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

Cosmic rays causing 30k network malfunctions in Japan each year

mainichi.jp

Post reply on HN
Print view View original

91–100 of 120 posts

Re: Cosmic rays causing 30k network malfunctions in Japan each year

#91

Post by sandworm101 »

woodruffw wrote: post #70
notum wrote: post #16

Cosmic rays are, or rather were, the reason why manufactures avoid shipping high end cameras by plane, cosmic rays kill pixels in imaging sensors: https://youtu.be/98FZ8C6HneE?t=479 It's also the reason why all ISS footage has dead pixels on it.

This is a fascinating claim (and video), but I can't find a ton of corroborating evidence for it: searches for "digital camera cosmic rays" bring up (1) considerations for cameras in space ( much higher background radiation levels than a commercial flight), and (2) consumer photography forums where people are discussing that 2011 talk. Some of the latter seem to think that Kodak has/had a vested interest in spreading…

Any ray that might damage a ccd would also impact film stock, exposing sections into bright dots. Did kodak also not ship film by air?

Re: Cosmic rays causing 30k network malfunctions in Japan each year

#92

Post by hnick »

notum wrote: post #16

Cosmic rays are, or rather were, the reason why manufactures avoid shipping high end cameras by plane, cosmic rays kill pixels in imaging sensors: https://youtu.be/98FZ8C6HneE?t=479 It's also the reason why all ISS footage has dead pixels on it.

Does this apply to human retinas too?

Re: Cosmic rays causing 30k network malfunctions in Japan each year

#93

Post by lights0123 »

nightcracker wrote: post #48
raisedbyninjas wrote: post #45

Earlier quoted context omitted.

5950 failures per billion hours is approximately equal to 1 failure every 19 years.

And if you have a datacenter with 200 machines, that's roughly once a month.

Each machine is going to have way more than 1 DRAM chip. A 128GB DDR4 stick is going to have ~20 chips on one side (not sure if they're double sided, just looking at product listing), and you're going to have terabytes of RAM per machine.

Re: Cosmic rays causing 30k network malfunctions in Japan each year

#94

Post by MauranKilom »

andy_ppp wrote: post #35
notum wrote: post #28

Earlier quoted context omitted.

Rays hit our planet regardless of Sun, if anything it might block a few. They are caused by ultra-energetic cosmic events, such as star collisions, black hole feeding cycles. Cosmic rays are just very potent photons, capable of knocking out electrons from an atom (meaning they are ionizing) causing havoc in precision electronics and, well, our DNA.

What is the tolerance for cosmic rays for a human... I ask because on the journey to Mars you’ll get quite a few I guess and also on the planet’s surface after you’re there with such a thin atmosphere?

According to https://xkcd.com/radiation/, you get about 4x the normal daily background radiation from a transamerican flight.

Re: Cosmic rays causing 30k network malfunctions in Japan each year

#95

Post by MauranKilom »

gotostatement wrote: post #76
CameronNemo wrote: post #56

Earlier quoted context omitted.

>In chaos theory, the butterfly effect is the sensitive dependence on initial conditions in which a small change in one state of a deterministic nonlinear system can result in large differences in a later state. https://en.wikipedia.org/wiki/Butterfly_effect

Is there reason to believe the brain is chaotic on that level? The reason I doubt it because any stable biological system has as one of its primary tasks - if not its #1 primary task - to maintain equilibrium. Otherwise it would collapse into chaos due to the inherent imprecision of molecular phenomena. So I would be very surprised if you could stimulate a neuron - not even a neuron, but an electron inside a neuron -…

Well, cosmic rays can cause perceptions: https://en.wikipedia.org/wiki/Cosmic_ray_visual_phenomena

That said, just saying "chaos theory means any change can cause anything" is a terribly weak argument for "cosmic rays cause ideas". Not to mention all the reasons why it's implausible as a significant idea generator.

Re: Cosmic rays causing 30k network malfunctions in Japan each year

#96

Post by sandworm101 »

kevin_nisbet wrote: post #17
shiftpgdn wrote: post #8

Kind of a fun ancedote: In "the old days" when you'd run a server room in your office we had a very large HPC cluster + a significant amount of storage and other one off servers on the top floor of a mid rise office building. I eventually moved it all to a former nuclear fallout facility where our systems were three floors down and under a gigantic pool of water. Error rates and random crashes fell off IMMEDIATELY. I…

Yea, when looking into these myself I did float in conversation that we'd need build a giant pool over our data centers. It was more of a joke though and never went anywhere. Although our error rate was more like 1-2 per week on the equipment I was looking at.

Pools are expensive. The same weight of gravel or sand would produce a similar effect. Put the server farm under a multi-level car park structure.

Re: Cosmic rays causing 30k network malfunctions in Japan each year

#97

Post by sunsipples »

sandworm101 wrote: post #78
shiftpgdn wrote: post #8

Kind of a fun ancedote: In "the old days" when you'd run a server room in your office we had a very large HPC cluster + a significant amount of storage and other one off servers on the top floor of a mid rise office building. I eventually moved it all to a former nuclear fallout facility where our systems were three floors down and under a gigantic pool of water. Error rates and random crashes fell off IMMEDIATELY. I…

Wonderful. Yet another reason for the IT office to be relegated to a sub-basement.

should turn the entire floor into a big toilet

Re: Cosmic rays causing 30k network malfunctions in Japan each year

#98

Post by njarboe »

bostonsre wrote: post #63
andi999 wrote: post #54

Earlier quoted context omitted.

But at least they should reasonably expect to arrive.

Anyone know what expectations Columbus or other expeditions had about survival/risk?

The Magellan Expedition left with 5 ships and ~270 men and returned with 1 ship and 18 men. People knew that going on long, overseas expeditions was very dangerous, but so was life in general in 1500. I imagine worrying about 50% increase in cancer risk by taking a voyage to fricking Mars, would seem very silly to those explorers.

Re: Cosmic rays causing 30k network malfunctions in Japan each year

#99

Post by hinkley »

shiftpgdn wrote: post #8

Kind of a fun ancedote: In "the old days" when you'd run a server room in your office we had a very large HPC cluster + a significant amount of storage and other one off servers on the top floor of a mid rise office building. I eventually moved it all to a former nuclear fallout facility where our systems were three floors down and under a gigantic pool of water. Error rates and random crashes fell off IMMEDIATELY. I…

I've had a couple outages just from people jiggling networking cables, back when nobody cared about locking them down.

I wonder how much of that was cosmic rays and how much was just less foot traffic resulting in fewer errors.

Re: Cosmic rays causing 30k network malfunctions in Japan each year

#100

Post by shiftpgdn »

sandworm101 wrote: post #96
kevin_nisbet wrote: post #17

Earlier quoted context omitted.

Yea, when looking into these myself I did float in conversation that we'd need build a giant pool over our data centers. It was more of a joke though and never went anywhere. Although our error rate was more like 1-2 per week on the equipment I was looking at.

Pools are expensive. The same weight of gravel or sand would produce a similar effect. Put the server farm under a multi-level car park structure.

Water is one of the most effective radiation shields we have for cosmic rays. NASA has contemplated using a water shield for Mars astronauts. There is a reason most fallout shelters are built under a pool when possible.
Post reply on HN