New Samsung SSD 840 EVO Read Performance Fix Coming Later This Month
by Kristian Vättö on April 14, 2015 1:40 PM EST
The Samsung SSD 840 EVO read performance bug has been on the table for over six months now. Initially Samsung acknowledged the issue fairly quickly and provided a fix only a month after the news hit the mainstream tech media, but reports of read performance degradation surfaced again a few weeks after the fix had been released, making it clear that the first fix didn't solve the issue for all users. Two months ago Samsung announced that a new fix is in the works and last week Samsung sent us the new firmware along with Magician 4.6 for testing, which will be available to the public later this month.
I covered the reason behind the issue in one of our earlier articles, but in short the read performance degradation is a result of cell charge decay over time that caused extensive read-retry cycles to retrieve the correct data. The new firmware fixes this by periodically refreshing (i.e. rewriting) old data, which recovers the cell charge back to its original state and ensures that no read-retry or ECC that would degrade the performance is needed. Samsung says that the refresh operation does not impact user performance, suggesting that it's a relatively low priority process that is run when the drive is idling.
The new Magician 4.6 also includes an Advanced Performance Optimization feature, which is similar to the performance restoration tool that Samsung released earlier. Basically, it's a command that tells the SSD to rewrite all of its internal data, which resets all cell charges and hence recovers performance. It's merely a supplementary tool as the firmware upgrade itself should be enough to restore performance, but in case the performance isn't fully restored after the firmware upgrade (and some idle time to let the drive refresh the cells), the tool can be used to force a cell charge refresh.
I haven't run any tests of my own because I don't have any 840 EVOs deployed in my systems (I only have one 2.5" EVO anyway), but Allyn Malventano from PC Perspective managed to run some tests on a degraded drive to show the impact of the new firmware.
Before update
After update
After "Advanced Performance Optimization"
Allyn's tests indicate that the new firmware seems to mostly fix the issue even without running the optimization tool. Note that Allyn didn't give the drive any idle time after the firmware update, so the update appears the be very effective and with idle time the performance would likely have restored on its own.
Obviously, the big question is whether the performance will stay high because there was never a problem with freshly written data. We won't know that for sure until a couple of months later, but given the way the new firmware handles old data it does sound more promising because no data should get old enough to be slow to read.
Some of you are likely skeptical about the effect on endurance since rewriting the data will consume P/E cycles, but I find this to be a non-issue. We know that Samsung's 19nm TLC NAND is rated at 1,000 P/E cycles, so if the drive was to refresh all cells once a week, even that would only consume 52 cycles in a year. In five years time the total would be 260 cycles, which leaves you with 740 cycles for user data writes (for the record, that's 52GB of NAND writes per day for five years with the 120GB 840 EVO).
All in all, I hope this fix will finally put an end to the performance degradation. The issue has been bugging many users for months and it's critical that the users get what they initially paid for. On one hand I'm confident enough to say that this fix is permanent given the way it works, but on the other hand I don't want to be too optimistic this time around because the first fix didn't turn out so great. Either way, I think this fix is the last chance for Samsung to provide a permanent solution because they already failed to do so once and it would no longer be fair to ask the customers to wait months for a fix that might or might not fix the issue. For now the only thing we can do is wait for user reports and hope for the best, but at least in theory the new firmware should be a permanent fix.
Facebook
Twitter
RSS
78 Comments
View All Comments
Solrax - Tuesday, April 14, 2015 - link
I have the exact same concern. I can drag out an old magnetic drive years after I've last used it and can read it fine. I recently booted up an old machine that was running Windows 98! I've never heard before that would be a concern with SSD, but it will apparently be a very real problem with the 840 EVO. I've already had one die exhibiting excessive ECC that sounds a lot like an extreme case of this same problem.I'm very concerned that my Surface Pro 3 has a Samsung SSD in it (reportedly of the 840 EVO technology). If I stop using it for a year it's drive may be effectively erased? Better get the recovery partitions off onto a flash drive...
Like others have said, this may be my last Samsung SSD. Too bad I didn't know about one being in the Surface. Nothing I can do about that (except at least they are apparently preparing the same firmware update for the Surface drive - they never released the first version for it).
Achaios - Tuesday, April 14, 2015 - link
Thank you for the update, Kristian. You are the best.KenPC - Tuesday, April 14, 2015 - link
I am amazed, dazed, and shocked by this article.Samsung launched TLC in a major way 2013..
By mid 2014, problems were well documented.
These are problems that made Samsung TLC drives definitely lower tier performance in the market and markedly different that the advertised and specified performance.
By late 2014, a first firmware 'fix' was found ineffective, but Samsung still promised to restore TLC performance to spec'd and advertised performance.
By Feb 2015, Samsung still promised to restore the drives to spec and their perceived market position in March, and evidence of slowdowns in the 840, 840evo and TLC based OEM drives were widely reported.
In mid April, (pardon the mixed metaphor), Samsung fed Anandtech the koolaid and said,, these are not the slowdowns you are looking for,, move along.......
So, to be quite clear, the slowdown disguise from Samsung ONLY works if you choose to install magician 4.x, and ONLY works if you have a consumer drive, and NOT if you have a Samsung OEM TLC based drive. (Oh and the extra bits written are also not of any concern, of course!)
So the 'fix' is to play musical chairs with the drive data every so often... ????
That's no fix,, restoring performance as advertised and spec'd is a fix!
gohanrocs12 - Wednesday, April 15, 2015 - link
did you fully read the article? There is a FW coming out as well, you won't need Magician if you update the FW since the FW will be doin everything for you automatically when you leave the system powered on and idle.KenPC - Thursday, April 16, 2015 - link
The middle chart for read speed clearly shows the FW update does not restore performance. It is not 'restored' until all the data is forcibly moved around.If the FW works, then why the need to include the full-drive data moving option at all?
And so far, the indications are that the updates are for the 840evo only and not the other Samsung TLC drives.
Kristian Vättö - Thursday, April 16, 2015 - link
Note that the drive wasn't given any idle time to fully restore the performance. With some idle time the performance should be fixed without the need to run the optimization tool. Its main purpose is for drives that have been used for archival purposes (although I wouldn't recommend an SSD, let alone a TLC drive for that) as the firmware's internal optimization process can only run if the drive is powered on.leexgx - Tuesday, March 6, 2018 - link
The ssd was not given any time to idle after he did the firmware update (read the article) so it been able to restore the ssd even to that point was very goodmore then likely just running the full ssd benchmark test after the firmware update most likely caused a force page refresh due to high ECC read retrys so the rest of the test was at expected speed (doing the adv performance optimisation should only need to be a one time event)
aggiechase37 - Tuesday, April 14, 2015 - link
Want to hear the real kick in the nuts? I have multiple drives in my video editing machine. The OS drive is an EVO, which the performance "optimization" tool updates fine. But for the source file drive, the tool won't fix it. I called in to Samsung, and I have to do this whirly bird routine of taking the drive completely out of the machine, putting it in my laptop, booting from some boot disk that I have to make, and then running the tool with some command line garbage. I've already been through that routine once. Anyone here think I want to go through that again? Me neither. Unless these drives are replaced with something that works as advertised, I'll never touch another Samsung product of any sorts so long as I live. This is pure bull.Laststop311 - Wednesday, April 15, 2015 - link
Well luckily there hasn't been any slowdown in the 850 evo drive. Since the cells are 40nm again I think the much larger cell size makes them a lot more robust, I believe the 840 evo used 20nm cells. Even so I still would not go for TLC nand. I have a 512GB 840 pro and the MLC it uses is flawless and it's speed is so good there is no point to upgrade until nvme and pci-e 3.0 x4 drives become commonplace. Tho I could use more space for more game installs as they have become so huge. May have to get a 1TB 850 pro to tide me over until 2TB drives are the same price as current 1TB drives and are 3.0 x4 interface and nvme.Jan-Erik - Saturday, June 18, 2016 - link
My 850 EVO have had a notisable performance loss after being unused for a while now. A round with diskfresh dragged the performance up from ~200MB/s to the normal 500+ MB/s. I'm surpriced nobody else is experiencing this problem...?I have the 840 EVO as well, and i do agree the performance degration is not even on the same page, but still a loss of over 50% performance on the 850 should be reason for Samsung to take action?