Linux Tests Of The QNINE M.2 NVMe SSD Enclosure To USB-C Adapter

[Maxim Levitsky]

To be honest, by defenition a NVMe drive doesn't support SATA (e stands for pci express), but M.2 connector can carry SATA signals in addition to NVME.

[ThoreauHD]

Wonder if it's a sleep/low power issue/setting on the disconnect.

[Michael]

Can you boot from it? Does it show in bios/efi boot menu?

Yes and yes, that is how the testing was done for the benchmarks.

[Veto]

Interesting test!! Some additional questions:

• What type of interface/bridge IC is used and/or can we get a clearer picture of the backside of the board?
• What is the output of lsusb and dmesg?
• Does SMART work (E.g. by smartctl)? It is historically a problem with USB adapters.

Most likely the adapter is a reference design for the central interface IC and the random disconnects due to either a driver or chip error, related to this specific IC. Buying a different adapter based on the same chip is likely to have the same disconnects.

[satan0rx]

You can see the JMicron logo on thr chip. So I guess it's the JMS583.

[dwagner]

You can see the JMicron logo on thr chip. So I guess it's the JMS583.

You don't really have to guess, since that is currently the only NVMe <-> USB 3.1gen2 chip on the market.
German c't magazine recently tested two such external enclosures (paywalled: https://www.heise.de/select/ct/2018/21/1539398715074134 ) - with similar results: The connection is simply unstable with all enclosures using this chip, and not only under Linux.

I guess we'll have to wait for the ASMedia ASM2364 chip to hit the market before expecting different results.

[torsionbar28]

[*]Does SMART work (E.g. by smartctl)? It is historically a problem with USB adapters.

USB 3.1 uses UASP for storage, so full SCSI command set is available. USB prior to 3.1 was junk, with junk protocols and implementations that were hit or miss on SMART. USB 3.1 fixes this mess finally.

[timrichardson]

A common reason to use an enclosure like this would be to clone an existing laptop SSD to a new one, and after cloning, taking the new drive out of the enclosure and into the laptop. Done that a few times with SATA drives. But I heard that NVMe enclosures don't work like this, for some reason: putting the drive into a the laptop requires reformatting it. Is this correct?

[PCJohn]

USB 3.1 is quite frankly the first iteration of USB that doesn't suck ass at storage. It only took what, 23 years to get here. yay?
v1.x was serial port replacement. v2.0 was stupid slow, no reason to use it over firewire. [...]

Surely, you was not IT guy that time.... USB was a huge step forward over connecting the things over serial (or even parallel) port. Installing drivers for serial devices was troublesome and painful. Configuring programs to use them required much of configuration: setting baud-rate, number of stop bits, etc. USB was a huge step forward. USB 2.0 was finally something reliable and fast enough for most of the things of that time (maybe, not for you). Firewire was there but did not get widespread use. I never had a single device. Complain or not, it never got widespread use in circles around me, same as SCSI disks. Anyway, I am happy that you are finally happy with USB 3.1.

[darkbasic]

Huh? The product tested in this article does; the SSD tested in the article is an NVMe drive. To my knowledge, all NVMe drives also support SATA. If you want something that'll benefit from the extra performance of an NVMe drive's PCIe lanes, I think the overhead and abstraction of USB would diminish those returns.

The Amazon product page says it does not support SATA M.2 drives.