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

SSD will fail at 40k power-on hours (2021)

cisco.com

Post reply on HN
Print view View original

91–100 of 276 posts

Re: SSD will fail at 40k power-on hours (2021)

#91

Post by landemva »

dtjb wrote: post #34
alliao wrote: post #17

Earlier quoted context omitted.

planned obsolescence is quite a thing...?

In some cases, but a product must fulfill its core purpose. If a SSD intentionally dumped data and self destructed at a set time, that would be disastrous for the brand. Same way a car doesn't adopt planned obsolescence by blowing up after 200k miles.

You are not a used car afficionado?

'This insulation prematurely disintegrates under normal use causing the wires it is designed to protect and insulate, to short causing many problems.'

http://www.mercedesdefects.com/2008/04/wire-harness-defect.h...

Re: SSD will fail at 40k power-on hours (2021)

#92

Post by wtallis »

robocat wrote: post #48
opencl wrote: post #30

Earlier quoted context omitted.

This will not affect your laptop, all of the models affected by this are enterprise SAS SSDs. Of course your SSD might have some other firmware bug that would eat your data, all you can do is search for the model number and see if the manufacturer has issued any notices/firmware updates.

> This will not affect your laptop That’s just your presumptive opinion, right? Edit: sorry, probably put that offensively. mikiem said about the HN drives: “These were made by SanDisk (SanDisk Optimus Lightning II) and the number of hours is between 39,984 and 40,032...” - https://news.ycombinator.com/item?id=32031428 Without knowing parts of a codebase are shared between SanDisk devices, it is hard to say that ente…

> Without knowing parts of a codebase are shared between SanDisk devices, it is hard to say that enterprise SAS devices have absolutely no code shared with consumer devices.

Even if the code containing this bug was shared between consumer and enterprise drives, it's not reasonable to assume that it would take SanDisk multiple years to check whether their consumer drives are also affected. The lack of a follow-up report from SanDisk is good evidence that their other products are not affected.

Re: SSD will fail at 40k power-on hours (2021)

#94

Post by wtallis »

usr1106 wrote: post #3

Cisco is not a SSD manufacturer. They write industry-wide bug. Does that mean that more than one SSD manufacturer is affected (because they use partially the same firmware)? Further down they mention only Sandisk. Or is the industry-wide just their newspeak for saying any Sandisk of affected model, regardless whether installed in a Cisco box or somewhere else?

Enterprise SSDs are commonly made by one of a handful of dominant companies and then rebranded by server vendors, so that you can see a SanDisk or Samsung SSD sold as a Dell EMC or Cisco or HPE drive.

Re: SSD will fail at 40k power-on hours (2021)

#95

Post by TaylorAlexander »

barry-cotter wrote: post #83
TaylorAlexander wrote: post #76

Earlier quoted context omitted.

If someone thinks inclusive language is a sign of hostility, then I think they have misunderstood the situation. I’m happy to have open source contributions from anyone, but I do share my pronouns in posts and on videos and I can tell you that the very small number of people who have gotten upset by that were angry unhelpful people who were more interested in complaining about language than contributing to the commun…

Quoted post unavailable.

It’s a space that is inclusive of queer folks. If someone can’t handle that, then yeah, they probably aren’t mature enough to safely interact with those people. Every space needs to have some rules in the event that someone gets nasty. Someone who gets upset when they encounter a non-binary person is probably going to make those people feel unwelcome. So you can either protect the vulnerable people or you can allow the bully to push other people out. But whoever is organizing that space can consciously decide, or they can let the bully decide for them.

By the way, you seem to have this really charged, negative view of queer spaces. Which I respectfully want to suggest is a misunderstanding of those spaces. I mean, if you go in all angry and complaining about other people, then sure, they’re gonna (rightfully) kick you out. But that’s true of most places if you show up and act like a jerk. The truth about these places, and being queer in general, is that this is a beautiful space of happiness for so many people. Being able to express gender openly without judgment is a positive, empowering experience for so many people. All you have to do to fit in is accept that. You don’t have to like it, though that is encouraged. But if you get so upset by someone existing as their true self that you have to argue with others, you’re probably not a good fit for that space.

I want to suggest you listen to the YouTube channel Beau of the Fifth Column. He’s got a lot of great takes he explains in a way I think you’d understand. And sometimes he talks about stuff like this.

Anyway I’m non-binary. I’m taking hormones and expressing my gender in ways I never knew I could (wearing clothes I “wasn’t supposed” to wear). It feels great. All I really ask for is that you accept me for who I am. And I hope you see that I’m able to be kind to you even though I know you think I’m a “pronoun person”.

Edit: Here’s a couple videos from Beau of the Fifth column talking about gender. He’s a white guy from the south who explains things in a non judgmental way and I think he has a good perspective, but I’ll let you decide:

https://youtu.be/vQ53lVyi4so

https://youtu.be/FaFK9uqbqrY

Re: SSD will fail at 40k power-on hours (2021)

#97

Post by toast0 »

bayindirh wrote: post #20
twawaaay wrote: post #5

Earlier quoted context omitted.

Very strange understanding of the word "evidence". No sane SSD manufacturer would do such thing on purpose. You do it and you loose business, that's it. The simplest explanation is that somebody made an honest engineering mistake.

When you purchase a server (fleet), you get a long warranty with it. Generally 3 to 5 years. So you expect this fleet to stay in service for Unless you burn through your SSDs, you're very unlikely to hit this event. When these servers' continue to be used and disks all start to fail at the same time, this will obviously stink. The bathtub curve is not like this. You can feel that.

40k hours is a little more than 4.5 years. These drives deterministically fail at that uptime (unless firmware is updated) and most servers are on 24x7, so if you run your servers for 5 years, it's highly likely you'd run into this. If you run your SSDs hard and they fail early as a result, then you'd be spared from this mass death. Or if you use three year leases and replace on a schedule.

Now more than ever, five year old server hardware isn't that far behind the curve unless you're on the bleeding edge. I've been looking for bottom of the barrel hosting lately, and there's lots of dedicated servers available with 10+ year old cpus, and probably most of the rest of the machine is a similar age.

Re: SSD will fail at 40k power-on hours (2021)

#98

Post by Silhouette »

dredmorbius wrote: post #87
kazen44 wrote: post #9

Earlier quoted context omitted.

the chance of two SSD's failing at the same time under normal circumstances is extremely slim. So this might actually be a good cause of this incident.

It seems more likely it was four drives (though dang and Mike both refer to "two" in the earlier thread). Both primary and failover servers had RAID arrays. I suspect RAID 10 (striped mirror), which would mean two drives would have to fail to take down a single server. Four drives of the same manufacturer spec and batch would do that.

This is what always worries me about our home server. It's running ZFS with multiple redundant drives but the supplier refused (when I explicitly asked) to supply it with disks known to be from different batches claiming that the odds of multiple failures close together were negligible. Obviously we have backups as well but the time and cost to restore a full server from online backups can be significant.

Re: SSD will fail at 40k power-on hours (2021)

#99

Post by djmips »

m0llusk wrote: post #35
pmoriarty wrote: post #27

Earlier quoted context omitted.

One thing everyone could and should be doing is backups.

Two things: Test restores or you don't actually have backups. Just saying.

Absolutely! Twice in my career, in huge failures, the backups turned out to be garbage! You don't want this!

Re: SSD will fail at 40k power-on hours (2021)

#100

Post by robocat »

wtallis wrote: post #92
robocat wrote: post #48

Earlier quoted context omitted.

> This will not affect your laptop That’s just your presumptive opinion, right? Edit: sorry, probably put that offensively. mikiem said about the HN drives: “These were made by SanDisk (SanDisk Optimus Lightning II) and the number of hours is between 39,984 and 40,032...” - https://news.ycombinator.com/item?id=32031428 Without knowing parts of a codebase are shared between SanDisk devices, it is hard to say that ente…

> Without knowing parts of a codebase are shared between SanDisk devices, it is hard to say that enterprise SAS devices have absolutely no code shared with consumer devices. Even if the code containing this bug was shared between consumer and enterprise drives, it's not reasonable to assume that it would take SanDisk multiple years to check whether their consumer drives are also affected. The lack of a follow-up repo…

Yeah, I agree it is very unlikely to affect someone’s laptop.

However I dislike a black and white “This will not” absolute fact statement: even if based on reasonable assumptions which is what appears to be the case versus detailed knowledge.

Most laptops don’t run their SSDs 24/7, and unless a manufacturer’s error affects a lot of consumers, we often don’t find out the cause of consumer equipment errors in my experience.

If the OP has a laptop older than 2020, with an SSD with a crucial chipset (especially if SATA), and they leave it on most of the time, then maybe check SMART hours.

Post reply on HN