I have a diy kit and bought the Transcend MTE220S 1tb drive via amazon that lukas uses in reform max(according to the “parts needed to finish diy…” thread).
So far it is working flawlessly, not trouble recognizing the Hardware or anything. Haven’t put much data on it yet as I am still doing base configuration to my system whenever I have free time.
I use a Seagate FireCuda 510 2TB, because of the 2600 TBW. It works without any problems
I bought a Crucial P1 1TB NVMe SSD yesterday, which works perfectly. I am typing this on the reform after booting from SD → NVMe. Exact model is CT1000P1SSD8. I searched on the Crucial website for more info but saw that this is discontinued and replaced by the P2 which I believe will work too. This was really cheap, under 10cents/GB and Gnome Disks reports 284.7 MB/s read, 193 MB/s write.
2TB, that’s some serious storage!
Hehe, my last daily driver had a ssd with 256 GB. Back in 2012 i thought this is big enough for all my needs… it wasn’t. So i thought it would be nice to have a little more space now on my reform x)
Never knew that series of drives has such a high rated endurance. Though it’d feel wrong to put a drive like that in an ARM laptop when my main desktop doesn’t even have something that nice (512GB 970EVO)
Just wanted to add to this list the drive I ended up getting. An ADATA XPG SX8200 Pro 512GB. Kinda overkill, though no where near as much as devyl’s Firecuda 510, but I wanted to go with one that had a DRAM cache as I didn’t trust that HMB would work, plus it had good write endurance (300TBW for 512GB).
Appears to be working just fine (I’ve been running my MNT on it all day now), and supports APSTE power saving by default, and from reviews is a very power efficient SSD.
I went with the 1TB model of the ADATA XPG SX8200 Pro. But that might have been a mistake as it does not work that well with my MNT reform .
It is detected, but it is really slow compared to the SD-card. E.g. I can read every line systemd prints out when booting from the NVMe. When using the SD-card all that just flies by.
Gnome disks reports 90.6 MB/s read, 33.6MB/s write, average access time 104.06msec.
That’s odd, I wouldn’t have suspected any difference hardware wise between the 512 and 1TB models of the same drive. I’m able to get ~287MB/s reads and writes to mine with 0.07ms access times. Something is seriously wrong with that access time
Do you have another computer to test the drive in? Perhaps you got a defective or counterfeit drive? Or try taking it out and re-seating it.
EDIT: Just to check the part # for mine is ASX8200PNP-512GT-C
The 1TB model should be ASX8200PNP-1TT-C instead.
I’ve been using mine daily for over a week now and have no issues running from the nvme drive at all, even at 4 days uptime currently.
Yeah, I wouldn’t expect there to be any difference between those to drives.
The part # on the box says ASX8200PNP-1TT-C.
0001:01:00.0 0 Non-Volatile memory controller: ADATA Technology Co, Ltd XPG SX8200 Pro PCIe Gen3x4 M.2 2280 solid State Drive (rev 03)
It seems legit, I tested it out in another computer (Ryzen 5 3600 on a B450 motherboard) and I get 3.2GB/s read, 2.4GB/s write and 0.01ms access time. I know ADATA has swapped out the controller on later revisions, maybe that’s the issue?
I re-seated the drive after testing it in the other computer. It didn’t do any difference, still slow.
EDIT: Mine is using the SMI SM2262G controller (aka the slower one).
Weird, I bought mine just over a week ago, but it’s possible it has a different controller. lspci gives
Non-Volatile memory controller: ADATA Technology Co., Ltd. XPG SX8200 Pro PCIe Gen3x4 M.2 2280 Solid State Drive (rev 03)
Same revision reported, I put the “heatsink” on mine already so I haven’t checked what the controller is, but I can try and take it off again to check next time I open the bottom. smartctl shows a firmware version of 42B2S7JA and controller ID of 1
Interesting, smartctl shows that the firmware version on my drive is 32A0T54A. The controller ID is the same as yours.
I don’t see any firmware updates on their site and they haven’t uploaded anything on fwupd.org.
I’ll do some more digging and see if I can figure out what’s wrong. Otherwise I guess I’ll just have to buy another NVMe drive.
EDIT: I checked the different logs using the nvme-cli and everything seems to be fine. Only thing I saw was the smart log triggered a
stack smashing detected error. In either case I opted to return the drive and I’ll see if I can find another drive that works. Has anyone had any experience with WD NVMe:s?
Went to the local store today and bought a WD Blue SN550 1TB and that works as expected!
With gnome disks I’m getting 296.2 MB/s read, 395.6MB/s write and access time 0.06ms.
Sorry my recommendation didn’t work for you. I’m honestly surprised by the write numbers you’re getting with that! I specifically avoided the Blue because it’s a dram less design (relies of a host memory buffer or else has no cache). Though that high write speed is suspicious. Wonder if that’s something to do with it’s SLC cache or what, might need to see if you can make the writes larger to find out.
I never tested my writes in gnome-disk before moving my root over to it, so not sure how mine will compare there. Either way the limiting factor for speed is the 1 PCIe lane on the Reform
No worries. At least now we know to avoid the XPG SX8200 Pro 1TB.
Yeah, I was a bit hesitant with the Blue. But I figured that the bottleneck will be the interface to the Reform. And that will allow it to keep up with the read/writes without any DRAM cache.
I tested to increase the sample size to 20M and the result was about the same. Maybe I should gone higher, but I don’t want to put too much unnecessary wear on it.
I agree that those writes looks a bit suspicious, given that it should be able to read faster than writing. If the data sheet is to be trusted (2400MB/s read, 1950MB/s write). But both are way above the speed that the one PCIe lane can handle. Like you said the limiting factor will be the one PCIe lane.
Now you have me thinking, I looked at the chip datasheet and it has 2x PCIe 2.0 interfaces, so with the one lane there should be a bandwidth of 500MB/s So the write speed isn’t out of the realm of possible.
Though now I’m wondering what the bottleneck is that most NVMe drives we have are getting <300MB/s. Wondering if it’s just the controllers in most drives being unhappy with a single 2.0 lane, a limitation of the SoC, or perhaps a kernel issue?
My drive should be capable of 3500MB/s reads on 4x 3.0 (3.94 GB/s max), it should have no trouble saturating a 2.0 link.
I bought a 1TB SK Hynix Gold P31, which is one of the drives recommended by Wirecutter. It seems to be working fine after a couple days. I’m seeing similar numbers to what others have posted: ~300 MB/s reads and ~380 MB/s writes.
It’s currently unencrypted, but I’m thinking about reformatting it and encrypting with LUKS. Does anyone know if there’s a significant performance impact using LUKS on the Reform?
Can confirm that WD Blue SN550 500gb works here.
Another working WD Blue SN550 - this time 2TB. Like in “Big NVMe…” thread, I intend to use it for copy of my data - and for experimenting with various OS.
Hey everyone - I’d be happy to try out a few of my nvme drives to add to the list, but simply saying that a drive officially “works” or not is a little subjective. What testing procedures can we agree on? Are we talking something relatively scientific where we write/read sequential/random blocks and record performance, checking that it passes CRC and exceeds some threshold of performance, or do we say “I saved a copy of The Matrix on the drive and was able to play it back?” If we’re preferring the former option, is there a script or an existing benchmarking tool we can all agree to use? Perhaps just verify
lsblk output and, if all good, run a
gnome-disks benchmark as mentioned earlier in this thread?