SOA-C03 · Question #91
A company plans to migrate several of its high performance computing (HPC) virtual machines (VMs) to Amazon EC2 instances on AWS. A CloudOps engineer must identify a placement group for this…
The correct answer is A. Deploy the instances in a cluster placement group in one Availability Zone. Cluster placement groups place EC2 instances close together within a single Availability Zone, providing very low network latency and high network throughput, which is ideal for HPC workloads that require fast, high-bandwidth communication between nodes. Partition and spread…
Question
A company plans to migrate several of its high performance computing (HPC) virtual machines (VMs) to Amazon EC2 instances on AWS. A CloudOps engineer must identify a placement group for this deployment. The strategy must minimize network latency and must maximize network throughput between the HPC VMs. Which strategy should the CloudOps engineer choose to meet these requirements?
Options
- ADeploy the instances in a cluster placement group in one Availability Zone.
- BDeploy the instances in a partition placement group in two Availability Zones.
- CDeploy the instances in a partition placement group in one Availability Zone.
- DDeploy the instances in a spread placement group in two Availability Zones.
How the community answered
(35 responses)- A83% (29)
- B9% (3)
- C6% (2)
- D3% (1)
Explanation
Cluster placement groups place EC2 instances close together within a single Availability Zone, providing very low network latency and high network throughput, which is ideal for HPC workloads that require fast, high-bandwidth communication between nodes. Partition and spread groups focus on isolation and failure-domain separation, not on maximizing inter-instance network performance.
Topics
Community Discussion
No community discussion yet for this question.