Label Capacity Must Equal User Capacity
There’s nothing wrong with over-provisioning (reserving some of the NAND capacity for better performance and durability), but the drive label must state the capacity the user has access to. This is basic marketing honesty. The entire hard-drive industry got sued for this years ago and established standards for user capacity as a result. Micron follows these standards—we always market our drives at the true user capacity. In the case of the C300 and C400, the user capacities are identical—64, 128, and 256 GB (the C400 also offers a 512 GB).

Performance Must Not Degrade
We’ve taken a long-term view of the market; each new generation of drives must haveequal or better performance than the last. New NAND designs do present challenges, but because Micron leads NAND development, our SSD team has early insight into new products, and we start work early to make sure our SSDs make the best use of that NAND. The C400 is proof of that. As shown in the chart, it’s noticeably faster than the C300.

Keep Endurance High
SSD Enthusiasts are aware that new NAND designs start out at lower endurance cycle counts than the previous generation, and are sometimes wary of next-generation SSDs as a result. But cycle counts don’t necessarily translate 1:1 to drive endurance specs—good NAND management (via the firmware and controller) is the key.

We specify SSD endurance in total bytes written (TBW). The 25nm C400 offers the same endurance as the C300 for the 128, 256 and 512 GB models—72 TB TBW. This is equivalent to 40GB per day every day for 5 years, and far exceeds the patterns of any PC user. The 64 GB drive endurance is rated at 36 TB TBW—that’s 20 GB per day over the same time period, which still exceeds typical consumer use patterns.

We take the reliability of the C400 very seriously and have gone to great lengths to develop advanced firmware algorithms that manage the NAND. Again, being NAND developers gives us the unique ability to design end-to-end SSD quality as a complete system, alongside our NAND design team.

I hope you don’t let these early attempts at 25nm SSDs dampen your enthusiasm about this new technology. The SSD market is going to change dramatically in the next few years, and leading-edge NAND (and SSDs from the companies that make that NAND) is what will make it possible. Crucial’s M4 SSD will hit the shelves in mid-March. There’s a lot to be excited about; you’ll see proof in the C400/M4 reviews in a just a few weeks.

Of course the demo itself isn’t a novel concept by any means, but we think you’ll agree that results are staggering.

Visit crucial.com for more information.

Today, we have answers to those questions.

I’m happy to announce that Lexar Media will be carrying the C300 at www.crucial.com. Many of you already know Crucial as a reliable retailer of top-quality performance memory upgrades, so the RealSSD drive is a perfect addition to their high-caliber line of products. The details:
Where: www.crucial.com
Models: 2.5”, 128GB and 256GB
Availability: February

If you missed our benchmark videos, scroll through the blog history to see what all the buzz was about. Or just wait a few weeks for the first set of independent reviews—we’re confident that the C300 RealSSD drive will solidly establish itself as the SSD all others are compared to.

Of course, our immediate goal is to get these in the hands of independent reviewers. You should see third-party tests coming out in the next month or so as we ramp to production and get drives sent out. Stay tuned–we’ll call out results both here and through our @RealSSD Twitter feed.

AS SSD Benchmark: 3G Empty

AS SSD Benchmark: 6G Empty

We’re using the same Intel Core2Duo system, equipped with our 256GB RealSSD C300 drive and a 6 Gb/s SATA host bus adapter. We also test it at SATA 3 Gb/s to show how it will perform in those systems. I think you’re going to like the results.

System Details
MoBo: Intel® X48 chipset based
Processor: Intel Core2Duo E8500
Memory: Micron® 2GB DDR3 1066 (PC3-8500)
OS: Windows® 7 Pro 64-b

System Details
MoBo: Intel® X48 chipset based
Processor: Intel Core2Duo E8500
Memory: Micron® 2GB DDR3 1066 (PC3-8500)
Drive Interface: SATA 6Gb/s (via Marvel HBA)

The SSD group at Micron has done extensive research into the behavior of Windows XP and Windows Vista under different conditions.  To gather data, the SATA interface was analyzed and data captured while installing, booting, shutting down, and running Office productivity applications on both operating systems.

The results of this research show that XP and Vista do indeed handle their interfaces to an SSD differently. The main difference is XP does not align the data in the best way for an SSD.  Vista, on the other hand, does align the data.  These findings differ from other claims we’ve seen that Vista is somehow worse for an SSD.  In fact Vista is better for an SSD (incidentally, so is Windows Mojave). The example below illustrates the difference… By aligning the data and not partially filling NAND pages, performance is optimized for the SSD.

Click to Enlarge...

Another key difference between Vista and XP is that Vista enables background drive defragmentation by default. Defragmentation is totally unnecessary with an SSD and actually wears the drive out more rapidly. However, most OEMs will disable background defrag on systems that ship with SSDs and Vista.  So—if you happen to be buying a new SSD for the holidays, be sure defrag is off when you upgrade.  You don’t want to hold performance back by making your new SSD live in the HDD days-of-old.

In order to help folks better understand some of the claims out there, I thought I’d provide a quick overview on managing NAND on an SSD as well as some background on wear-leveling concepts.

First, understand that unlike DRAM and SRAM which can be read and written one word at a time, hard drives and SSDs are “block addressed” devices. The Logical Block on a hard drive or SSD is 512 bytes in size. On a hard drive, a given logical block is always on the same physical location region of the disk. On an SSD the relationship between physical and logical blocks is less direct due to endurance issues with NAND. If an operating system or program continuously addresses a limited number of logical blocks then those logical blocks will likely wear out before the rest of the NAND wears out.  That said, well-designed SSDs continually move logical blocks about the drive to minimize “hot spots” and reduce NAND wear.

Firmware running on the SSD controller takes care of these tasks in a process commonly referred to as wear-leveling.  Today all of the latest-generation SSDs implement complex wear-leveling schemes in an effort to efficiently utilize the available NAND cycles available.  Think of NAND memory on an SSD like a carpet in a house.  In a house with older carpet you will notice that the carpet becomes worn out in high-traffic areas but other areas like under furniture and the edges of the rooms the carpet is still new and unworn.  In this same house if the carpet was used evenly in all areas it would last much longer.  This is the same concept for an SSD—wear-leveling moves the high traffic areas evenly around the entire NAND array giving the SSD a much longer life.   Within the umbrella of wear-leveling there are a couple other concepts you will see in the industry—garbage collection and write amplification.

Garbage Collection

NAND has some constraints that are not ideal for use as a storage medium in a storage device like an SSD.  The storage area on a NAND device is broken into units called pages and blocks.  A page is typically 4KB in size and a block is a group of pages (64 to 128 pages to a block for today’s NAND devices).  In order to write data to a NAND device, it must be erased first.  The smallest unit that can be erased is a block. Once the block is erased the pages can be written one at a time until the block is filled.  It is undesirable to have to erase a block and move the data around on every single write that is received from the host because this process is slow—resulting in poor SSD performance.  The process is referred to as “read-modify-write”.  In order to avoid performing read-modify-write procedures, modern SSDs will keep a pool of blocks pre-erased and ready for new data.  When data is written to the same logical area repeatedly it is always written to a new physical area in the NAND. Along with the written data, a table that tells the controller where to locate the latest data is updated and the old locations are marked invalid.  At some point the drive runs out of pre-erased blocks and must re-claim the areas marked invalid by the firmware.  This process of reclaiming blocks is called garbage collection and SSDs must do it frequently or they will quickly run out of space.

To put this into an everyday example, imagine that you and your friends order two pizzas for dinner. The two pizzas arrive and soon everyone is busy moving slices of pizza onto their own plates. The only problem is there’s no room on the table for the requisite pitchers of beer. So you make the command decision to combine the remaining slices of pizza onto one pizza tray—creating new empty space on the table.  Your friends pour their beer and applaud your sheer brilliance…as a garbage collector!

Write Amplification

The amount of information written to the NAND is always greater than that written by the user because wear leveling and the garbage collection process generate some extra NAND writing.  Write amplification is a measure of the amount of data written to the NAND verses the amount of data written by the user to the SSD.    The objective of the firmware on the SSD is to be as efficient as possible to limit the extra NAND writes.

That said, there is a lot of misinformation about write amplification. All drives will have a worst case limit when the drive is nearly full. In this case, the write of a single 512byte logical block will result in at least one NAND page being written. With a page size of 4K the write amplification must, out of necessity, be 4kbytes/512bytes, for a write amplification of 8. However, most SSD vendors report something much closer to one, which would be the case for an empty drive and larger data transfer sizes.

So…next time you see new claims about SSD performance and endurance, keep these concepts in mind. They’re a good place to start judging whether they’re catching up or if you should be impressed.