[rvz]

I don't think Netflix is even designed to handle very extreme multi-region live-streaming at scale as evidenced in this event with hundreds of millions simultaneously watching.

YouTube, Twitch, Amazon Prime, Hulu, etc have all demonstrated to stream simultaneously to hundreds of millions live without any issues. This was Netflix's chance to do this and they have largely failed at this.

There are no excuses or juniors to blame this time. Quite the inexperience from the 'senior' engineers at Netflix not being able to handle the scale of live-streaming which they may lose contracts for this given the downtime across the world over this high impact event.

Very embarrassing for a multi-billion dollar publicly traded company.

[gonzo41]

They must have try to do this on the cheap, thinking they could dynamically scale on the fly for this. Big mistake.

[anakaine]

This is a total supposition without any proof.

[colesantiago]

What more proof do you need other than the fact that streams went down worldwide on a highly anticipated event from a public company?

I wouldn't be surprised if lots of engineers at Netflix are currently now writing up a length post mortem of this.

And this is from the company that created the discipline of chaos engineering for resilience.

It is clear they under invested and took the eye of the ball with this.

This is bad, like very very bad.

[jhugo]

The assumption that it was related to insufficient investment isn’t supported by any evidence. Flawed technical decisions can be made by the most expensive engineers too.

[colesantiago]

The evidence is that the stream went down.

We will see why it went down and to what extent they underinvested in their post mortem.

[jhugo]

That’s not evidence for the assertion you made.

[fragmede]

Their CDN is colo and doesn't run on AWS.