Examkin

Question

Difficulty: HardHigh-Performing and Elastic Compute Solutions

A bioinformatics research institute is deploying a distributed genomic sequence alignment pipeline on Amazon EC2 instances. The analysis nodes must communicate with each other using a specialized Message Passing Interface (MPI) implementation, requiring sub-millisecond, low-latency node-to-node network performance. Client requests are distributed across these instances using a Network Load Balancer (NLB) that routes incoming traffic to a custom processing engine listening on TCP port 99999999. A lightweight status daemon is running on TCP port 8080 on each instance to monitor the node's system-level health. Which combination of actions should a solutions architect take to meet these requirements? (Choose TWO.)

  1. Deploy the EC2 instances in a cluster placement group within a single Availability Zone.Answer
  2. Configure the NLB target group to route traffic to TCP port 99999999 and explicitly set the health check port to TCP port 8080.Answer
  3. C
    Deploy the EC2 instances in a spread placement group across multiple Availability Zones.
  4. D
    Configure the NLB target group to route traffic to TCP port 99999999 and use the default traffic-port setting for health checks.
  5. E
    Deploy the EC2 instances in a partition placement group distributed across multiple partitions.

Answer

Deploy the EC2 instances in a cluster placement group within a single Availability Zone, and configure the NLB target group to route traffic to TCP port 99999999 and set the health check port to TCP port 8080.
To achieve sub-millisecond, low-latency node-to-node network performance for MPI-based communications, instances must be placed as close together as possible, which is achieved by deploying them in a cluster placement group within a single Availability Zone. Additionally, because the client traffic is routed to the custom processing engine on TCP port 99999999 but system-level health is monitored by a separate status daemon on TCP port 8080, the Network Load Balancer target group must route traffic to port 99999999 while explicitly querying port 8080 for health checks. This prevents the load balancer from sending health check requests to the custom engine port, which would otherwise result in nodes being marked as unhealthy.

Step-by-Step Solution

1
Analyze the network latency requirement for MPI-based node-to-node communication.
Determine that a cluster placement group in a single Availability Zone is required to achieve the lowest possible latency and highest network throughput.
Cluster placement groups place instances physically close together on the same underlying hardware network, which is ideal for tightly coupled node-to-node communication.
2
Analyze the ports used by the application and the health monitoring agent.
Identify that incoming client traffic uses TCP port 99999999, while system health status is exposed on TCP port 8080.
The target group must route traffic to port 99999999, but target group health checks must target port 8080 where the status daemon is listening.
3
Configure the Network Load Balancer target group settings.
Set the target group port to 99999999 and override the health check port to explicitly use 8080.
Leaving the health check port at the default 'traffic-port' would cause the NLB to probe port 99999999, which would fail because the status daemon is not listening there, resulting in all targets being marked unhealthy.

Key Concept

High-performing compute architectures require low-latency placement groups combined with correctly aligned load balancer health check configurations.
Estimated Time:2m 30s
Rate this question

Topics

High-Performing and Elastic Compute Solutions

More questions from this topic