mediumMultiple Choice
350-401 Practice Question: An enterprise is deploying a virtual router…
An enterprise is deploying a virtual router (vRouter) as part of its NFV infrastructure. The engineer needs to ensure that the vRouter can handle a sudden spike in traffic without dropping packets. The vRouter is running on a KVM hypervisor. What should the engineer configure to guarantee CPU resources for the vRouter during peak demand?
⚠ Common exam trap
Cisco often tests the distinction between resource optimization (DPDK, NUMA) and resource guarantee (pinning, reservation), leading candidates to pick DPDK because it is associated with high performance, even though it does not guarantee CPU availability under contention.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Configure CPU pinning and CPU reservation for the vRouter VM.
CPU pinning binds the vRouter's virtual CPUs to specific physical cores, preventing other processes from using them, while CPU reservation guarantees a minimum amount of CPU capacity. Together, they ensure deterministic CPU availability during traffic spikes, preventing packet drops due to resource contention on the KVM hypervisor.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Enable memory ballooning on the vRouter VM.
Why it's wrong here
Memory ballooning reclaims RAM from the guest under host pressure; it does not reserve CPU cycles, so a traffic spike can still starve the vRouter of processor time. It is tempting because ballooning is a genuine KVM memory-overcommitment control, and would be the right choice when the host needs to reclaim guest memory rather than guarantee compute.
- ✓
Configure CPU pinning and CPU reservation for the vRouter VM.
Why this is correct
CPU pinning binds the vRouter's vCPUs to dedicated physical cores, and CPU reservation guarantees those cycles are not reclaimed by other VMs. Together they prevent the hypervisor scheduler from starving the vRouter during traffic spikes, avoiding packet drops.
- ✗
Enable DPDK on the vRouter's virtual NICs.
Why it's wrong here
DPDK bypasses the kernel network stack for faster packet processing, raising throughput but consuming CPU rather than reserving it; under contention the vRouter can still be descheduled and drop packets. It is tempting because DPDK is standard for NFV performance, yet guaranteeing CPU during spikes requires a KVM CPU reservation or dedicated vCPUs.
- ✗
Set the vRouter VM to use NUMA node pinning.
Why it's wrong here
NUMA node pinning binds the VM's memory and vCPUs to one socket to reduce cross-node latency; it does not reserve a guaranteed CPU share, so a spike can still be starved by other guests. It is tempting because pinning improves locality, but guaranteeing CPU during peak demand requires a KVM CPU reservation or dedicated vCPU allocation.
Go deeper
Related to this question
About these practice questions
One of 1,923 original 350-401 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This 350-401 practice question is part of Courseiva's free Cisco certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the 350-401 exam.