Hacker News Reader

Comment by userbinator | Hacker News Reader

Reading the part about using foam to make these drives quieter, and the link to the author's other article about putting drives on foam, makes me write this obligatory warning: hard drives do not like non-rigid mounting. Yes, the servo can usually still position the heads on the right track (since it's a servo), but power dissipation will be higher, performance will be lower, and you may get more errors with a non-rigid mount. Around 20 years ago it was a short-lived fad in the silent-PC community to suspend drives on rubber bands, and many of those who did that experienced unusually short drive lifetimes and very high seek error rates. Elasticity is the worst, since it causes the actuator arm to oscillate. The ideal mount is as rigid as possible.

View on HN

Meanwhile: https://www.youtube.com/watch?v=tDacjrSCeq4

this vid is like a xkcd on its own for hard drives

I guessed what that would be before clicking. Yes, HDDs are extremely sensitive to any vibration.

As someone with a bit of experience on this topic:

HDDs doesn't like micromovements. If you put it on a pink foam mat (both a computer and yoga ones) it wouldn't matter. If you 'rigid mount' it but your screws would came lose then your HDD wouldn't like it because it wo&ld result in microvibrations from the self induced oscillations.

Rubber washers are good because they eat those microvibrations. The hard foam which is talked about in the linked article is not good because it is bad from the all aspects - too hard to eat up microvibrations, too soft to be a rigid mount.

The worst thing you can do is to rigid mount an HDD to a case which is a subject to a constant vibration load eg from a heavy duty fan or some engine.

Yes. If you need this you are far better off buying SSDs than wasting time on these silly ideas.

How much would 18TB of SSDs cost compared to 18TB of HDDs? Probably a big reason why many go for HDDs still today.

SSDs are still roughly 3x per $/Tb. You can get a 8Tb QVO SATA drive for a like ~$300 so... ~$40/Tb

Where are you seeing 8TB (assuming you meant TB and Tb) for $300?

At Amazon. Guess I needed to check it better. Also I shouldn't did it in a bar. sigh

Anyway, I have a spreadsheet with both the prices and $/Gb/Tb so I just copy the relevant part here and hope formatting would persist:

    $/Tb Item Interface Capacity Price, $
     $90 SSD 4Tb Samsung 870 QVO (MZ-77Q4T0BW) SATA3 4000 $359
     $96 SSD 2Tb Samsung 870 QVO (MZ-77Q2T0BW) SATA3 2000 $192
    $102 USB 1Tb SanDisk Ultra Dual Drive Go (SDDDC3-1T00-G46) USB 1000 $102
    $103 SSD Samsung PM1643a MZILT3T8HBLS-00007 3.84T (root) SAS 3840 $394
    $104 SSD 4Tb Samsung 870 EVO (MZ-77E4T0BW) SATA3 4000 $417
    $105 SSD 2Tb Transcend 225S (TS2TSSD225S) SATA3 2000 $210
    $106 SSD 4Tb Transcend 230S (TS4TSSD230S) SATA3 4000 $425
    $107 SDXC 2Tb MicroSD SanDisk Extreme (SDSQXAV-2T00-GN6MN) SDXC 2000 $215
    $109 SSD 2Tb Samsung 870 EVO (MZ-77E2T0BW) SATA3 2000 $217
    $111 SSD 2Tb Kingston KC600 Series (SKC600/2048G) SATA3 2000 $223
    $115 SSD 8Tb Samsung 870 QVO (MZ-77Q8T0BW) SATA3 8000 $923
    $128 SSD 7.68Tb Samsung PM9A3 (MZQL27T6HBLA-00A07) OEM U.2 7680 $985
    $129 SSD 1Tb Samsung 870 EVO (MZ-77E1T0BW) SATA3 1000 $129
    $134 SSD 3.2Tb Intel P4610 Series (SSDPE2KE032T801) U.2 3200 $430
    $140 SSD 1.6Tb Intel P4610 Series (SSDPE2KE016T801) U.2 1600 $224

So 8Tb QVO are $115/TB.

Might be useful to add an "endurance" column to this, as the enterprise drives will tend to have multiple times the endurance of the consumer ones.

The endurance ratings are definitely worth knowing about if you write heavily to things.

Thanks, very interesting. TIL.

I've been mounting my 3.5" hard drives on those "fad" rubber band 5.25" drive bay adapters for decades and have not noticed any increased failure rate at all. Sure, seek time may be worse, but the reduced noise has been worth it for me.

The problem isn't just slower seeks; it's when vibration causes the head to go off-track and write data where it shouldn't, faster than the servo can correct. Track pitch in modern hard drives is only a few dozen nanometers.

I think OP is talking about something quite different.

Can you give a pic or link on what you are using?

I'm pretty sure whatever that community experienced is more anecdotal that statistically provable...

I’ve worked at a scale that is statistically relevant. Tens of thousands of drives under my control. I’ve seen a ton of different failure modes. Some of our anecdotes are actually useful. The problem with book and lab theory is that sometimes the theoretical problems don’t manifest (SSD wear out for example) and sometimes the minor seeming things turn out to matter a lot.

Reply on news.ycombinator.com