Datacenter efficiency and its effect on Humans
CEO & Founder of Server Density.
Published on the 31st October, 2016.
Did you know?
About 2 percent of world energy expenditure goes into datacenters. That’s according to Anne Curie, co-founder of Microscaling Systems who spoke at the most recent HumanOps event here in London.
That 2 percent is on par with the aviation industry who, as Curie points out, gets plenty of slack very publicly about being a serious polluter—even if the aviation industry is incredibly more efficient than the datacenter industry average.
Curie starts her talk with some good news. To a large extend, all the tech progress achieved over the last 20 years went into improving the lives of developers and ops people alike. The cloud takes away the pain of deploying new machines, while higher level languages like Ruby and Python make development exponentially quicker and painless.
We optimize for speed of deployment and we optimize for developer productivity. We use an awful lot of Moore’s Law gains in order to do that.
Enter datacenter efficiency
But there is a caveat to all that progress. Suddenly all of that motivation you had for using your servers more efficiently is gone because somebody else is maintaining those servers for you. You don’t have to worry about where they are, you don’t have to lug them, you don’t even have to order them or find space for them.
Anne Curie offers some fascinating insights on what all this progress means for humans, their systems, and the environment overall.
Want to find out more? Watch Anne Curie’s talk. And if you want the full transcript (it’s a keeper), go ahead and use the download link right below this post.
What is HumanOps again?
HumanOps is a collection of principles that advance our focus away from systems, and towards humans. It starts from a basic conviction, namely that technology affects the wellbeing of humans just as humans affect the reliable operation of technology.
Alert Costs is one such feature. Built right into Server Density, Alert Costs measures the impact of alerts in actual human hours. Armed with this knowledge, a sysadmin can then look for ways to reduce interruptions, mitigate alert fatigue, and improve everyone’s on-call shift.