Question

Difficulty: MediumHigh-Performing and Elastic Compute Solutions

A logistics company is building a high-throughput route optimization engine on Amazon EC2. The workload requires a fleet of compute-optimized instances to communicate with each other over a low-latency network using Message Passing Interface (MPI). The instances also run a management daemon on port 9090 which needs to be monitored by an Application Load Balancer (ALB) target group. Which two actions should the solutions architect take to meet these performance and monitoring requirements?

  1. Launch the EC2 instances in a cluster placement group.Answer
  2. Configure the ALB target group health checks to specifically query port 9090.Answer
  3. C
    Launch the EC2 instances in a spread placement group.
  4. D
    Launch the EC2 instances in a partition placement group.
  5. E
    Configure the ALB target group health checks to use the default traffic port while setting the daemon port to 9090.

Answer

Launch the EC2 instances in a cluster placement group and configure the ALB target group health checks to specifically query port 9090.
The correct configuration requires launching the instances in a cluster placement group to minimize network latency for the MPI workload, and configuring the target group health checks to target the custom port where the daemon is listening to prevent false unhealthy states.

Step-by-Step Solution

1
Determine the networking placement requirement for tightly coupled MPI compute nodes.
Identify that a cluster placement group is required to achieve the necessary low-latency and high-throughput node-to-node network performance.
MPI workloads require tight synchronization and minimal latency, which cluster placement groups provide by locating instances close together on the underlying hardware.
2
Determine the health monitoring configuration for the management daemon.
Identify that the health check must be explicitly configured to monitor port 9090.
By default, health checks use the traffic port or default port 80. If the daemon runs on custom port 9090, health checks to other ports will fail, marking the instances as unhealthy.

Key Concept

Low-latency EC2 placement groups and custom port target group health checking
Rate this question