News for hackers. Stuff that matters.
Re:Intel Confronts Potential ‘PR Nightmare’ With Reported Ch... by Waterluvian on Wednesday January 03, 2018 @09:56AM (#16061434)
Hm. Do cloud providers need to provide up to 30% more capacity for the same price, or do customers need to purchase up to 30% more capacity to get the same speed?
Re:Intel Confronts Potential ‘PR Nightmare’ With Reported Ch... by rocqua on Wednesday January 03, 2018 @10:03AM (#16061479)
Unless demand is fully inelastic, if you up the price fewer people will buy. As such, this should hit the cloud provider profits.
Re:Intel Confronts Potential ‘PR Nightmare’ With Reported Ch... by maratd on Wednesday January 03, 2018 @10:10AM (#16061550)
> Unless demand is fully inelastic

It's mostly inelastic. People don't buy resources unless they need to do work. Alternatives, such as on-prem hardware, are affected as well.

The only work that would be affected would be the work that becomes unprofitable at a 10-30% hardware cost increase and this is probably marginal enough to be ignored.

Re:Intel Confronts Potential ‘PR Nightmare’ With Reported Ch... by scottlamb on Thursday January 04, 2018 @03:07PM (#16073608)
> It's mostly inelastic. People don't buy resources unless they need to do work.

I work on a system (at Google) with significant hardware cost. Fundamentally, the work my system is doing needs to be done. But the time we spend improving efficiency is hugely elastic. I look at a CPU profile or request flow, have an idea to improve it, look at how much machine resources we're spending, guesstimate how long it will take us to implement and maintain, and use a chart to see if my idea is worth my team's time or not.[1]

If the resources get more expensive or simply impossible to acquire,[2] we'll optimize more.

[1] There are other considerations (will it make the code more complex, thus increasing risk of a security/privacy flaw? what about opportunity cost given that it's hard to hire more engineers and scale a team?) but that's a reasonable mental model.

[2] There's a global RAM and SSD manufacturing crunch already, and if lots of CPUs are replaced due to these vulnerabilities or simply are no longer enough, that's gonna be a big crunch as well. If you're one of the few biggest cloud providers, I think you can't just replace / add tons more hardware than planned without dramatically increasing the price per unit for everyone.

Re:Intel Confronts Potential ‘PR Nightmare’ With Reported Ch... by maratd on Thursday January 04, 2018 @05:00PM (#16074469)
> But the time we spend improving efficiency is hugely elastic.

In the context of the above posts, "elastic" is an economic term used to refer to the demand curve. There is no supply/demand curve when it comes to internal technical decisions for optimization =)

I would say your work is highly correlated to the price of hardware per some unit of performance AND the amount of work that you need to complete AND the amount of hardware already available AND the cost of labor needed for optimization.

I imagine in your case, since these systems are tightly controlled, you can probably run unpatched without taking a substantial risk.

Re:Intel Confronts Potential ‘PR Nightmare’ With Reported Ch... by rocqua on Wednesday January 03, 2018 @01:33PM (#16063628)
I'd say most of the elasticity comes from people deciding not to migrate to the cloud at all. Rather than people deciding to stop using the cloud.
Re:Intel Confronts Potential ‘PR Nightmare’ With Reported Ch... by glebm on Wednesday January 03, 2018 @10:22AM (#16061673)
*fully elastic
Re:Intel Confronts Potential ‘PR Nightmare’ With Reported Ch... by rocqua on Wednesday January 03, 2018 @01:30PM (#16063600)
No, if demand is slightly elastic, an increase in price will still cause a decrease in demand.

https://en.wikipedia.org/wiki/Price_elasticity_of_demand

Re:Intel Confronts Potential ‘PR Nightmare’ With Reported Ch... by BoorishBears on Wednesday January 03, 2018 @10:01AM (#16061470)
This bug doesn’t magically chop all CPU performance down by almost a third.
Re:Intel Confronts Potential ‘PR Nightmare’ With Reported Ch... by cjbprime on Wednesday January 03, 2018 @10:07AM (#16061520)
What does it do, then? That is approximately what the mitigation patch does, according to early averages of perf changes.
Re:Intel Confronts Potential ‘PR Nightmare’ With Reported Ch... by Choco31415 on Wednesday January 03, 2018 @10:17AM (#16061614)
Performance is chopped 5-30%, with newer CPU's with PCID being affected less significantly. [0] BoorishBears is possibly pointing out that 30% is a worst case.

[0]: https://www.phoronix.com/scan.php?page=article&item=linux-41...

Re:Intel Confronts Potential ‘PR Nightmare’ With Reported Ch... by BoorishBears on Wednesday January 03, 2018 @10:53AM (#16061971)
This combined with what the other comment mentions, it's a range from 5%-30% with 30% being a worst case the average user does not encounter.

This is an issue, but laypeople are overblowing the effect on their everyday computing.

Re:Intel Confronts Potential ‘PR Nightmare’ With Reported Ch... by BuckRogers on Friday January 05, 2018 @07:50PM (#16083090)
What about gaming performance? Once everything is patched[0], that is. I know no one knows, but it'll be interesting to see Intel's last remaining advantage (clock frequency) mitigated somewhat by all of this.

[0]https://gist.github.com/woachk/2f86755260f2fee1baf71c90cd653...

Re:Intel Confronts Potential ‘PR Nightmare’ With Reported Ch... by colanderman on Wednesday January 03, 2018 @10:24AM (#16061695)
Syscall-heavy workloads are affected to a much greater degree than CPU-heavy workloads. (This is a direct consequence of the fact that the workaround involves a per-syscall overhead.)
Re:Intel Confronts Potential ‘PR Nightmare’ With Reported Ch... by Waterluvian on Wednesday January 03, 2018 @10:25AM (#16061705)
Yes. Which is why I'm saying "up to 30%"