DEA-C01 Question #98: Real Exam Question with Answer & Explanation

Question

A manufacturing company has many IoT devices in facilities around the world. The company uses Amazon Kinesis Data Streams to collect data from the devices. The data includes device ID, capture date, measurement type, measurement value, and facility ID. The company uses facility ID as the partition key. The company's operations team recently observed many WriteThroughputExceeded exceptions. The operations team found that some shards were heavily used but other shards were generally idle. How should the company resolve the issues that the operations team observed?

Options

• AChange the partition key from facility ID to a randomly generated key.
• BIncrease the number of shards.
• CArchive the data on the producer's side.
• DChange the partition key from facility ID to capture date.

Explanation

{"question_number": 8, "question_summary": "Resolving hot shards (WriteThroughputExceeded) in Kinesis Data Streams caused by skewed facility ID partition key", "correct_answer": "A", "explanation": "The root cause of WriteThroughputExceeded with idle shards alongside hot shards is partition key skew - large facilities generate far more records than small ones, funneling disproportionate write traffic to specific shards. Switching to a randomly generated partition key distributes records uniformly across all shards, eliminating hotspots. Option B (increasing shards) increases total throughput capacity but does not fix skew - the same shards will still be hot and others idle. Option C (archiving on the producer side) reduces data volume but does not address the distribution imbalance. Option D (changing to capture date) may still produce skew if write volume peaks at the same time across all facilities.", "generated_by": "claude-sonnet", "llm_judge_score": 4}

No community discussion yet for this question.