Comments on: Amazon blames human error for Xmas Eve outage; Netflix vows better resiliency

By: Dlf

Dlf — Sat, 23 Feb 2013 04:22:34 +0000

Nearly two months later and still having issues? Something else up?

By: JustMe

JustMe — Thu, 03 Jan 2013 12:09:15 +0000

big deal, yawn…

By: vtrravikumar

vtrravikumar — Thu, 03 Jan 2013 04:30:27 +0000

The fact that cloud services may be affected due to human errors is something very scary.

By: Michelle Accardi

Michelle Accardi — Wed, 02 Jan 2013 23:17:16 +0000

They need a strong IT management software partner to help them avoid these t all costs. As these services grow the risk for error where things aren’t automated increases. Application Performance management, infrastructure management, security and automation solutions can help and need to be working in the back end to help these companies from passin gon challenges to their end users.

By: David Saintloth

David Saintloth — Wed, 02 Jan 2013 19:34:55 +0000

The fact remains and as admitted by Netflix itself that if their system were more robust to cross AV issues this would not have impacted their customer base. The reasons for it not being robust given this high profile outage is that a) distributing video streaming is hard and b) distributing it across multiple AV’s is expensive. They are currently still working on the a), the fact that human error happens is why AWS doesn’t give 5 nine’s of service…but having multiple AV’s isolates clients that distribute across more than two AV’s from outages that impact their customer base significantly….video streaming which is inherently real time is *always* going to impact some customers even if Netflix were on all of AWS’s AV’s simply because an interrupted stream has to be picked up again and latency is seen in real time…you just can’t help that but you can prevent it from being a several hours outage to just being a few seconds of a hiccup as the client fails over to other available if not near by AV’s. Netflix is admitting they need to build a more robust design to those possibilities.

By: Carlos Soares

Carlos Soares — Wed, 02 Jan 2013 19:08:01 +0000

AWS still not ready for prime time?

By: Jhmunz

Jhmunz — Wed, 02 Jan 2013 18:44:04 +0000

I would suggest looking at the SLAs and related Service Credits.
If Netflix are happy with the recompense following Xmas eve, happy days. If not, I would suggest looking at their Procurement Team and process.
Whatever, human error, where one human is being ‘blamed’ is unacceptable and unprofessional.

By: Christopher Haire

Christopher Haire — Wed, 02 Jan 2013 17:47:46 +0000

IMO, if I were Netflix, I would consider privatizing some of the AWS components they use. Load balancers are one of them… Netflix probably has a good handle on the traffic they serve at this point. It’s probably way cheaper in the long-run to build their own datacenter and run most of the traffic internally, scaling out to elastic services for peak or non-planned-for usage.

By: Dave G

Dave G — Wed, 02 Jan 2013 14:50:31 +0000

KISS principle – rather than building a bigger, more clever mousetrap, focus on your core competences and just do what you do best.

By: Cloud Master

Cloud Master — Wed, 02 Jan 2013 11:05:58 +0000

But what’s the point of more regional availability if you have no uptime to even access it?