News SK Hynix, Sabrent SSDs Reportedly Lose Data After Power Loss

[Admin]

A Twitter user has tested an SK Hynix and Sabrent Rocket SSD and found both to have strange data loss issues after data is transferred from the DRAM cache to the NAND flash.

SK Hynix, Sabrent SSDs Reportedly Lose Data After Power Loss : Read more

 

[Alvar "Miles" Udell]

A line interactive pure sine wave UPS is as important as your power supply.

 

[ingtar33]

i'm going to be honest, even if the ssd has power loss protection, you're inviting disaster by using a ssd without a UPS. it's peak stupidity. and frankly the fact people need to be told this is a little troubling to say the least.

SSDs have no mechanical storage. period. their storage is all electronic. any power loss, brownout, power supply blowing up, cap going on the motherboard, power fluctuation of any type will endanger your data. not running with a surge protector/battery backup is like inviting the only significant danger to your storage into the house.

 

[Sleepy_Hollowed]

I'd love to know which drives were tested that failed from certifiers.

I used to buy Crucial end of the line drives with advertised protection, which I think was tested.

I've got UPSes and laptops have batteries.... but still, it's quite a gamble to rely on OSes now a days to properly shut down when certain things are running, or if there's users logged in.

 

[watzupken]

Power lost is a problem not just for SSD with DRAM, but also mechanical drives. So I am not sure what is the point of this finding. For most people, this is a non-issue. If one is constantly writing/ reading critical data, then there must always be a backup power, or at least they should be getting SSDs with power loss protection where the capacitors can store power to allow the write to be written to the NAND.

 

[Soul_keeper]

This is good, we need to know this. I hope he can afford to test many of the current drives.

 

[King_V]

Welp, I haven't received it yet, but I guess I'll be returning the SK Hynix Gold P31 and getting the Samsung 970 Evo Plus instead.

Given that WD and SK are also putting terms of service stickers on their SSDs, according to Russ. That's a strike against those brands, in addition to the particular models that fail on power loss.

 

[cryoburner]

i'm going to be honest, even if the ssd has power loss protection, you're inviting disaster by using a ssd without a UPS. it's peak stupidity. and frankly the fact people need to be told this is a little troubling to say the least.

SSDs have no mechanical storage. period. their storage is all electronic. any power loss, brownout, power supply blowing up, cap going on the motherboard, power fluctuation of any type will endanger your data. not running with a surge protector/battery backup is like inviting the only significant danger to your storage into the house.

A UPS isn't going to help if the power supply or motherboard randomly fails though. Really, if the data is important enough that you wouldn't want to risk losing it, then it should be backed up on another drive as well to minimize potential loses.

In any case, testing how a drive handles loss of power seems rather useful, and makes me wonder why drive reviews don't test for that, seeing as different drives may handle the situation differently.

 

[plonk420]

that makes me a bit nervous. i have a few SK Hynix S31s (SATA version of the P31)

 

[mgerdts]

That isn't entirely unexpected given that none of these consumer-class drives have power capacitors for full power-loss protection functionality, but it does indicate that some drives may have better emergency data flushing systems even without a full-fledged power loss protection feature.

Actually, it is unexpected. The tests that were performed involved issuing a write command followed by a flush command. Per the NVMe 1.4 specification:

6.8 Flush command

The Flush command is used to request that the contents of volatile write cache be made non-volatile. If a volatile write cache is enabled (refer to section 5.21.1.6), then the Flush command shall commit data and metadata associated with the specified namespace(s) to non-volatile media. The flush applies to all commands for the specified namespace(s) completed by the controller prior to the submission of the Flush command. The controller may also flush additional data and/or metadata from any namespace.

Data that the drive said was written to stable storage via a successful completion of a flush command was not present on the drive when reading it after returning power to the drive. That means that these drives are not conforming to the specification.

The power loss protection feature is addressed in section 5.21.1.6, mentioned in the earlier quote.

5.21.1.6 Volatile Write Cache (Feature Identifier 06h), (Optional)

This Feature controls the volatile write cache, if present, on the controller. If a volatile write cache is present (refer to the VWC field in Figure 251), then this feature shall be supported. The attributes are specified in Command Dword 11.

Note: If the controller is able to guarantee that data present in a write cache is written to non-volatile media on loss of power, then that write cache is considered non-volatile and this feature does not apply to that write cache.

That is, drives that support power loss protection will use DRAM + a battery/capacitor to make it so that the write cache is not considered a volatile cache. As such, all acknowledged writes are considered to be on stable storage, even if not followed by a flush. In fact, section 6.8 says that in such a case, a flush command is a no-op if a sanitize operation is not in progress.

If a volatile write cache is not present or not enabled, then Flush commands:

• shall complete successfully and have no effect if a sanitize operation is not in progress; and
• may complete successfully and have no effect if a sanitize operation is in progress.