Brands please. It’s time they have some pressure to fix these data corruption issues
I tested four NVMe SSDs from four vendors – half lose FLUSH'd data on power loss (2022)
101–110 of 261 posts
Re: I tested four NVMe SSDs from four vendors – half lose FLUSH'd data on power loss (2022)
#102Earlier quoted context omitted.
Multiple reports in the Twitter thread that this also happens for server-grade HDDs.
I couldn't find this? Can you link this claim?
https://nitter.net/john_p_looney/status/1495823128546746372#...
https://nitter.net/lgerbarg/status/1495822123772018688#m
I interpreted those as being server-grade but maybe they’re not.
Re: I tested four NVMe SSDs from four vendors – half lose FLUSH'd data on power loss (2022)
#103Earlier quoted context omitted.
I think this is typical behaviour with ext4 on Linux, if the application doesn't do fsync/fdatasync to flush the data to disk. Depending on mount options, ext4fs does metadata journaling ensuring the FS itself is not borked, but not data journaling which would safeguard the file contents in event of unclean shutdown with pending writes in the caches. The same phenomenon is at play when people complain that their log…
The current default is data=ordered, which should prevent this problem if the hardware doesn't lie. The data doesn't go in the journal, but it has to be written before the journal is committed. There was a point where ext3 defaulted to data=writeback, which can definitely give you files full of null bytes. And data=journal exists but is overkill for this situation.
The "data" setting of ext filesystems isn't replacement for fsync().
Re: I tested four NVMe SSDs from four vendors – half lose FLUSH'd data on power loss (2022)
#104Does advertising a product as adhering to some standard, but secretly knowing that it doesn't 100%, count as e.g. fraud? I.e., is there any established case law on the matter? I'm thinking of this example, but also more generally USB devices, Bluetooth devices, etc.
For IT products, I doubt it. For sectors where regulation is more mature of course: take food, automotive, etc.
Re: I tested four NVMe SSDs from four vendors – half lose FLUSH'd data on power loss (2022)
#105Misleading headline since after testing eight more drives, none more failed. 2/12 is not nearly as dramatic as “half”, and the ones that lost data are the cheap brands as one would expect.
2/12 is not good, especially if the drives that failed were using off the shelf phison controllers which is basically the entire market besides sandisk/samsung/intel.
Re: I tested four NVMe SSDs from four vendors – half lose FLUSH'd data on power loss (2022)
#106If you need PLP use an enterprise drive. That's what they're for.
I've seen lost completed FUA writes on enterprise drives quite a few times.
Re: I tested four NVMe SSDs from four vendors – half lose FLUSH'd data on power loss (2022)
#107Earlier quoted context omitted.
There were a few more listed deeper in the thread. Fyi, the nitter version is actually readable: https://nitter.net/xenadu02/status/1495693475584557056#m Samsung 970 Evo Plus: MZ-V7S2T0, 2021.10: Pass WD Red: WDS100T1R0C-68BDK0, 04Sept2021: Pass Crucial P2 250GB CT250P2SSD8, FW P2CR046: Pass Samsung 980 250GB MZ-V8V250, 2021/11/07: Pass WD Black SN750 1TB WDS100T1B0E, 09Jan2022: Pass WD Green SN350 240GB WDS240G20C,…
So...vendors no sane person would store valuable data on their drives were the only ones that failed. The sound of a dog biting a man...
Pretty much every brand uses phison controllers in at least some of their products, even wd/samsung/intel who design controllers in house use them for their cheapest offerings because phison is all about making the cheapest product possible.
Re: I tested four NVMe SSDs from four vendors – half lose FLUSH'd data on power loss (2022)
#108Earlier quoted context omitted.
So...vendors no sane person would store valuable data on their drives were the only ones that failed. The sound of a dog biting a man...
SK Hynix is the #3 flash manufacturer (acquired Intel's NAND biz), and their RAM is quite decent. i wouldn't think twice about buying if it wasn't for this report.
Hynix's flash is just fine. It's the controller at fault for this.
Re: I tested four NVMe SSDs from four vendors – half lose FLUSH'd data on power loss (2022)
#109Earlier quoted context omitted.
The current default is data=ordered, which should prevent this problem if the hardware doesn't lie. The data doesn't go in the journal, but it has to be written before the journal is committed. There was a point where ext3 defaulted to data=writeback, which can definitely give you files full of null bytes. And data=journal exists but is overkill for this situation.
The "data" setting of ext filesystems isn't replacement for fsync().
It's not a replacement but it can give you some guarantees.
Also fsync is a terrible API that should be replaced, but that's mostly a different topic.
Re: I tested four NVMe SSDs from four vendors – half lose FLUSH'd data on power loss (2022)
#110There is a flood of fake SSDs currently, mostly big brands. I've recently purchased counterfeit 1TB. It passes all the tests, performance is ok, it works... except it gets episodes where ioping would be anything between 0.7 ms and 15 seconds, that is under zero load. And these are quality fakes from a physical appearance perspective. The only way I could tell mine was fake is that the official Kingston firmware updat…
Where are you seeing counterfeits? AliExpress, Ebay, Amazon?
Probably chinese sellers on all those sites. I've noticed a common thread with people who complain about counterfeits is that they're literally buying alphabet soup brand fakes from chinese FBA sellers instead of buying products directly sold by amazon or from more traditional retail channels.