Question 930
A team has corrected this HPE compute solution issue: A design promises millisecond response time from distant archival storage without measuring its round-trip latency. Which continuing practice would best prevent the same problem?
Explanation
Correct Answer
Use end-to-end I/O latency rather than only device capacity in storage selection. This recurring assurance measure is tied to the diagnosed risk: Storage location and access tier have not been matched to service-level requirements. For the active incident, the corrective action remains: Select appropriate supported near-compute storage and test the full I/O path.
Incorrect Answers
Storage location and access tier have not been matched to service-level requirements. Using the proposed safeguard would guard against a separate risk: Physical capacity planning ignores retained copies and growth overhead. Use end-to-end I/O latency rather than only device capacity in storage selection.
Security classification and retention requirements differ across storage resources. The selected safeguard helps with that exposure, but it leaves the recurrence risk here unaddressed. Storage location and access tier have not been matched to service-level requirements. Use end-to-end I/O latency rather than only device capacity in storage selection.
Storage location and access tier have not been matched to service-level requirements. The proposed safeguard is intended for another failure mechanism: The workload may be bottlenecked before the accelerator rather than constrained by GPU capacity. Use end-to-end I/O latency rather than only device capacity in storage selection.