tezvyn:

Diagnosing high I/O wait on a database volume

Source: interviewintermediate

WHAT IT TESTS: storage performance diagnosis. OUTLINE: check IOPS and throughput against the volume limit, look for burst-credit exhaustion, then move to provisioned IOPS or a larger volume.

WHAT IT TESTS: whether you can diagnose I/O bottlenecks methodically before throwing hardware at them. ANSWER OUTLINE: measure actual IOPS, throughput, and queue depth and compare against the volume's provisioned limits, check whether burst credits on a general-purpose SSD are exhausted, and verify the instance's own network or EBS bandwidth cap. Then switch to provisioned-IOPS volumes, grow the volume to raise the baseline, or add caching. RED FLAG: scaling CPU or memory while the real limit is the disk, or ignoring burst-credit depletion.

Read the original → interview

Get five bites like this every day.

Tezvyn delivers a daily feed of 60-second tech bites with quizzes to lock in what you learn.

Diagnosing high I/O wait on a database volume · Tezvyn