Skip to content
GridM BNG · Line-rate data plane

Commodity NICs. Carrier throughput.

A kernel-bypass forwarding plane turns standard x86 servers with merchant NICs into carrier capacity: tens of gigabits per rack unit, terabits per POP with ECMP scale-out, and no proprietary silicon anywhere in the path.

OLT / GPONFTTH accessDSLAM / SwitchDSL + ethernetWireless / RFWISP accessSUBSCRIBERSPPPoE · IPoE · QinQbng-node-01bng-node-02bng-node-NGridM BNG clusterN+1 · session sync · ECMP scale-outcommodity x86 · bare metal / VM / K8sRADIUS · BillingAAA + CoA · your stackIP core · InternetBGP · upstreams · peering

Illustration mirrors the shipping GridM BNG console. Identifiers are fictional.

What ships in the box

  • DPDK-class forwarding on commodity Intel and NVIDIA/Mellanox NICs
  • Multi-gigabit to terabit: scale up with cores, scale out with nodes
  • ECMP scale-out across nodes, add capacity node by node
  • Runs on standard x86: your servers, your favorite OEM or white-box
  • No proprietary line cards, optics markup or chassis fabric

Kernel-bypass forwarding

Packets never touch the kernel network stack. Poll-mode drivers on Intel and NVIDIA/Mellanox NICs deliver line-rate forwarding with per-subscriber QoS and CGNAT applied inline.

Scale out, not up

Need more capacity? Add a node and let ECMP spread subscribers across the cluster. A POP grows from 10 Gbps to multiple terabits in server-sized steps, not chassis-sized leaps.

Your hardware, your vendor

Any OEM or white-box x86 with supported NICs. Source servers on your schedule and terms, keep cold spares on the shelf, and let hardware refreshes ride the server market instead of a vendor roadmap.

Reference

Line-rate data plane: the spec card

Performance and HA

Data plane
Kernel-bypass, line rate on commodity NICs
Throughput
Multi-gigabit to terabit via ECMP scale-out
Redundancy
N+1 with session sync, hitless failover
Upgrades
In-service software upgrades, canary per node
FAQ

Line-rate data plane, in detail

Standard x86 servers with supported Intel or NVIDIA/Mellanox NICs, from any OEM or white-box vendor. A single 1U server handles tens of gigabits and tens of thousands of subscribers; clusters scale out with ECMP to hundreds of thousands of sessions and terabit-class forwarding. We publish sizing guidance and validate hardware during onboarding.

Explore the rest of the platform

See line-rate data plane on live traffic

Book a live demo with a network engineer. We will walk your topology, size the hardware and show real sessions terminating on the console, not slides.

Runs on your hardware · One plan, every feature · Migrate in slices