6U and 8U, from 8 to 60 bays
• Drives — 3.5" and 2.5" SAS or SATA, SAS recommended, up to 28TB per 3.5" bay
• Flash — U.3 NVMe options for high-performance cache and tiers
• Validated with Proxmox VE, VMware ESXi, Hyper-V and XCP-ng
• Services — iSCSI LUNs, NFS and SMB shares, snapshots, clones, compression
• Use cases — backup and archive, virtualisation datastores, file services, HCI, big data

Enterprise features

What SNS Storage OS brings

• ZFS data integrity — End-to-end checksums, self-healing, compression and copy-on-write, protecting data at rest and in motion.
• Snapshots and replication — Point-in-time snapshots with fast clones, and ZFS send and receive for remote replication and DR workflows.
• Block and file services — Thin-provisioned iSCSI LUNs for hypervisors, and NFS or SMB shares with AD and LDAP integration.
• Scalability — Scale up with additional drives and JBOD shelves, or scale out using clustered SDS architectures.
• Resilience — Redundant PSUs, hot-swap bays, multipath I/O and data-centre-grade cooling profiles.
• NVMe acceleration — U.3 NVMe for cache and tier acceleration, to meet demanding I/O profiles.

Example chassis

Two points on the range

Illustrative configurations showing the span. Every system is sized to the workload and capacity you actually need.

• 2U — 12 bay — Media: 3.5"/2.5" SAS or SATA, up to 28TB per 3.5" bay. Notes: ZFS snapshots and replication, iSCSI/NFS/SMB, dual redundant PSUs
• 8U — 60 bay — Media: 3.5"/2.5" SAS or SATA, petabyte class. Notes: Scale up via additional shelves, high-efficiency cooling and power, hypervisor validated

How performance is tuned

Capacity is the easy half

Raw capacity is arithmetic. Sustained throughput under a real workload is a design problem, and it is where a storage platform is either specified well or is not.

ZFS ARC and L2ARC caching, a SLOG device for synchronous writes, balanced SAS expanders and a network fabric sized to match all contribute — and getting one of them wrong caps everything behind it.

• ARC and L2ARC caching tuned to the working set
• SLOG for synchronous writes, where the workload demands them
• Balanced SAS expanders, so bay count does not become a bottleneck
• 25, 40 and 100G network options matched to the throughput target

• per 3.5" bay
• raw in a 60-bay chassis
• checksums and self-healing
• up with shelves, out with nodes

SNS Rack Series — FAQ

What buyers ask before sizing

• What workloads suit the Rack Series? — Answer: Virtualisation on VMware, Proxmox, Hyper-V or XCP-ng; database servers; backup and archive repositories; file services; HCI nodes; and big data clusters.
• How much capacity can I achieve? — Answer: Up to 28TB per 3.5" bay. With 60 bays that is up to 1.68PB raw in a single chassis before RAID or erasure coding, and multiple chassis can be clustered for further scale.
• How is performance optimised? — Answer: ZFS ARC and L2ARC caching, SLOG for synchronous writes, balanced SAS expanders, and tuned 25, 40 or 100G networking.
• Can I start small and grow? — Answer: Yes. Start with 8 to 12 bays and add drives, attach JBOD shelves, or expand to additional nodes as requirements grow.
• Is it suitable for compliance archiving? — Answer: Yes. Snapshots, replication, encryption and WORM or immutability — via an object layer or software policy — can meet stringent retention requirements.

Size it first

Work the numbers before you specify

The calculators run the same arithmetic our engineers do, so you can arrive with a starting configuration rather than a blank page.

• RAID capacity planner — Usable capacity, redundancy overhead and rebuild exposure across RAID levels.
• NVR storage & retention — Camera count, codec, bitrate and retention days to the storage you actually need.
• All sizing tools — Six calculators running the same arithmetic our engineers do.

Related range

The rest of the storage range

Quieter, faster, or non-stop.

• SNS tower storage — Quiet 4 and 8 bay storage for branch, edge and SMB sites.
• SNS flash storage — 2U all-flash for databases, VDI and latency-sensitive primary workloads.
• Dual controller storage — Active-active controllers and unified SAN and NAS, expandable to 208 drives.