OFL-03 · Hardware Offload and Virtualization

Four ways to give a VM a network, and the numbers for each.

Compare passthrough, SR-IOV, virtio and accelerated vSwitches on one workload, then choose with evidence.

Advanced≈ 30 h 10 units4 labs

passthroughiommuvirtiovppdpdkgpunvmevirtualization

You build: a side-by-side comparison report with the chosen option justified.

Promise

Choose between passthrough, SR-IOV, virtio, and accelerated vSwitches for a workload, and measure the difference.

Prerequisites

basic virtualization; OFL-04 recommended.

Units

1. Hardware foundations ch 01–02

PCIe, SR-IOV, server I/O topology.

2. Platforms and kernel ch 03–04

comparing hypervisors, kernel virtualization support.

3. Configuration ch 05–06

passthrough and SR-IOV set-up.

4. Virtual networks and acceleration ch 07–11

virtual networking, virtio, DPDK, VPP, smart NICs.

5. Other devices ch 12–13

GPU and NVMe passthrough.

6. NFV and containers ch 14–15

7. Monitoring and performance ch 16–18

tools, latency, throughput.

8. Quality, security, HA ch 19–21

QoS, IOMMU isolation, fault tolerance.

9. Cloud, edge, AI, finance, 5G ch 22–26

10. Operations ch 27–30

large deployments, faults, benchmarking, future.

Labs

Each lab names its environment and a pass check. Labs are not marked complete on "it ran" — the pass check has to hold.

Lab	What you do	Environment
OFL-03ach 05	Verify the IOMMU and assign a devicePass check: Device appears in the guest	hardware60 min
OFL-03bch 08	virtio versus VF throughputPass check: Both numbers and the gap explained	hardware90 min
OFL-03cch 10	VPP forwarding in a VMPass check: Forwarding counters match	hardware120 min
OFL-03dch 17	Tune a VM for low latencyPass check: p99 before and after	hardware90 min

Capstone project · CAP-07

Offload Plan with Measured Gains · 3 weeks

Management asks whether a virtual switch should move to a SmartNIC or DPU.

Baseline the host, measure the offload on the same workload, decide, and state the workload where offload loses.

Deliverables: Measurement data, decision record, rollout plan.

Outcomes

I can verify that the IOMMU is on before assigning a device.
I can compare virtio and SR-IOV throughput and explain the gap.
I can tune a VM for low latency.

Also in

Hardware Acceleration Engineer

How it runs

Work through the units in order. Each unit groups the chapters of the study guide with its share of the labs. You can start any time; there is no cohort date and nothing expires.

Labs run in a VM, a container, a simulator or on real hardware, and the card above names which. Where a lab needs hardware — an RDMA NIC, a programmable switch model, an FPGA — there is a simulator fallback so you are never blocked by equipment.

Questions

Do I get a certificate?

You get a completion record for the course. Path badges and project credentials are earned by passing the labs and the project review, not by attendance.

Can my team take this together?

Yes — and if you would rather have it delivered live, with the instructor in the room, this course also exists as a scheduled live cohort. See the live dates.

How long does it take?

≈ 30 h of study including the labs. Most engineers take it part-time over a few weeks.