Hacker Newsnew | comments | show | ask | jobs | submit login

To be fair to Amazon the author should have spun up 100 instances, benchmarked them, and used the fastest one. This is a best practice for AWS.



To me, that's an infrastructure smell.

-----


How would you ensure that an instance launched on hardware bought 6 months ago is identical to the hardware under an instance launched N years ago and still running? Buy old hardware on eBay to prevent newer hardware introducing variation?

-----


I would start with a provisioning process that isn't completely opaque about such things.

-----


> To be fair to Amazon the author should have spun up 100 instances, benchmarked them, and used the fastest one. This is a best practice for AWS.

Why choose the fastest one? This would be the least accurate way to give an indication if the performance of AWS instances. A mean, or perhaps median depending on the skew, would be a better choice.

Unless you're saying that the benchmarks on the other servers are effectively cherry picked best results.

-----




Guidelines | FAQ | Support | API | Security | Lists | Bookmarklet | DMCA | Apply to YC | Contact

Search: