Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

How Tier 2 cloud vendors banded together to cope with Spectre and Meltdown

techcrunch.com

Post reply on HN
Print view View original

51–60 of 71 posts

Re: How Tier 2 cloud vendors banded together to cope with Spectre and Meltdown

#51

Post by runeks »

jordanthoms wrote: post #48

All this seems like a pretty compelling reason to move to using VMs and type safety to provide process isolation instead of using the hardware, e.g. https://www.destroyallsoftware.com/talks/the-birth-and-death... or Microsoft's Singularity and Midori projects. It's a shame there's so much inertia behind the current setup of hardware memory management etc that it seems it'll be a long time before anything actually hap…

How would this approach have helped in this case?

As I understand it, the flaw in question allows reading kernel memory by executing user space code. How can a layer of software, on top of this type of buggy hardware, fix this issue?

In one sense, the issue has already been fixed by a layer of software on top — which restricts a bunch of stuff, and reduces performance — but I assume this isn’t what you’re looking for.

Re: How Tier 2 cloud vendors banded together to cope with Spectre and Meltdown

#52

Post by Meai »

peterwwillis wrote: post #50

Note that Google released information a week early, giving attackers a leg up in attacking these cloud providers, as opposed to Google giving the cloud providers the information immediately, which would have helped them defend themselves. But, surprise: Google is their competitor. Google is basically the new Microsoft, except Microsoft could actually design working products when it was evil.

What's with these random jabs at companies, you are just trying to create a culture of irrational dislike. I don't even care if you attack Google but everytime you do so, you have to cite exactly why you are doing it. Not some nebulous "oh they cant even make a single working product" which is objectively false and just provocation.

Re: How Tier 2 cloud vendors banded together to cope with Spectre and Meltdown

#53

Post by cm2187 »

mschuster91 wrote: post #4
brianwawok wrote: post #3

Earlier quoted context omitted.

Why? Intel made billions last year. They will make billions this year. They will make billions next year.

> Why? Because the fallout will cost billions over the next years. Intel as a company due to class-action lawsuits, recalls, rebates, and the shareholders because the drop in stock value after the announcement will cost them quite a chunk of money. In addition, more long-term, I sincerely hope that the cloud vendors (and maybe even Apple!) recognize that their total dependence on Intel (and NVIDIA in deep learning...…

Until Intel fixes their architecture, wouldn't all the major cloud providers switch new purchases to AMD for the time being?

Re: How Tier 2 cloud vendors banded together to cope with Spectre and Meltdown

#54

Post by mschuster91 »

gaadd33 wrote: post #45
mschuster91 wrote: post #4

Earlier quoted context omitted.

> Why? Because the fallout will cost billions over the next years. Intel as a company due to class-action lawsuits, recalls, rebates, and the shareholders because the drop in stock value after the announcement will cost them quite a chunk of money. In addition, more long-term, I sincerely hope that the cloud vendors (and maybe even Apple!) recognize that their total dependence on Intel (and NVIDIA in deep learning...…

You do know that INTC is up compared to 1 month ago? If it didn't drop that much on the initial announcement, why would it plummet in the coming months?

Because there is no quantifiable impact yet. Right now all that's known is "mh, it's bad, but the OS vendors are patching it"... now give the situation a couple weeks to brew, wait for more data on the CPU impact of these patches and the inevitable lawsuits. Plus, Intel might want to think about delaying the next CPU releases (or introduce a new stepping of existing CPUs) to fix the bugs in hardware... all stuff that ain't cheap.

Re: How Tier 2 cloud vendors banded together to cope with Spectre and Meltdown

#57

Post by TrueSelfDao »

discoursism wrote: post #10
logronoide wrote: post #2

The more I know about how Intel has managed the information, the less I trust them. What a disaster. CEO and all the Press and Communication team of Intel should be fired

It's not clear to me what the best approach is here. The wider the circle of those who know, the more likely it is that there will eventually be a leak. Three can keep a secret if two are dead and all that.

If I'm not mistaken, this was the same approach taken when dealing with heartbleed.

Re: How Tier 2 cloud vendors banded together to cope with Spectre and Meltdown

#58

Post by mikmak »

Moter8 wrote: post #55

FYI, the submitter is someone from Scaleway, so he perhaps would also answer some questions on what infos they had or something.

everything we have at Scaleway is on our blog http://blog.online.net things are calming down now, we known what are the fixes for the known bugs and their limitations We can probably expect more OS patches in the coming weeks to improve performances and potentially fix new variants of these bugs that could come in the future

Re: How Tier 2 cloud vendors banded together to cope with Spectre and Meltdown

#59

Post by mikmak »

walterbell wrote: post #36
alanpost wrote: post #6

Prgmr.com has been participating on the Slack channel this article mentions. Being able to share notes gleaned from reaching out to vendors and sort through the information and mitigations for Spectre and Meltdown has been a huge help.

Do you think the communication channel will persist beyond the current vulnerability? E.g. give it a name, allow other cloud providers to join?

actually this kind of channel existed before (with OVH at first for the last few months, to fight some big abusers/phishings together) I guess it will depends on everyone's good will, but most of us will probably stay connected, it does not cost much to keep a slack tab opened (well a few Gb of memory haha, thanks Slack) ;)

Re: How Tier 2 cloud vendors banded together to cope with Spectre and Meltdown

#60

Post by chinathrow »

discoursism wrote: post #10
logronoide wrote: post #2

The more I know about how Intel has managed the information, the less I trust them. What a disaster. CEO and all the Press and Communication team of Intel should be fired

It's not clear to me what the best approach is here. The wider the circle of those who know, the more likely it is that there will eventually be a leak. Three can keep a secret if two are dead and all that.

There was a leak.

Typing this from Ubuntu - still no updated kernels yet.

Post reply on HN