If nothing else, the odyssey of Samsung’s 840 EVO has not been lacking in excitement. After initially launching in 2013 to great fanfare as an excellent, strong-performing low-cost drive, over the long run performance regressions began to occur in deployed drives that saw the read performance of old data significantly drop. At the heart of the issue was the drive’s relatively uncommon 19nm TLC NAND, which given the combination of small feature size and tighter requirements of TLC, eventually resulted in the drive having to slow down and re-read cells to properly read the charge-decayed cells.

Aiming to fix the issue, in 2014 Samsung released a performance restoration tool and firmware update for the 840 EVO. The combination of the tool and firmware would update the drive to better handle decayed cells and reduce the need to re-read them, meanwhile the restoration tool would refresh the drive’s data by re-writing all of the data to fresh cells. The idea being that fresh data in combination with the newer firmware would prevent the drive’s performance from decaying again.

Unfortunately that didn’t work out as planned, and while the data refresh from the performance restoration tool did bring drive performance back up, over the long run performance once again began decaying on old data, even with the firmware improvements. As a result Samsung has commissioned a second, more permanent fix for the 840 EVO. This fix involves another firmware update, this time installing a firmware that periodically refreshes old data rather than the one-off refresh of the performance restoration tool. Refreshing the data once again brings performance back up to where it should be, and the periodic, repeating nature of the refresh means that data is never allowed to get too old to let performance degrade again.

Ultimately Samsung’s second fix is a bit of a brute force solution to the problem, but at this point there doesn’t seem to be anything Samsung can do about 19nm TLC cell charge decay other than to refresh the data, as the problem is intrinsic to the NAND itself. Pre-release versions of the firmware show that this fix works, and conceptually this is much more likely to work over the long run than Samsung’s initial fix. The tradeoff is that it does consume P/E cycles to refresh the data, but by our own calculations even 5 years of refreshes at 1/week would only be 26% of the drive’s rated 1000 cycle lifetime. Meanwhile for the longer term, Samsung has since moved on to 3D-VNAND in newer drives, which is more stable than very small geometry planar NAND and essentially turns back the clock on NAND scaling issues. So the 840 EVO should be the last Samsung TLC drive to encounter this issue.

In any case, after previewing the updated firmware to the press, Samsung has released the updated firmware and its associated version of Samsung Magician (version 4.6) to the public over on their website. After an initial staggered release over the weekend – we suspect to make sure not too many users had the firmware if a problem quickly cropped up – Samsung looks to have opened downloads to everyone. However Mac and Linux users will want to note that at this time only the Magician version of the firmware has been released; the bootable ISOs for directly updating the drive have yet to be updated.

In the meantime this will continue to be an issue we keep an eye on. As with the initial problem and Samsung’s first fix, the decay issue only occurs after a time, so we’ll have to see where 840 EVO performance is in a couple months’ time. However with the very nature of the problem and the periodic refreshing of data, we’re hopeful that this will finally put an end to the performance degradation.

Source: Samsung

POST A COMMENT

74 Comments

View All Comments

  • dromo - Friday, May 1, 2015 - link

    Well, point of view I guess:) but queued trim commands worked fine until this fw relase. Why break it now and make 840 Evo unusable for linux users? Reply
  • toobluesc - Sunday, May 3, 2015 - link

    It definitely got worse for me. My Linux (4.0 kernel) times out regularly. Write-up on my blog @ http://bit.ly/1DN2XUM with some performance numbers and errors.

    My / and /home filesystems are mounted with "discard". I'll see if calms down in the next few days otherwise I'll try dropping discard. Sigh, this looks more like a regression. Worked flawlessly before the update from EXT0AB0Q to EXT0DB6Q.
    Reply
  • skraftnm - Wednesday, April 29, 2015 - link

    I'm using my Evo in RAID mode, 50gb as cache for my system (rapid storage) and 70gb as regular partition.
    But i can't access ssd features such as firmware update and performance restoration because of the RAID mode set in the bios. (instead of AHCI).
    What am i supposted to do?
    Since i can't use the software, will it work just update firmware? (in another computer wich is using ahci mode)
    How could i test my drive? (crystal disk mark will not test older data, right?)
    Reply
  • fiveandhalf - Wednesday, April 29, 2015 - link

    Hi:
    Anyone experience 840 Pro firmware issue under raid controller?
    we have 6 x 840 Pro 512GB running under Dell PowerEdge 720 with H710 controller as raid1, scores around 400MB/s sequential 4K write constantly over past year until last month, we upgraded 2 x SSD firmware from DXM05B0Q to DXM06B0Q and the sequential 4K write speed dropped dramatically from 400MB/s to fluctuation of 20-200MB/s in the same hardware.
    We thought it might be our hardware, so we moved the two different firmware version SSD to another PowerEdge, (as 2 x raid0), as yield same result. We have been talking to Samsung helpdesk who has been nice but unhelpful, It seems to me this is a firmware bug.
    BTW, if we plug the old and new version of SSD back to a desktop with a SATA3 connector, re-do the 4K write test, it is constantly lower on new firmware but not much, something like 390MB/s vs 420MB/s

    Here is the command we use to test with a 20GB test file, we even re-format the drive and tested as empty drive, still same result

    Sqlio.exe -kW -t4 -s30 -dS -o128 -fsequential -b4 -BH -LS testfile.dat

    Hope anandtech.com lab can reproduce this issue, and if it is a bug, we can get Samsung to do something about it.
    Reply
  • fiveandhalf - Wednesday, April 29, 2015 - link

    here is a screenshot of the test result
    http://i60.tinypic.com/2ilk288.jpg
    Reply
  • icarium_jag - Thursday, April 30, 2015 - link

    Any update on new firmware for mSATA version? Reply
  • RSebire - Saturday, May 2, 2015 - link

    Thank you for this article. I've been reading this site for years, but never felt as compelled to say thanks before.
    Thank you for updating me on this issue.
    I have the 840 EVO. Last month after your first article on this drive, I took the plunge and removed my 1TB 840 EVO out of my PS4 and did the performance restoration tool kit on it.
    I haven't even finished installing my digital games on it yet (downloaded somewhere in the region of 800GB's this month on to it.) And now I must go and do it all over again.
    I'm glad I read this site :)

    My PlayStation Now Beta has gone mental in the last 48 hours, locking me out of games and apps, even taking my PlayStation Plus away. Thankfully it is not to do with this, and the only way I'm going to get my PlayStation 4 working again is to wait for the new Firmware that fix's it according to Sony support - So I wont be using it for several weeks anyway.

    I just wanted to say thank you.
    Kind regards
    Richard
    Reply
  • Choppedliver - Saturday, May 2, 2015 - link

    Wow, some seriously spoiled brats and naysayers on here.

    Most people wouldn't know there was an "issue", because it's not an issue. It's only an issue to the "I told you so" people who need to be "right" about something.

    I've got one. I am not even the slightest bit concerned, nor have I noticed an "issue".

    What I do notice, is when I go to a friends house, and they have a mechanical clunker or a hard drive. A "sometimes" slower ssd is still pretty damn quick.
    Reply
  • Oxford Guy - Sunday, May 3, 2015 - link

    It looks like Apple is leaving the people who bought those expensive 1 TB drives out in the cold. Not only does the company refuse to even tell its customers whether the drive uses TLC or not (which it most likely does), there has been no word on a firmware update:

    SM1024F
    Reply
  • Oxford Guy - Sunday, May 3, 2015 - link

    "Samsung Releases Second 840 EVO Performance Kludge"

    FIFY
    Reply

Log in

Don't have an account? Sign up now