Hacker News new | comments | show | ask | jobs | submit login

Do you have something better to point to? It's easy to complain about stuff, but at least he's out there trying to do something. Presumably it can be improved.

I'm particularly fond of the quote "lead, follow, or get the hell out of the way", which is a bit harsh in this case because a lot of your advice is good. It could be framed in a more constructive way, though - there's some Comic Book Guy tone there in your comment.


My intended tone was not "don't try", but "try harder".

I've listed at least 5 ways to improve/normalize the testing, as well as linking to a document that does a pretty good job of explaining statistics (particularly, how programmers do a bad job of statistics; baselines for benchmarks; etc).

"At least he's out there trying" -- with this not-so-great benchmarking, the author has just effectively SHITTED on 2/3 companies that have gone to great lengths to build amazing infrastructure AND managed to spread his FUD around the web, to the point where it reached the HN front page -- and you want credit for trying?

Get the hell out of the way.

It's true: you don't say something like "Well, Amazon just sucks." without backing the statement up with something more credible. As someone a little less savvy on the topic I'm glad to know that the test wasn't even close to the final word and why. Thank you.

It's probably also true that your tone is more abrasive than it needs to be.

Part of the problem is a benchmark like this, put together with plain ignorance, and published on the web will give people who don't know any better all kinds of false perceptions.

Well, if these benchmarks are misguided and useless, it is useful to recognize it as such so you don't go out and trade all your EC2 instances for Linodes.

"At least we're doing something!" is a silly defense.

They probably have some faults, but the general conclusions smell right to me: I don't think they're in the "really screwed up and wildly misleading" category, but in the "ok, interesting, could use some work though" category.

There is nothing you should be more wary of than a benchmark that matches your pre-existing intuition. It'll lead you to ignore serious methodological issues, without any sound scientific (or any other epistemological) reason. https://speakerdeck.com/alex/benchmarking is a slide deck I gave at my office on how to do better benchmarking

EDIT: I should probably mention I work at Rackspace, and thus everything I say on this subject should be taken with appropriate grains of sand :)

Well AWS is slow is not surprise, there was an article on HN in last couple of weeks that pitted Azure against AWS and AWS was faster hands down. So this is no surprise at least to me.

This statement is exactly the problem he is describing. :) One metric for a specific use case or scenario is a terrible indicator of overall "quality". It is much more nuanced than that. I think the worst tickets I've gotten in the 10 years sofar sysadmining is when a customer just states their app is "slow".

There are other studies that have compared the offerings on multiple benchmarks as well. Here's the one I was referring to: https://zapier.com/engineering/quick-redis-benchmark-aws-vs-... see the comparison for yourself on multiple benchmarks.

Yes in simplistic terms for a specific metric I'm sure other providers have better hardware than AWS, if that is all one wants to base their value of "better" on then so be it, but that is pretty naive.

Many argue that the AWS ecosystem (25 services at last count) and the extensive featureset of AWS outweigh the bare bones "fast" metrics of other providers.

I think like the poster above is mentioning...there is generally more to it than a simple metric or two sampled a few times from a single endpoint. But I guess it all lies on ones definition of what they consider valuable...

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