Dell PowerSwitch S5224F-ON 25GbE Switch

The Dell PowerSwitch S5224F-ON is a 1RU, 24-port 25GbE SFP28 switch with four 100GbE QSFP28 uplinks, a 1.08 Tbps switching fabric (2.16 Tbps full duplex) and 881 nanosecond port-to-port latency.

Dell positions it for low-density 10/25GbE server and storage aggregation - the rack that does not need 48 access ports but does need the same fabric features, the same operating system and the same 100GbE uplinks as the rest of the family.

Where a 24-port 25GbE leaf belongs

Half a rack of servers does not need a 48-port leaf, and buying one anyway means paying for ports that will never be lit. The S5224F-ON is the answer to that: 24 access ports at 25GbE - 600 Gbps of access bandwidth - against 400 Gbps of uplink across four 100GbE QSFP28 ports, which is a 1.5:1 oversubscription ratio. That is a better ratio than most 48-port leaves achieve, and it makes the S5224F-ON a good fit for storage racks and smaller compute pods where east-west traffic is heavy relative to port count.

It is also a natural VLT pair member: two units give 48 active 25GbE server ports across two rack units with no spanning-tree blocked links, which is the same usable port count as a single 48-port leaf but with switch-level redundancy.

Feature-wise nothing is missing. The S5224F-ON runs the same SmartFabric OS10 image, the same VXLAN and BGP EVPN capability and the same 32 MB buffer as the 48-port and 96-port models. The differences are 8GB of CPU memory instead of 16GB, and a 1.08 Tbps fabric sized to the port count.

Why 25GbE displaced 10GbE for server access

A 25GbE SFP28 port and a 10GbE SFP+ port are the same physical cage, the same single electrical lane and the same one-cable-per-server structured cabling. The difference is the lane rate. Moving a rack from 10GbE to 25GbE access multiplies usable access bandwidth by 2.5x without adding a single port, a single fibre run or a single rack unit - which is why 25GbE became the default server-access speed rather than a step up to 40GbE, where the same bandwidth costs you four lanes and a fatter cable.

The same logic applies to the uplinks. A 100GbE QSFP28 uplink is four 25GbE lanes in one cage, so leaf-to-spine capacity scales on exactly the same serdes generation as the access ports. That single-generation consistency is the reason the S5200-ON family remains a sensible buy on the secondary market: the optics, the DACs and the breakout cables are all mainstream 25G-lane parts rather than an orphaned speed.

Breakout: 24 access ports become up to 40

Each 100GbE QSFP28 port is four 25GbE lanes in one cage, so a breakout cable converts one uplink port into four 25GbE or four 10GbE ports. Spend all four uplinks on breakout and the S5224F-ON tops out at 40 ports of 25GbE (24 native SFP28 plus 16 from breakout) or the same count at 10GbE.

The uplinks are multi-rate in the other direction too: four native 40GbE ports, or eight 50GbE ports via breakout. A common pattern is two uplinks left at 100GbE for the spine pair and two broken out to eight extra access ports.

Airflow direction, and why it is not a preference

Dell builds every S5200-ON in two airflow directions and names them by where the air goes. I/O Panel to PSU airflow draws cool air in at the port face and exhausts it at the power-supply and fan face - the standard build. PSU to I/O Panel airflow is the reverse, drawing in at the power-supply face and exhausting out of the port face.

Which one is correct is decided by which way the switch faces in the rack. In a hot-aisle/ cold-aisle row, servers pull cool air from the cold aisle and exhaust into the hot aisle. A switch racked with its port face toward the cold aisle needs standard airflow. A switch racked with its port face toward the hot aisle - a very common choice, because it puts the switch ports on the same side as the server NICs and halves the cable runs - needs reverse airflow, or it will inhale its own row's exhaust.

Power supplies and fan modules are direction-specific parts on this model, so the direction is set when the chassis is built rather than changed in the rack. Confirm the direction you need when you request a quote.

Mixing directions inside one row is the most common cause of a "this switch runs hot" complaint that has nothing to do with the switch. Tell us which direction your row needs and we will confirm the build before anything ships.

Fabric features you get regardless of port count

Every S5200-ON shares the same feature set, so the choice between models is a question of port density rather than capability. All of them carry a 32 MB packet buffer and support Virtual Link Trunking and Routed VLT for multi-chassis active-active pairs without a spanning-tree blocked link. All of them do VXLAN gateway bridging and routing at line rate, and under SmartFabric OS10 they add BGP EVPN with Integrated Routing and Bridging in both asymmetric and symmetric modes, which is what lets you build a controller-less network virtualization overlay.

For converged storage traffic the family implements the full Data Center Bridging set: priority flow control (802.1Qbb), enhanced transmission selection (802.1Qaz), DCBx and iSCSI TLV, plus Routable RoCE so RDMA traffic can cross a leaf-spine boundary. OS10 also supports Precision Time Protocol (IEEE 1588v2) in hardware. Layer 3 is a full stack - OSPF, BGP, policy-based routing, IPv4 and IPv6 - not a licence-gated subset.

SmartFabric OS10, SONiC and what a licence actually means on the used market

The S5200-ON is an ONIE switch, and that is the single most important thing to understand before buying one second-hand. Dell decouples the hardware from the network operating system: the spec sheet's own ordering table lists every model in both a Dell SmartFabric OS10 build and a NO-OS build, on identical hardware. The Open Network Install Environment on the switch will install SmartFabric OS10, Enterprise SONiC Distribution by Dell Technologies, or a third-party network operating system, and the chassis does not care which one you choose.

What you are buying from us is the hardware. A Dell OS10 entitlement is a licence bound to the unit's service tag and to a Dell account, and it does not automatically travel with a switch on the secondary market. A refurbished unit may well arrive with OS10 already installed and fully functional, and it may not carry an active entitlement or a Dell support contract. We do not promise a transferred Dell licence, a software subscription or a support contract with a refurbished switch, and you should be suspicious of any reseller who does.

The practical approach is to plan the NOS as a separate line item: budget an OS10 or Enterprise SONiC subscription from Dell if you need vendor support and TAC escalation, or run community SONiC or another ONIE-compatible NOS if you are comfortable owning the software stack yourself. Tell us what you intend to run and we will tell you what state a specific unit is in before it ships.

Common questions

Is a 24-port leaf worth it over a 48-port one?

If you will not light 48 ports, yes. The uplink ratio is better - 1.5:1 here against 3:1 on a 48-port leaf with four 100GbE uplinks - and a VLT pair of two S5224F-ON units gives 48 active server ports with switch-level redundancy rather than a single point of failure.

What does it give up against the larger models?

CPU memory (8GB rather than 16GB), onboard storage (32GB rather than 64GB) and fabric capacity sized to the port count. The feature set, the operating system and the 32 MB buffer are identical.

Can I get more than 24 access ports out of it?

Yes - up to 40 at 25GbE or 10GbE, by breaking out all four 100GbE QSFP28 uplinks into four lanes each.

Choosing within the S5200-ON family

All five models share the same operating system, the same 32 MB buffer and the same Layer 2 and Layer 3 feature set. You are choosing density and uplink ratio, nothing else.

Stepping up a generation, the Dell PowerSwitch S5448F-ON moves the same design language to 100GbE access and 400GbE uplinks.

Condition, testing and what ships in the box

This is a refurbished, professionally reconditioned unit. Every switch is powered up, inspected and functionally tested before it leaves us, and it ships with warranty coverage. Power supplies, fan modules, rail kits, console cables and optics are configurable above - choose the airflow direction that matches the chassis, because power supplies and fans are direction-specific parts.

If you need a specific firmware or NOS state, a specific optics loadout, or matched pairs for a VLT domain, tell us before you order and we will build to it.

Specifications