Over the last month there has been some concern over the read performance of Samsung’s 840 EVO drives, and whether after Samsung’s previous performance fix, that these same drivers are starting to regress in performance once again. Since then we have been pressuring Samsung for additional information on the issue and a response, and this afternoon Samsung has finally issued a statement on the matter.

In October, Samsung released a tool to address a slowdown in 840 EVO Sequential Read speeds reported by a small number of users after not using their drive for an extended period of time. This tool effectively and immediately returned the drive’s performance to normal levels. We understand that some users are experiencing the slowdown again. While we continue to look into the issue, Samsung will release an updated version of the Samsung SSD Magician software in March that will include a performance restoration tool.

As a reminder, the original 840 EVO performance degradation issue was a result of a combination of NAND cell charge decay and NAND management algorithm issues. While NAND cell charge decay is a normal part of NAND operation, it was something Samsung’s more complex TLC NAND was more sensitive to. Meanwhile Samsung’s algorithms, when faced with this decay, erroneously went into an aggressive read-retry state, which is ultimately what lead to the drop in read performance. Samsung’s fix in turn addressed their NAND management algorithm, and at least at the time was thought to be a permanent fix for the issue.

These more recent performance issues and now Samsung’s statement make it clear that the issue is unfortunately not as fixed as Samsung initially thought it would be. At this point Samsung isn’t saying what the root cause of this latest issue is, but it’s likely that this is a continuation of the original issue. In any case the upshot is that Samsung believes the issue can be corrected, however given the last fix it’s not clear whether this next fix will be any more a permanent fix than the last one.

Source: Samsung (via email)

POST A COMMENT

75 Comments

View All Comments

  • Mark_gb - Monday, February 23, 2015 - link

    I too have this drive. And I too am affected by the slowdown.
    HOWEVER, I have never lost a single bit of data, nor has the drive ever stopped working. To find out if the drive has actually slowed down, we have to run benchmarking programs to find out.
    So yeah, its slower than it should be. But, its still thousands of times fast than a hard drive, and it works perfectly well.
    We bought TLC SSD's. The very first TLC SSD's to go on the market in fact. We took a chance on it. And as we all know now, there have been some very minor problems. It was fixed once, and I expect that it will be fixed again.
    BTW, my 1TB 840 EVO is still the ONLY storage device in my system. And it keeps me happy! :)
    Reply
  • Hulk - Friday, February 20, 2015 - link

    I realize the EVO 840 uses 19nm TLC vs. the 40nm TLC for the EVO 850 and therefore the EVO 850 should be more robust in terms of these voltage fluctuations, but I'm wondering if we're going to see the same issues down the road with the 850 EVO's as well? It took a year or more for the issue to crop up on the EVO 840? I was looking to buy one and now I'm thinking the extra money (and peace of mind) for the MLC in the 850 Pro might be worth it. Reply
  • chucky2 - Friday, February 20, 2015 - link

    A tool that the user is going to have to run, or a cron job the tool itself will run (and thus needing the tool to be installed), is not an acceptable solution. They need to: 1.) actually fix the issue permanently, or 2.) exchange these drives for an equal or better performing drive that does not have the issue, or 3.) offer full refunds. Nothing less is acceptable IMO. Reply
  • Hulk - Friday, February 20, 2015 - link

    I agree.

    It's starting to look like the drive are degrading faster than expected or in a different manner than expected and they are scrambling to "band aid" the drives to get them out of the warranty period. If this goes on too long could they be looking at a class action?
    Reply
  • chucky2 - Friday, February 20, 2015 - link

    I'd add this to Samsung: OCZ took a beating on their SSD rep for a long time (it still exists)...don't go down that road in the community... Reply
  • mapesdhs - Wednesday, February 25, 2015 - link

    OTOH, if all those who spewed OCZ hate for so long don't react to Samsung in the same
    way if the problems persist, then that would be pretty weird. Haters should at least be
    consistent. :D

    Ian.

    PS. I have more than 40 OCZ SSDs, never had a problem with any of them. Have
    a bunch of Samsung models aswell, various others; the only one that went whacko
    was a SanDisk Extreme II which briefly stopped being recognised after a fw update
    attempt (eventually righted itself for reasons unknown, though btw, SanDisk were
    happy to send a replacement even though I made it clear I bought it used, so
    creds to them for that; they added it to their support setup too).

    Not bought an EVO so far, just seemed like the prices were too high IMO. Have
    many 830s, 840s, 840 Pro and 850 Pro though.

    Ian.
    Reply
  • nirolf - Monday, February 23, 2015 - link

    I agree too.

    I'd say the title is misleading, it seems that they're not working on a new firmware to fix the issue, they're just working on a work-around. That's really bad news and it probably says that the problem is kind of "unfix-able" (hardware level).
    Reply
  • nirolf - Monday, February 23, 2015 - link

    For the record, I have 2 of these (one 120 GB and one 240GB 840EVO) that both had the new firmware since day one and their performance is already sub-par (lots of ~100 MB/s zones) after 2 month of use. I trusted the "fix" and got screwed. I'll avoid Samsung for a long time for this. Reply
  • sheh - Friday, February 20, 2015 - link

    Would it be possible to get real information from Samsung on the data retention specs of this and other drives? Reply
  • sheh - Friday, February 20, 2015 - link

    I don't mean the JEDEC mandated specs, but more details. For example, stuff like retention-vs-P/E graphs. Reply

Log in

Don't have an account? Sign up now