[talk] Holidaze, AWS, and astounding "clock drift outage"
spork at bway.net
Wed Jan 3 03:41:47 EST 2018
> On Jan 3, 2018, at 3:09 AM, Isaac (.ike) Levy <ike at blackskyresearch.net> wrote:
> Hi All,
> After weeks of nonsense (and boring long stories),
> On Mon, Dec 18, 2017, at 3:39 PM, Isaac (.ike) Levy wrote:
>> Hi All,
>> A bit OT from the pit of internet hell, but perhaps of interest to folks
>> here: This weekend AWS has been doling out a disruption of service of
>> the worst kind, clock skew insanity. And when I say insanity, I mean
>> true madness.
> Updates, perhaps of interest in several categories,
> Through continued holiday NTP/hardware adventure, we were told we were casualties of a Xen exploit to be publicly announced Thursday:
> As of today, Intel appears to be prepping to get in the mix, with issues apparently *quite* related,
> Thursday my Ops teammates and I will certainly be popping popcorn to watch this show.
<non security hot take>
Security concerns aside, if there really is a 30%-ish performance hit for “some virtualization workloads”, and we assume AWS is basically all Intel, and that that 30% is now just datacenter-warming rather than computing, and 30% more capacity will be added, consuming 30% more power, is this like a whole “add a Denmark to the power grid” event?
Like a security flaw is going to hasten global warming?
</non-security hot take>
> When we all knew how stupid this technical approach was years ago, why has the cloud taken the shape it has?
> I'm looking forward to the day the current favella of what we currently call "the cloud" has burned to the ground. And, I hope not completely burned- so we can look upon it's ashes for centuries and know how *not* to build things.
> talk mailing list
> talk at lists.nycbug.org
More information about the talk