Samsung’s 850 EVO solid-state drive reviewed

Samsung’s 850 EVO SSD has been a long time coming. We got our first hint of its existence in July, when the firm revealed that it was developing a TLC version of its 3D V-NAND. More details on the three-bit variant were released in August, when Samsung confirmed that the flash was destined for the 850 EVO. Then, in October, mass production of TLC V-NAND chips began, setting the stage for today’s formal unveiling.

The new EVO has some Shaq-sized shoes to fill. Samsung claims that its predecessor, the 840 EVO, is the best-selling SSD on the market. We haven’t seen sales figures to support that assertion, but the EVO does have more than double the number of Amazon user reviews of its peers. An overwhelming majority of those—4,540 as I write this—give the drive a five-star rating.

Our expectations are especially high because the 850 EVO’s elder sibling, the 850 Pro, is the fastest SATA SSD we’ve ever tested. Samsung’s latest hotness is based on the same core technology, just with an extra bit per cell and some clever caching to pick up the slack. And it’s backed by a higher endurance rating and longer warranty than most SSDs.

In the realm of SATA SSDs, the 850 EVO is kind of a big deal. Let’s see what it can do.

TLC in three dimensions

The defining element of the 850 EVO is easily its three-dimensional flash. This new, three-bit implementation has the same 32-layer structure as the MLC V-NAND in the 850 Pro. The cell geometry is the same, and the die area should be similar, but the chips are fabbed at a different facility. Samsung doesn’t mass-produce V-NAND and then sort the results into MLC and TLC bins; the chips in the 850 EVO were born to host three bits per cell

Indeed, this entire generation of V-NAND seems tailor-made for TLC. The individual chips offer 128Gb of capacity with three bits per cell, a much rounder number, at least in PC storage terms, than their 86Gb MLC payload. That makes perfect sense, because V-NAND’s strengths nicely offset TLC’s weaknesses.

Three-bit flash has lower write performance and endurance than its two-bit counterpart. The extra bit is at fault: it requires the cell to differentiate between twice as many possible values within the same limited voltage range. Writing and verifying data is more difficult—and slower—as a result. TLC’s higher bit density makes the cells more sensitive to normal flash wear and more prone to interference from adjacent cells.

Source: Samsung

V-NAND tackles those weaknesses in several ways. First, it trades the floating gates typically found in planar NAND for a 3D charge-trap that’s inherently more robust. This structure stores electrons in a trapping oxide that wraps around a vertical electron channel. The oxide is an insulator, so any physical damage only affects electrons in the immediate vicinity. With floating gates, a breach in the oxide can drain the entire contents of the cell, rendering it useless.

Stacking cells vertically also helps V-NAND’s endurance. Instead of increasing the bit density by making the cells smaller, and thus weaker, Samsung lays down multiple layers based on a fairly large 40-nm planar geometry. The company claims this coarser 2D process puts enough distance between the cells to completely eliminate interference along the horizontal bit lines. Samsung says there’s enough space between the layers to virtually eliminate interference along the vertical word lines.

With less interference to worry about, V-NAND can employ a simpler programming algorithm that improves write performance. It can also exploit the inherent robustness of the trapping oxide to program the cells more aggressively—or write less aggressively to extend the life of the flash.

TLC V-NAND still has an extra bit per cell, so it can’t match the peak speed or endurance of its MLC counterpart. However, Samsung claims the EVO’s flash is good enough to keep up with the planar MLC NAND found in most SSDs.

Capacity Max sequential (MB/s) Max 4KB random (IOps) Endurance

(TBW)

Price $/GB
Read Write Read Write
120GB 540 520/140 94k 88k/38k 75TB $99.99 $0.83
250GB 540 520/270 97k 88k/70k 75TB $149.99 $0.60
500GB 540 520/420 98k 90k/80k 150TB $269.99 $0.54
1TB 540 520/420 98k 90k/80k 150TB $499.99 $0.48

The endurance ratings certainly put the EVO in MLC territory. According to the official specs, the 120GB and 250GB versions are good for 75TB of total writes, while the 500GB and 1TB flavors can withstand 150TB. Impressively, the larger EVOs have the same endurance rating as the 850 Pro.

We don’t have any V-NAND units in our ongoing endurance test, but that experiment has taught us that SSDs can last much longer than their specifications promise. Common sense also tells us that point is largely academic. PC users typically write no more than a few terabytes a year, which is much less than modern drives are rated to survive.

Note that the specs table lists two write speeds for each drive capacity. The first figure describes the performance of TurboWrite, a flash-based caching scheme inherited from the 840 EVO. TurboWrite addresses a portion of the flash in a single-bit SLC configuration that offers higher performance and endurance than even MLC setups. Incoming writes are funneled into this cache and then moved to TLC storage during idle periods. If the cache is filled before it can be flushed, inbound data proceed directly to three-bit cells, and write performance drops accordingly. The second set of write speed figures in the table above refer to TLC writes.

We’re waiting on Samsung to confirm the cache sizes for the various capacities, but if the implementation is the same as in the 840 EVO, the 1TB drive has a 9GB cache, the 500GB has 6GB, and the others have 3GB. That’s not loads of storage, but it should be sufficient to cover the shorter, bursty writes typical of client workloads. The 850 EVO’s performance specs also suggest caching effectively offsets the performance penalty associated with lower-capacity SSDs. Despite lacking sufficient flash dies to exploit the controller’s highly parallel NAND interface, the 120GB and 250GB drives nearly match the TurboWrite peaks of the higher-capacity EVOs.

In a surprise twist, the 850 EVO 1TB pictured above uses the same triple-core MEX controller as the 850 Pro, while the rest of the family taps a newer MGX chip with only two cores. Samsung contends that V-NAND’s raw performance is good enough for the smaller drives to reach top speed with one fewer core. The greater “hardware automation” introduced with the MEX generation likely lessens the need for additional general-purpose horsepower, as well.

Dropping a core saves cost and power, both important factors in the solid-state sphere. SSD makers are increasingly competing on price, and Samsung is evidently shaving pennies wherever it can. Just look at the tiny circuit board used for the 250GB variant:

For additional perspective, here’s how the two drives look inside their 2.5″ shells:

Samsung packs a lot of other goodness into these tiny packages. The 850 EVO’s 256-bit AES encryption is compliant with the TCG Opal 2.0 and IEEE 1667 standards, meeting the requirements for Microsoft’s eDrive system. The drive supports the ultra-low-power DevSleep state, and it can throttle its clocks to prevent overheating in toasty environments. Then there’s the five-year warranty, a premium perk that defies the series’ mid-range pricing.

The EVO works with Samsung’s excellent SSD Magician utility, which monitors health stats, performs firmware updates, and migrates old data to new drives. That utility also includes RAPID mode, an optional, DRAM-based caching scheme similar to Windows’ SuperFetch mechanism.

We haven’t tested DRAM caching in this review (there’s a full suite of RAPID results in our 850 Pro coverage), but we have put the 850 EVO 250GB and 1TB through their paces against a deep field of competitors. Our performance analysis begins on the next page.

 

CrystalDiskMark — transfer rates

First, we’ll tackle sequential performance with CrystalDiskMark. This test runs on partitioned drives with the benchmark’s default 1GB transfer size and randomized data.

We’ve color-coded the results to make the 850 EVOs easier to spot. We’ve also highlighted the other Samsung SSDs, coloring the TLC and MLC drives in different shades.

Both 850 EVOs are near the front of the pack in our CrystalDiskMark tests. Even the 250GB unit delivers strong write performance, which is really no surprise. The 1GB test should fit easily inside the TurboWrite buffer.

HD Tune — random access times

Next, we’ll turn our attention to random access times. We used HD Tune to measure access times across multiple transfer sizes. SSDs have near-instantaneous seek times, so it’s hard to graph the results on the same scale as mechanical drives. The WD Black and Seagate SSHD will sit out this round to focus our attention on the SSDs.

The 1MB random write test trips up some of the SSDs, but not the 850 EVOs, which are competitive throughout. To be fair, virtually all the SSDs have comparable access times in the other tests. Tiny fractions of a millisecond separate most of the drives in most of these tests.

 

TR FileBench — Real-world copy speeds

FileBench, which was concocted by TR’s resident developer Bruno “morphine” Ferreira, runs through a series of file copy operations using Windows 7’s xcopy command. Using xcopy produces nearly identical copy speeds to dragging and dropping files using the Windows GUI, so our results should be representative of typical real-world performance. We tested using the following five file sets—note the differences in average file sizes and their compressibility. We evaluated the compressibility of each file set by comparing its size before and after being run through 7-Zip’s “ultra” compression scheme.

  Number of files Average file size Total size Compressibility
Movie 6 701MB 4.1GB 0.5%
RAW 101 23.6MB 2.32GB 3.2%
MP3 549 6.48MB 3.47GB 0.5%
TR 26,767 64.6KB 1.7GB 53%
Mozilla 22,696 39.4KB 923MB 91%

The names of most of the file sets are self-explanatory. The Mozilla set is made up of all the files necessary to compile the browser, while the TR set includes years worth of the images, HTML files, and spreadsheets behind my reviews. Those two sets contain much larger numbers of smaller files than the other three. They’re also the most amenable to compression.

To get a sense of how aggressively each SSD reclaims flash pages tagged by the TRIM command, the SSDs are tested in a simulated used state after crunching IOMeter’s workstation access pattern for 30 minutes. The drives are also tested in a factory fresh state, right after a secure erase, to see if there is any discrepancy between the two states. There wasn’t much of one with the 850 EVOs, so we’re only presenting the used-state scores.

The 850 EVO performs very well versus its peers, posting competitive copy speeds with both larger and smaller files. Despite having fewer cores in its controller and fewer dies at its disposal, the 250GB model holds its own in FileBench. In some of the tests, it’s even faster than its 1TB counterpart and the 850 Pro.

 

TR DriveBench 2.0 — Disk-intensive multitasking

DriveBench 2.0 is a trace-based test comprised of nearly two weeks of typical desktop activity peppered with intense multitasking loads. More details on are available on this page of our last major SSD round-up.

We measure DriveBench performance by analyzing service times—the amount of time it takes drives to complete I/O requests. Those results are split into reads and writes.

Impressively, the 850 EVO 1TB nearly matches the mean service times of the 850 Pro. The 250GB drive isn’t as quick, but it still represents a substantial step up from the equivalent 840 EVO. The differences between the two generations are particularly acute with writes.

All the SSDs execute the vast majority of DriveBench requests in one millisecond or less—too little time for end users to perceive. We can also sort out the number of service times longer than 100 milliseconds, which is far more interesting data. These extremely long service times make up only a fraction of the overall total, but they’re much more likely to be noticeable.

The 850 EVOs slog through fewer extremely long reads than their planar peers. They barely log enough longer writes to show up on the radar, which is especially impressive for the 250GB version. The 840 EVO 250GB suffers more than a thousand writes over 100 milliseconds—150 times more than its replacement.

 

IOMeter

Our IOMeter workload features a ramping number of concurrent I/O requests. Most desktop systems will only have a few requests in flight at any given time (87% of DriveBench 2.0 requests have a queue depth of four or less). We’ve extended our scaling up to 32 concurrent requests to reach the depth of the Native Command Queuing pipeline associated with the Serial ATA specification. Ramping up the number of requests also gives us a sense of how the drives might perform in more demanding enterprise environments.

We run our IOMeter test using the fully randomized data pattern, which presents a particular challenge for SandForce’s write compression scheme. We’d rather measure SSD performance in this worst-case scenario than using easily compressible data.

There’s too much data to show clearly on a single graph, so we’ve split the results. You can compare the 850 EVO’s performance to that of the competition by clicking the buttons below each graph.

Instead of presenting the results of multiple access patterns, we’re concentrating on IOMeter’s database test. This access pattern has a mix of read and write requests, and it’s similar to the file server and workstation tests. The results for these three access patterns are usually pretty similar. We also run IOMeter’s web server access pattern as part of our standard suite of tests, but it’s made up exclusively of read requests, so the results aren’t as applicable to real-world scenarios. Our own web servers log a fair amount of writes, for example.


Although the 850 EVOs don’t match the I/O throughput of the 850 Pro, they do deliver higher transaction rates than their ancestors. The 250GB and 1TB incarnations are evenly matched up to four concurrent requests, after which the former starts to plateau. The smaller drive is still competitive with most SSDs, but its larger sibling scales higher, up to a queue depth of 16.

Regardless of the queue depth, the 850 EVOs are well behind the standouts in this test. The Intel 730 Series is an absolute monster across the board, and some of the OCZ drives offer even higher transaction rates under the heaviest load.

Boot duration

Before timing a couple of real-world applications, we first have to load the OS. We can measure how long that takes by checking the Windows 7 boot duration using the operating system’s performance-monitoring tools. This is actually the first test in which we’re booting Windows off each drive; up until this point, our testing has been hosted by an OS housed on a separate system drive.

Level load times

Modern games lack built-in timing tests to measure level loads, so we busted out a stopwatch with a couple of titles.

To no one’s surprise, the 850 EVO’s load times aren’t much different from those of the other SSDs. Most of the drives are separated by less than a second.

As soon as this stream of new releases subsides, we’ll be switching to an all new collection of load-time tests. We have faster test rigs and PCIe SSDs that may provide more interesting results.

Power consumption

We tested power consumption under load with IOMeter’s workstation access pattern chewing through 32 concurrent I/O requests. Idle power consumption was probed one minute after processing Windows 7’s idle tasks on an empty desktop.

The 850 EVO 250GB has particularly low power consumption at idle and under load. Its terabyte twin requires more juice, but that drive still has lower idle power than anything in its weight class. All the other terabyte SSDs draw less power under load, though.

That’s it for performance. If you’re curious about the other SSDs in this review or about how we conduct our testing, hit up the methods section on the next page. Otherwise, feel free to skip ahead to the conclusion.

 

Test notes and methods

Here’s a full rundown of the SSDs we tested, along with their essential characteristics.

  Flash controller NAND
Adata Premier SP610 512GB Silicon Motion SM2246EN 20-nm Micron sync MLC
Adata Premier Pro SP920 512GB Marvell 88SS9189 20-nm Micron sync MLC
Corsair Force GT 240GB SandForce SF-2281 25-nm Intel sync MLC
Corsair Force LS 240GB Phison PS3108-S8 19-nm Toshiba Toggle MLC
Corsair Neutron 240GB LAMD LM87800 25-nm Micron sync MLC
Corsair Neutron GTX 240GB LAMD LM87800 26-nm Toshiba Toggle MLC
Corsair Neutron XT 240GB Phison PS3110-S10 A19-nm Toshiba Toggle MLC
Crucial M500 240GB Marvell 88SS9187 20-nm Micron sync MLC
Crucial M500 480GB Marvell 88SS9187 20-nm Micron sync MLC
Crucial M500 960GB Marvell 88SS9187 20-nm Micron sync MLC
Crucial M550 256GB Marvell 88SS9189 20-nm Micron sync MLC
Crucial M550 512GB Marvell 88SS9189 20-nm Micron sync MLC
Crucial M550 1TB Marvell 88SS9189 20-nm Micron sync MLC
Crucial MX100 256GB Marvell 88SS9189 16-nm Micron sync MLC
Crucial MX100 512GB Marvell 88SS9189 16-nm Micron sync MLC
Intel 335 Series 240GB SandForce SF-2281 20-nm Intel sync MLC
Intel 520 Series 240GB SandForce SF-2281 25-nm Intel sync MLC
Intel 730 Series 480GB Intel PC29AS21CA0 20-nm Intel sync MLC
OCZ Vertex 4 256GB Indilinx Everest 2 25-nm Micron sync MLC
OCZ Vertex 450 256GB Indilinx Barefoot 3 M10 20-nm Micron sync MLC
OCZ Vertex 460 240GB Indilinx Barefoot 3 M10 19-nm Toshiba Toggle MLC
OCZ ARC 240GB Indilinx Barefoot 3 M10 A19-nm Toshiba Toggle MLC
SanDisk Extreme II 240GB Marvell 88SS9187 19-nm SanDisk Toggle SLC/MLC
Samsung 840 Series 250GB Samsung MDX 21-nm Samsung Toggle TLC
Samsung 840 EVO 250GB Samsung MEX 19-nm Samsung Toggle TLC
Samsung 840 EVO 500GB Samsung MEX 19-nm Samsung Toggle TLC
Samsung 840 EVO 1TB Samsung MEX 19-nm Samsung Toggle TLC
Samsung 840 Pro 256GB Samsung MDX 21-nm Samsung Toggle MLC
Samsung 850 EVO 250GB Samsung MGX 32-layer Samsung V-NAND TLC
Samsung 850 EVO 1TB Samsung MEX 32-layer Samsung V-NAND TLC
Samsung 850 Pro 512GB Samsung MEX 32-layer Samsung V-NAND MLC
Seagate 600 SSD 240GB LAMD LM87800 19-nm Toshiba Toggle MLC
Seagate Desktop SSHD 2TB NA 24-nm Toshiba Toggle SLC/MLC
WD Caviar Black 1TB NA NA

The solid-state crowd is augmented by a couple of mechanical drives. WD’s Caviar Black 1TB represents the old-school hard drive camp. Seagate’s Desktop SSHD 2TB is along for the ride, as well. The SSHD combines mechanical platters with 8GB of flash cache, but like the Caviar Black, it’s really not a direct competitor to the SSDs. The mechanical and hybrid drives are meant to provide additional context for our SSD results.

Since you’ve made it this far, here are a couple more shots of the drives we tested:

We used the following system configuration for testing:

Processor Intel Core i5-2500K 3.3GHz
CPU cooler Thermaltake Frio
Motherboard Asus P8P67 Deluxe
Bios revision 1850
Platform hub Intel P67 Express
Platform drivers INF update 9.2.0.1030

RST 10.6.0.1022

Memory size 8GB (2 DIMMs)
Memory type Corsair Vengeance DDR3 SDRAM at 1333MHz
Memory timings 9-9-9-24-1T
Audio Realtek ALC892 with 2.62 drivers
Graphics Asus EAH6670/DIS/1GD5 1GB with Catalyst 11.7 drivers
Hard drives Seagate Desktop SSHD 2TB with CC43 firmware

WD Caviar Black 1TB with 05.01D05 firmware

Adata Premier SP610 512GB with N0402C firmware

Adata Premier Pro SP920 512GB with MU01 firmware

Corsair Force Series GT 240GB with 1.3.2 firmware

Corsair Force Series LS 240GB with S8FM07.9 firmware

Corsair Neutron Series 240GB with M206 firmware

Corsair Neutron Series GTX 240GB with M206 firmware

Corsair Neutron Series XT 240GB with SAFC00.e firmware

Crucial MX100 256GB with MU01 firmware

Crucial MX100 512GB with MU01 firmware

Crucial M500 240GB with MU03 firmware

Crucial M500 480GB with MU03 firmware

Crucial M500 960GB with MU03 firmware

Crucial M550 256GB with MU01 firmware

Crucial M550 1TB with MU01 firmware

Intel 335 Series 240GB with 335s firmware

Intel 520 Series 240GB with 400i firmware

Intel 730 Series 480GB with L2010400 firmware

OCZ Vector 150 256GB with 1.1 firmware

OCZ Vertex 450 256GB with 1.0 firmware

OCZ Vertex 460 240GB with 1.0 firmware

OCZ ARC 100 240GB with 1.0 firmware

SanDisk Extreme II 240GB with R1131

Samsung 830 Series 256GB with CXM03B1Q firmware

Samsung 840 Series 250GB with DXT07B0Q firmware

Samsung 840 EVO 250GB with EXT0AB0Q firmware

Samsung 840 EVO 500GB with EXT0AB0Q firmware

Samsung 840 EVO 1TB with EXT0AB0Q firmware

Samsung 840 Pro Series 256GB with DXM04B0Q firmware

Samsung 850 EVO 250GB with EMT01B6Q firmware

Samsung 850 EVO 1TB with EMT01B6Q firmware

Samsung 850 Pro 512GB with EXM01B6Q firmware

Seagate 600 SSD 240GB with B660 firmware

Power supply Corsair Professional Series Gold AX650W
OS Windows 7 Ultimate x64

Thanks to Asus for providing the systems’ motherboards and graphics cards, Intel for the CPUs, Corsair for the memory and PSUs, Thermaltake for the CPU coolers, and Western Digital for the Caviar Black 1TB system drives.

We used the following versions of our test applications:

Some further notes on our test methods:

  • To ensure consistent and repeatable results, the SSDs were secure-erased before almost every component of our test suite. Some of our tests then put the SSDs into a used state before the workload begins, which better exposes each drive’s long-term performance characteristics. In other tests, like DriveBench and FileBench, we induce a used state before testing. In all cases, the SSDs were in the same state before each test, ensuring an even playing field. The performance of mechanical hard drives is much more consistent between factory fresh and used states, so we skipped wiping the HDDs before each test—mechanical drives take forever to secure erase.

  • We run all our tests at least three times and report the median of the results. We’ve found IOMeter performance can fall off with SSDs after the first couple of runs, so we use five runs for solid-state drives and throw out the first two.

  • Steps have been taken to ensure that Sandy Bridge’s power-saving features don’t taint any of our results. All of the CPU’s low-power states have been disabled, effectively pegging the 2500K at 3.3GHz. Transitioning in and out of different power states can affect the performance of storage benchmarks, especially when dealing with short burst transfers.

The test systems’ Windows desktop was set at 1280×1024 in 32-bit color at a 75Hz screen refresh rate. Most of the tests and methods we employed are publicly available and reproducible. If you have questions about our methods, hit our forums to talk with us about them.

 

Conclusions

Before we weigh in with our final verdict, we’ll bust out a few of our famous value scatter plots. These plots use an overall performance score compared against a common baseline. This score is based on a subset of the performance data from our full suite, with CrystalDiskMark’s sequential transfer rates substituted for older HD Tune scores. (More details about how we calculate overall performance are available here.)

We’ve mashed up the overall scores with per-gigabyte prices from Newegg. (Samsung’s suggested retail price was used for the 850 EVOs, since they’re not selling online as I write this.) The best solutions will gravitate toward the upper left corner of the plot, which signifies high performance and low prices.

Solid-state and mechanical storage have vastly different performance and prices, and those disparities make the main plot a little busy. Click the buttons below the plot to switch between all the drives and a cropped look at just the SSDs—and keep in mind that we’ve trimmed the axes for the SSD-only plot. Unfortunately, the plot with all the SSDs is just too crowded to have individual labels for each one.


Our plots nicely show the dense band of SSDs with similarly outstanding all-around performance. The 850 EVOs are well-positioned within this upper echelon, which is new territory for the 250GB model. The EVO family’s 1TB predecessor is also part of the leading pack, but the old 840 EVO 250GB lags behind overall. Credit V-NAND’s superior write performance for elevating the lower capacity to new heights.

The 850 EVOs are likely to drift to the left once they’re added to the endless rotation of SSD sales. Their value proposition isn’t entirely contingent on lower pricing, though. A high endurance rating, long warranty, robust encryption support, and slick software all contribute to a strong overall package. Apart from the fact that sustained write workloads will saturate the SLC cache, the EVO doesn’t really have any weaknesses.

In a sense, the 850 EVO feels like TLC’s destiny. Three-bit flash has always been dogged by the performance and endurance compromises that come along with the extra bit, but those weaknesses are neatly balanced by the benefits of V-NAND’s 3D goodness. The 850 EVO is clearly fast enough to keep up with consumer-grade SSDs based on planar MLC NAND, and it’s also rated to outlast them.

V-NAND is obviously faster and more durable with two bits per cell, but that configuration is overkill for most consumer SSDs. There’s little point to higher speeds when the 6Gbps interface and clunky AHCI protocol are the main storage performance bottlenecks. Good luck exceeding the 850 EVO’s endurance spec with a typical client workload. This is more SSD than most people need.

Only time will tell whether users will flock to the 850 EVO like they did to the original, but the new model is definitely a worthy sequel—and TR Recommended.

Comments closed
    • neblotr
    • 5 years ago

    Hmm, Guess the question now is when will the competitors release their latest iterations to go up against samsung’s latest consumer model? In all reality I’m just an enthusiast 🙂 enjoyed going through the destruction test for the 840 evo (loved it so much I replaced my drive over the summer and dad’s for christmas) and look forward to seeing if the apparently different internal structure contributes to increased overall reliability/longevity of the drive (maybe this one makes it to 1.5pb? 🙂 (Well, I guess the only question is, when will tech report destroy a drive for us? 😉

    On the other hand, I’m considering OWC drives, solely because of the higher grade controller that nullifies TRIM (Say what you will about it already being obsolete, but I saw drive issues on the 840 evo within a week when I upgraded my OSX to Yosemite, they disabled kext signing and in effect TRIM on third party drives, almost immediately after I got up the courage to crack open a $1500 laptop…Long story, lot’s of tears from what i can imagine are the 1% of hardware inclined apple users (near extinction). Doing that would allow me to set up a RAID setup between one of their drives and the 840 EVO I’ve got.

    Till then I’m just going to run ole mavericks and use 3rd party hardware (not that there’s an alternative, apple doesn’t make their own anymore) to upgrade, while quietly giving Apple and Cook the finger.

    Ignore the following, it’s purely cathartic rant:
    On a more ranting side of things: my college now requires all students to strip off watches in the test center because of smart watch crazy (apparently flunkies they staff are too stupid to spot check the nursing student wearing a battle scarred Gshock that shops @ Goodwill, smh @ incompetence)

      • neblotr
      • 5 years ago

      Looks as though the 850 is taking over the 840 with a vengeance. 236 reviews on amazon in 61 days, 10+/day for the last 2 weeks. Not sure if the internet content creator 1% rule applies to amazon reviews but impressive sales #s if it does, price is down to $108 for the 250gb (only blackfriday 2014 sales were lower than that on the 840 and only by 10-15$) lowest recorded price yet, if this continues Ill be forced to pull my optical drive and toy around with RAID 😀

    • 6GTX9
    • 5 years ago

    Out of curiosity, where does Sandisk’s Extreme Pro line up in the charts and how does it compare to the 850 EVO?

      • continuum
      • 5 years ago

      Anand finds them very close. In fact they’re the top two high-end (enthusiast and professional) SSD’s they recommend… at least for SATA.

    • DarkMikaru
    • 5 years ago

    So now that we’ve clearly established that pretty much any 240 – 256GB SSD you purchase will give you lightning performance I humbly suggest a 120GB Budget Showdown Bonanza!!

    Why? Because that information would be crazy useful to many of us who build / upgrade systems on tight budget. 120GB SSD’s have gotten so cheap now I include them as Defaults in all system builds, short of it absolutely not fitting in the budget. But most of the time I can convince anyone of the infinite speed benefits for a mere 59 dollars.

    Next, the performance can vary wildly. And that is information buyers would find useful. Example: Kingston V300’s should be avoided if you plan on using them to write large files (ISO’s, HD Rips, Backup Images) due to there write speed being ridiculously slow. The OCZ Arc 100 on the other hand gives 300+ Write & Read regardless of the workload. So at 59.99 I’d take the OCZ over the Kingston any day.

    Silicon Power also pulled a Kingston by changing on the NAND on their drives as well. First few I bought gave me 320 Read / 180 Write fairly consistently. The next batch was 210 Read / 130 Write…. Firmware numbers where different, just like what Kingston tried to pull. Anyway… just a thought. I’d love to see a budget roundup. Cause from what it looks like to me… there’s little to know difference in the higher end offerings.

    • TheMonkeyKing
    • 5 years ago

    i know the endurance test is ongoing and is showing most of the drives going way beyond the recommended lifespan of writes/rewrites, so I am wondering if it would be helpful to show the mortality process?

    More specifically, how do we know what happens when it dies? Does it brick itself after a set number of writes, percentage of cache exhausted? Does it set itself in read-only mode to allow a user to copy data to a new host?

    Yes, I know the mechanical drives rely on SMART warning and such and most can go bad without any warning, but the SSD is different beast all together and should have some newer and more reliable concepts of detailing a death watch or aiding in recovery, yes?

    • ronch
    • 5 years ago

    Kinda wish I waited a few months more before grabbing my 250GB 840 Evo, as prices tumbled roughly 30% about 5 months after I got it. And now this. Barely a year has passed and my 840 Evo is starting to look pretty unexciting. Oh well. I’ve been planning to hold on to it for at least 3 years so it WILL inevitably fade into obscurity sooner or later.

    • nico1982
    • 5 years ago

    [quote<] if the implementation is the same as in the 840 EVO, the 1TB drive has a 9GB cache, the 500GB has 6GB, and the others have 3GB[/quote<] What happens when the drive is partitioned?

      • buletov
      • 5 years ago

      Partitioning a drive is a rather high-level (logical) operation. This cache is abstracted on a much lower level, and completely managed by the drive itself. Additionally, flash drives do not expose their storage in a linear fashion like most traditional mechanical drives*. Thus, this SLC cache will be fully utilized by the drive regardless of the partition one is writing to. This also explains the futility of using a defragmenter on the SSD drive – you would ‘defragment’ logical positions of the files, and not the psychical ones – which is the whole point (to make files load faster by reducing time spent on drive head movement).

      * – Even tho magnetic drives also manage it to a certain level, to account for blocks that have lost their magnetic properties. But the space is mostly mapped 1:1 in relation to a logical vs. physical location.

      • Dissonance
      • 5 years ago

      The cache is stored in a portion of the flash that’s inaccessible to the user. Partitioning the drive shouldn’t change the size of the TurboWrite buffer.

    • anotherengineer
    • 5 years ago

    “The test systems’ Windows desktop was set at 1280×1024 in 32-bit color at a 75Hz screen refresh rate.”

    Hmmm a 1280×1024 @ 75Hz refresh rate, are you using a 17″ CRT as a monitor with VGA input??

      • Dissonance
      • 5 years ago

      Nah, that config is based on an old Samsung 17″ LCD that’s since been retired. We use the same resolution and refresh rate to keep everything apples-to-apples with the new displays.

      • Klimax
      • 5 years ago

      Space-wise still better then current 1080 monitors which will eat up space without any return for it. The only apparent salvation are 4k monitors. Otherwise current selection of LCDs is one of the worst I saw. (Maybe only beaten by LCDs when they got introduced…)

    • flip-mode
    • 5 years ago

    [quote<]This is more SSD than most people need.[/quote<] I don't read every SSD article TR published, so I could have missed it before, but this is the first time I have seen one of TR's editors express this sentiment, and I think it is a very fair thing to say. I think "most people" would be plenty satisfied by just about any SSD out there. I'm plenty satisfied by an old Samsung 830 SSD. All I want now is more capacity. Honestly 2TB seems to be my sweet spot - that's enough for OS and all files to fit on one drive and get backed up to another. Wake me when I can get a 2TB SSD for $200-ish - will that be any time soon? I think (hope) that day is coming within the next few years. It is conceivable that I will never by another mechanical drive for my personal computer again, if my current drives last long enough for SSD prices and capacities to reach the right point for me. TL;DR: keep the capacities rising and the prices falling!

    • strangerguy
    • 5 years ago

    Welcome to the “good enough” commoditization of SSDs where real world performance for 99% of users is so close that it can be said all are exactly the same, thus price is now the only main consideration to decide a purchase, which means the MX100.

      • dmjifn
      • 5 years ago

      Yeah, price… in line behind “sufficient capacity”, “form factor”, and “trust”. I definitely agree that once you’ve narrowed down the field to those drives with the right GBs, slot type, and that you don’t feel squeamish about then price is the only main consideration.

    • Wall Street
    • 5 years ago

    Props to the Techreport for being one of the only sites to show real world Windows boot time and level load time benchmarks. Too many sites now only review synthetic benchmarks. I just bought a Sandisk Ultra II, and it is hard to judge based on reviews just how much slower mainstream drives like the Samsung Evo, the Ultra II or the MX 100 are than the premium drives like the Samsung 850 Pro, Extreme Pro or M550. Nice to see that the massive money savings really only means a couple of tenths of seconds in the real world daily workloads (or game-loads as the case may be).

      • MadManOriginal
      • 5 years ago

      The only worthwhile sites that do lots of SSD reviews with meaningful real-world stuff that I know of are Techreport and Anandtech. Xbitlabs also does worthwhile reviews, but they are less frequent.

        • Visigoth
        • 5 years ago

        Agreed. Also, X-bit Labs seems awfully quiet the last few months…maybe they’re shutting down?

          • MadManOriginal
          • 5 years ago

          Things aren’t so great in Russia these days :/

      • Krogoth
      • 5 years ago

      For mainstream applications, load time is CPU-bound (Clockspeed) on SSD.

      You need go to professional-tier applications to notice any difference with SSDs.

    • dmjifn
    • 5 years ago

    I’ve been wondering if I’d feel remorse for getting the 840 EVO 1TB on BF. But once you consider BF was $0.35 / GB, it looks REAL GOOD on that scatter plot.

    Signed,
    Happy consumer

      • bwcbiz
      • 5 years ago

      Yeah, the 840 EVO looks pretty good. You only get a 3-year warranty instead of 5 years, and a slight performance ding, but the price is only about 2/3 as much.

        • dmjifn
        • 5 years ago

        The semi-irony of that is that this would be the first drive where that would matter to me. Warranty’s been basically a vote of confidence from the company. None of the SSDs I’ve had to date have been ones I intended to have for more than 2 years. By the time a 128GB drive died on me, I would probably have no interest in replacing it with *another* 128GB drive. The 1TB EVO on the other hand is first one I’m hoping to have in service for the long haul.

        Which makes the fact that I got one that [url=http://www.neowin.net/forum/topic/1225419-ssd-whines-when-under-load/<]whines[/url<] and [url=http://forums.anandtech.com/showthread.php?t=2362022<]drones[/url<] a bit annoying!

          • MadManOriginal
          • 5 years ago

          This is a good point. Although a few recent games have bloated to huge size, I do feel that even for gamers, the 500GB-class size is more than enough for some time unless you install or leave installed games you aren’t playing. For general users, even 120GB-class is enough space, and 256 is plenty; supplemented by a spinny drive for mass storage if needed.

          If I bought a 500GB-class SSD now, I would expect to be using it for quite a while. I am still trying to hold off until a full platform upgrade thgouh, with NVMe goodness built-in.

    • HisDivineOrder
    • 5 years ago

    Remember when TLC was going to bring us lower prices.

    Them were the days. I remember I actually believed that line. In fact, cheaper prices came not from TLC, but from MLC-based products. Somehow, Samsung’s convinced even TR that TLC-based drives can be better than MLC drives and that’s a feat, I think.

    Reminds me of the people who swear by TN-based monitors no matter how bad they are. They just gots to have ’em.

    MLC, IPS. Golden standards to live by. TLC should be in value-priced drives that hit record lows. Anything less and, well, you just got conned.

      • HERETIC
      • 5 years ago

      Kind of agree in a way-but,had a sales manager who got upset with me when i said he’d ripped
      off a customer.His reply-If a customer is happy with his purchase he hasn’t been ripped off.
      Modern day example- i phone customers happy happy happy to pay $800 for a $200 phone.
      .
      Think Samsung will have a three tier approach with 850 Evo in the middle until yields increase
      and 850 Evo becomes more profitable than the 840.Then the prices will drop.
      Also depends on what volume Samsung is able to pump out…………………

      • f0d
      • 5 years ago

      i got a great price performance drive when i got my 840 evo, there wasnt anything as cheap as it or as fast as it when it came out (this is in australia im talking about) the mx100 wasnt out and many of the other competitors wasnt available to me

      even now its pretty high up in the benchmarks compared to newer drives and flash endurance isnt a problem going by the tests that tech report did – im never going to write as much as they did when they started having problem with the drive, it will be retired and probably replaced with a 2tb ssd in 2017 or something
      i havnt even written 2TB to mine yet let alone around 300TB when the TLC 840 started to have problems in the tech report tests

      also nothing wrong with TN panels as even scott mentions in the last podcast, imo a 144hz lightboost is way better for gaming than any ips panel – sure if i was doing some kind of professional work or photoshopping i would get a ips but i game with my pc and i never look at the screen from any angle other than head on so the angle thing isnt an issue for me at all

    • SuperSpy
    • 5 years ago

    Is the ‘Test notes and methods’ page supposed to be at the end of the article? It’s page 6 instead of the normal page 2.

    • Takeshi7
    • 5 years ago

    You need to use more contrasting colors in your graphs. The IOMeter graph just looks like a ton of blue lines And I can’t tell which color is which because they are all so close together.

    • willmore
    • 5 years ago

    [quote<]... greater "hardware automation" introduced with the MEX generation likely lessens the need for additional general-purpose horsepower, as well.[/quote<] Should that be MGX?

      • Dissonance
      • 5 years ago

      Nope. The automation was introduced with the previous generation. The MGX just drops a general-purpose core from that implementation.

        • willmore
        • 5 years ago

        Then that doesn’t make much sense. If the automation was added in the same generation where they added an extra core, why did they add the extra core? Maybe it was a contingency? For example, if the added hardware automation didn’t work, they had that extra core to do it in software instead?

          • Dissonance
          • 5 years ago

          MEX just introduced hardware automation, not the third core. Samsung’s SSD controllers have been triple-core since at least the 830 Series.

            • willmore
            • 5 years ago

            Okay, that makes perfect senese, then. Thanks for the followup.

    • GTVic
    • 5 years ago

    [quote<]It can also exploit the inherent robustness of the trapping oxide to program the cells more aggressively—or write less aggressively to extend the life of the flash.[/quote<] Can the user control how aggressively their bits are written?

      • Dissonance
      • 5 years ago

      Nope. SSD makers keep those dials to themselves.

    • drfish
    • 5 years ago

    Awesome stuff – but I just don’t see myself upgrading from my existing 830s at home until I build a completely new rig and get setup with M.2.

      • DPete27
      • 5 years ago

      Amen to M.2

      • albundy
      • 5 years ago

      i’m in the same boat. i wont be buying anymore SSDs in the future. next upgrade will also be an M.2 drive. it would be nice to save a 3.5″ slot for an HDD. i was disappointed to not see the Sandisk Extreme Pro in this review.

    • wierdo
    • 5 years ago

    850 Evo’s looking good, but the MX100 and M550 are still mighty impressive on that price/performance chart. Looks like things are gonna get interesting.

    I hope this leads to fierce price competition soon, would love to pick myself up a 500gb SSD this year, would be great if we reach ~0.30-35 cents/gb before then.

      • DPete27
      • 5 years ago

      If you’re in the market for 500GB+ SSD’s…sure the MX100 and M550 are good, but for the majority of customers that are likely to buy a 240-256GB SSD, they’re awful in comparison. For that reason, I dislike the MX100 and M550 because to the uneducated buyer, they’re almost a borderline marketing scam: The 500GB variants get reviewed and get the reputation, but customers buy the terribly performing (compared to the majority of other SSDs) 256GB ones.

      Yes, smaller lith NAND is making this performance disparity more common as of late, but things like caching on the 840/850 EVO, Sandisk’s Ultra II (and others I’m sure) that aim to level the playing field for smaller capacity drives with less parallelism are a HUGE show of good form from manufacturers IMO.

        • wierdo
        • 5 years ago

        I don’t know, would the average user coming from spinning drives really complain or even notice the difference between the 250 and 500 drives? They’re both gonna blow away the old medium.

        Even we, knowing there’s a difference, would in most cases not notice it in daily use imho, so I wouldn’t call it a scam, but rather typical market segmentation. Maybe the 120gb ones could be on the borderline though, too much of a sacrifice for my taste.

        But yes that’s why I went with 500 as the target, sure it might not be a big deal but I’d rather not cut corners or my geek-OCD will drive me crazy about it.

          • UberGerbil
          • 5 years ago

          Yeah, the transition from HD->SSD is so much greater than the differences among SSDs it really doesn’t matter. Especially with nothing else to compare it to.

          This summer I put a 250GB MX100 into my Aunt’s computer with no regrets. It’s old enough it doesn’t even have SATA3, so it’s not like the SSD itself is going to be the problem. (It’s also on Vista, so I’ll have to TRIM it manually when I visit next summer, but I’ll probably be putting her on Windows 10 at that point anyway).

        • MadManOriginal
        • 5 years ago

        That applies only to the MX100, FYI. The M550, unlike the M500, has fully populated channels at 256GB.

      • Ninjitsu
      • 5 years ago

      Yeah, just popped a 512GB MX100 in dad’s 2010 Macbook pro, from a 256GB HDD that was starting to feel quite sluggish. Also upgraded the RAM from 2x2GB to 2x4GB.

      Cloned drive, went fine, boot times fell from 1-2 mins after POST to 20s. Disk wouldn’t verify, though, so I reset the PRAM (first time since we got the laptop).

      POST times fell from about a minute to a few seconds, disk got successfully verified and all is awesome.

      • MadManOriginal
      • 5 years ago

      They are, but that chart doesn’t reflect street or perpetual sale prices. When you actually look at SSD prices for purchase, the Crucial ones are reasonable, but nothing mind-blowing like the chart would make you think. Just take the performance of an SSD, and move the data point left or right depending upon the purchase price.

      I do ever so wish TR would make the charts dynamic, and pull the data from Newegg (or maybe best price from a handful or sites) real-time when possible. Basically make it a mini PCPartsPicker.

    • anotherengineer
    • 5 years ago

    With 900GB+ drives being under 50 cents/gig. I think it’s time for TR to do a roundup/shoot-off of all the drives in the 900GB-1TB range.

      • SomeOtherGeek
      • 5 years ago

      Bumped cuz I think this is important. These drives are bigger therefore it will take long to use it up hence the need for endurance testing. Pretty please with sugar on top?

      • NeelyCam
      • 5 years ago

      Yes! In fact, I’d appreciate it if 500GB drives were included as well

    • Chrispy_
    • 5 years ago

    Looks solid.

    I’m just not that sold on TLC NAND since I’m suffering from the 840-series performance bug which (for vanilla 840 drives) is still unresolved. It seems to affect all of Samsung’s TLC products and they don’t seem to be treating it as an important issue.

      • kuraegomon
      • 5 years ago

      I upvoted you because it’s definitely a valid question, but I’d guess that it’s very unlikely to affect the 850 EVO for two reasons:

      – The firmware is likely an evolution of the 840 EVO codebase, which already has the bug fix.
      – The NAND in the 850 is so different – and as Geoff pointed out, 3D V-NAND is pretty much a perfect match for a TLC implementation.

      I’m definitely going to replace my current SSD configs with 850 EVOs, once they’ve been in the wild for a few months.

        • Chrispy_
        • 5 years ago

        I’m sure they won’t have the same TLC bug, but it’s a blight on Samsung’s otherwise decent record and they don’t seem in any hurry to fix it for the hugely-popular vanilla 840 or any of their OEM drives with the same TLC old-data issues.

        What if there’s a 3D V-NAND issue and they take months to fix it? Intel still set the benchmark for acknowledging problems and delivering complete solutions to their problems in record time.

        edit:
        Yeah, I guess I was specifically raising TLC as an issue but actually I was more concerned that Samsung are adding even more complexity to TLC without having fixed problems with existing TLC drives.

      • smilingcrow
      • 5 years ago

      It seems presumptuous to say Samsung aren’t taking the issue seriously just because they don’t have a fix available. It may be unsolvable in which case we will see what they are made of.

      • dmjifn
      • 5 years ago

      That’s a pretty good point, IMO. There’s a vanilla 840 in my wife’s machine and I intended to run the restoration tool on it sometime soon, completely glossing over the fact the fix was for the EVO only. While I think Samsung is probably taking it seriously, the fact they haven’t fixed it may mean they won’t or can’t due to the particular controller (assuming it’s different). Maybe I should put my old Toshiba in there and sell the Samsung instead.

      • strangerguy
      • 5 years ago

      With the MX100 512GB now going under $200 I wouldn’t bother with any of the Samsung TLC drives. Especially when the MX100 has power loss protection and MLC NAND.

        • MadManOriginal
        • 5 years ago

        MX100’s ‘power loss protection’ is a misperception, or misunderstanding, that is perpetuated by Micron’s simplified use of the terminology.

        To quite Anandtech
        [quote<]In the MX100 review, I was still under the impression that there was full power-loss protection in the drive, but my impression was wrong. The client-level implementation only guarantees that data-at-rest is protected, meaning that any in-flight data will be lost, including the user data in the DRAM buffer. In other words the M500, M550 and MX100 do not have power-loss protection -- what they have is circuitry that protects against corruption of existing data in the case of a power-loss.[/quote<] You can read half way down the page here: [url<]http://www.anandtech.com/show/8528/micron-m600-128gb-256gb-1tb-ssd-review-nda-placeholder[/url<] So, while it is a decent feature to have, it is not full power loss protection as people think of it.

Pin It on Pinterest

Share This