Recently, Enterprise Storage Forum published an article by Henry Newman in which he argued that lithography limits and disk drive density are going to keep solid state disks (SSDs) from replacing spinning disks. To help explain his argument, I’m going to outline why one of the keys to this equation, SSD density, is in grave danger of stopping next year.
SSD Technology Review
Between the floating gate and the substrate is the tunnel oxide – the barrier to the floating gate through which the electrons "tunnel" into the floating gate. The transistor either has electrons tunneled into the floating gate (indicating a logical 0) or does not have any electrons tunneled into the floating gate (indicating a logical 1). The process of forcing electrons into or out of the floating gate, called Fowler-Nordheim Tunneling (F-N Tunneling), is achieved by applying a voltage between the control gate and the source or drain. When the charge is removed, the floating gate either retains the electrons (if they were tunneled into the gate) or has no extra electrons if they were removed. This allows Flash memory to retain values after power is removed.
To program (write) to the transistor, which creates a logical 0, a positive voltage is applied to the drain which activates the electrons underneath the floating gate in the substrate. Then a larger positive voltage is applied to the control gate forcing the electrons to tunnel into the floating gate.
To erase the transistor, or to remove the extra electrons, a negative voltage is applied to the control gate and a positive voltage is applied to the source. This forces the electrons out of the floating gate and into the source.
To read the transistor, a positive voltage that is much lower than the write voltage is applied to the control gate. An additional positive voltage, also lower than the write voltage, is applied to the drain. The current between the source and the drain will determine if the floating gate has extra electrons (logical 0) or does not (logical 1).
This is the basic concept transistors use to store data in the SSD. Constructing SSDs from NAND is a bit more challenging and something like assembling a pyramid of pachyderms.
Creating NAND Flash Units
With NAND Flash, the floating-gate transistor is used as the basis for SSDs. The first step is to daisy-chain the transistors (gates) in series. Typically 32 gates are chained in series. These groups are connected in a NOR style where each line is connected directly to ground and the other is connected to a bit line. This arrangement has advantages for cost, density, and power as well as performance but it is a compromise that has some implications.
A number of these groups are then combined into pages (or sub-pages). The typical page is 4KB in size. The pages are then combined to form a block. A block, illustrated below in Figure 2, is typically formed from 128 pages giving a block a size of 512KB.
The blocks are combined into a plane. Typically a total of 1,024 blocks are combined into a plane, giving it a typical size of 512MB as show in Figure 3.
Typically there will be multiple planes in a single NAND Flash die. Manufacturers will also put several dies into a single NAND Flash chip. Then you can put multiple chips in a single drive.
Constructing drives is fairly straightforward is not dissimilar to creating memory DIMMs. But there are a number of issues that need to be addressed for SSDs to be successful and, perhaps more importantly, these issues are particularly sensitive to the lithography size.
Performing I/O Operations on SSD's
One of the coolest things about SSDs is that they don’t contain spinning media, which greatly reduces latencies and increases potential throughput. Reading, writing, and erasing are all done electrically as opposed to spinning media, where a large part of the latency is due to mechanical movement of the read/write heads and waiting for the particular block to spin around to the right spot. With SSDs, voltages are applied to the chips to cause an I/O operation . However, everything is not as easy as it seems.
Recall that the transistors are connected in series. To measure the state of any particular cell, all cells in the series have to be in a conductive state. This is accomplished by applying a bias voltage of +5V that is high enough to turn on all the gates in the series so that the particular cell that has the desired data can be read reliably enough, or written to (programmed), or erased.
The details of the read process are a bit involved and beyond the scope of this article, but it begins by applying the +5V bias voltage. Then a 0.5V voltage is applied above the bias voltage to read a particular cell. Notice that the bias voltage is a factor of 10 greater than the voltage needed to read the cell.
Writing to the cells is similar to reading, but the voltages are much higher. For writing or erasing to cells the voltages can be as high as 20V.
An important observation is that to read, write, or program a particular cell, the +5V bias voltage has to be applied. This is much larger than the read voltage of 0.5V but not as large as the program voltage (20V). Even more important is that the bias voltage is applied to all cells in the line (series) even if only one cell in the series is to be used. For example, to read one cell, a voltage 10 times greater than the actual read voltage has to be applied to all gates in the line. Moreover, typically there is never just a single line that is being read so almost all cells in the block are subjected to the +5V bias voltage. Over time, the electromagnetic (EM) field created by the bias voltage affects all cells, ultimately impacting the voltage level needed to program or write to the cell. In fact, it reduces the voltage level required to program the cell.
For a brand spanking new cell, the voltage required for programming is around 20V so that you can write to the cell or erase the data. But, over time, applying all the various voltages necessary for an I/O operation will impact the voltage required to program the cell.
Since not every cell has the same voltage applied at the same time, each cell will have its own individual required programming voltage. However, to accommodate the worst case, a programming voltage of 20V is applied every time. This can be bad for erasing data because the erase has to happen on a block level so all cells have to be subjected to the same voltage level (20V). This can cause the cells to actually push out more electrons than required for erasing. This phenomenon is sometimes referred to as "deep-erasing." If a cell is deep-erased then the next time it is programmed it may not have enough electrons to be measured correctly. This is compensated by a "verify" step of the write cycle that detects the problem and repeats the write cycle until the cell achieves the correct charge (number of electrons). But, having to do this reduces the performance of the SSD because it is just this one cell that does not have the correct number of electrons. Good SSD controllers can recognize this problem and deactivate the particular line on the page or deactivate the page and use a page from the "pool" of backup pages. There has even been discussion of using a lower program voltage as the block ages.
One can see that there are many aspects to making SSDs work correctly and repeatedly. One thing to remember is that without changes to the materials or the techniques for storing and retrieving data, the voltages and associated problems stay the same.
Data Corruption and Retention Issues
Potential SSD issues go beyond deep-erase problems. As a result of the voltages being applied to the cells, EM fields are created within the SSD. While designers have gone to great lengths to isolate cells from one another, the fields from one cell can extend to another. The effects of a field from a neighboring cell or line may have some impact on a particular cell. A fresh SSD will have cells that need approximately +5V for the bias voltage, 0.5V for a read voltage, and 20V for programming/erasing. But over time, the required voltage for programming a cell actually decreases. During programming, a cell will create a field large enough to perhaps change the properties of a neighboring cell. While designers go to great lengths to make sure that this doesn't happen or that the SSD can compensate for this happening, this phenomenon still occurs and can lead to silent data corruption.
The silent data corruption scenario is fairly simple – a cell has some voltage applied to it, a bias voltage or a program/erase voltage. The resulting field can disturb neighboring cells changing their properties. For example, the number of electrons in the cell can decrease or electrons can be tunneled into the cell. In either case, it's possible to change the value in the cell silently.
Designers are aware of this issue and have created techniques to prevent data corruption. However, these techniques cost money and no one wants to make SSDs more expensive. As a result, most SSDs are designed to meet JEDEC's data retention requirements meaning that a brand new SSD should be able to store data at least 10 years (when the SSD has more write/erase usage, the data retention time decreases). These requirements define how long data is to be retained without loss as a function of how many write/erase cycles have occurred (on average). Therefore SSD designers will include techniques designed to prevent data loss just beyond these data retention time spans. I can't criticize them for doing this – adding more measures would only increase cost and customers are already pretty sensitive to SSD pricing. However, it is important to realize that you can get data corruption on the SSD at some point.
One of the important questions to ask is what happens to the SSD as lithography reductions are used to build NAND devices?