Subject: Storage | March 28, 2013 - 04:15 PM | Jeremy Hellstrom
Tagged: SuperSSpeed, S301 Hyper Gold, ssd, slc, SandForce SF-2281
SuperSSpeed is mixing the performance and endurance of SLC flash storage with the lower cost of the SandForce SF-2281 in an attempt to bring the price of their SLC drive to an affordable level for the consumer. The mix seems a good idea as the reduced write latency of SLC flash may help to overcome SandForce's weakness when writing incompressible data. [H]ard|OCP's testing bears this out as the drive kept up with a larger Samsung 840 Pro, one of the current performance kings. You will pay for the privilege however as the 128GB drive currently retails for $250 as SLC flash is not cheap. Consider that in almost any casual usage scenario, you are never going to push this drive to its limits ... unless you are going to start your own Frame Rating machine.
"The SuperSSpeed S301 128GB SLC SSD brings SLC flash into the consumer market. The extreme endurance and excellent write performance makes for an interesting SSD powered by the SandForce SF-2281 controller. The Intel 25nm SLC NAND removes much of the Achilles heel of the SandForce processors, delivering consistent performance."
Here are some more Storage reviews from around the web:
- OCZ Vertex 3.20 – Vertex 3 updated to 20nm @ Bjorn3D
- OCZ Vertex 3.20 120GB Solid State Drive Review @ Pro-Clockers
- OCZ Vertex 3 .20 120GB SSD @ Tweaktown
- OCZ Vertex 3 .20 240GB SSD @ Tweaktown
- KingFast Ultra-Cache K13 & K25 SATA2 SSD Review @ ModSynergy
- Kingston V300 120GB SSD Review @ HCW
- Kingston V300 120GB SSD @ Bjorn3D
- Intel 335 Series 180GB SSD Review @ Hardware Canucks
- The SSD Review SSD Database Is Live
- ADATA DashDrive Air AE400 Wireless Storage Device @ Tweaktown
- Kingston DataTraveller Ultimate 3.0 G3 64GB USB3.0 Flash Drive @ Tweaktown
- Kingston HyperX Predator 512GB USB 3.0 Flash Drive @ Tweaktown
- QNAP TS-469L @ Legion Hardware
- G-Technology G-Drive Mobile USB 1TB USB 3.0 Portable Hard Drive Review @ NikKTech
- OWC Mercury On-The-Go Pro USB 3.0 Portable Enclosure Kit Review @ Madshrimps
- ADATA DashDrive HV610 External Hard Drive @ Tweaktown
- ADATA DashDrive Durable HD710 External Hard Drive @ Tweaktown
Taking an Accurate Look at SSD Write Endurance
Last year, I posted a rebuttal to a paper describing the future of flash memory as ‘bleak’. The paper went through great (and convoluted) lengths to paint a tragic picture of flash memory endurance moving forward. Yesterday a newer paper hit Slashdot – this one doing just the opposite, and going as far as to assume production flash memory handling up to 1 Million erase cycles. You’d think that since I’m constantly pushing flash memory as a viable, reliable, and super-fast successor to Hard Disks (aka 'Spinning Rust'), that I’d just sit back on this one and let it fly. After all, it helps make my argument! Well, I can’t, because if there are errors published on a topic so important to me, it’s in the interest of journalistic integrity that I must now post an equal and opposite rebuttal to this one – even if it works against my case.
First I’m going to invite you to read through the paper in question. After doing so, I’m now going to pick it apart. Unfortunately I’m crunched for time today, so I’m going to reduce my dissertation into the form of some simple bulleted points:
- Max data write speed did not take into account 8/10 encoding, meaning 6Gb/sec = 600MB/sec, not 750MB/sec.
- The flash *page* size (8KB) and block sizes (2MB) chosen more closely resemble that of MLC parts (not SLC – see below for why this is important).
- The paper makes no reference to Write Amplification.
Perhaps the most glaring and significant is that all of the formulas, while correct, fail to consider the most important factor when dealing with flash memory writes – Write Amplification.
Before geting into it, I'll reference the excellent graphic that Anand put in his SSD Relapse piece:
SSD controllers combine smaller writes into larger ones in an attempt to speed up the effective write speed. This falls flat once all flash blocks have been written to at least once. From that point forward, the SSD must play musical chairs with the data on each and every small write. In a bad case, a single 4KB write turns into a 2MB write. For that example, Write Amplification would be a factor of 500, meaning the flash memory is cycled at 500x the rate calculated in the paper. Sure that’s an extreme example, but the point is that without referencing amplification at all, it is assumed to be a factor of 1, which would only be the case if you were only writing 2MB blocks of data to the SSD. This is almost never the case, regardless of Operating System.
After posters on Slashdot called out the author on his assumptions of rated P/E cycles, he went back and added two links to justify his figures. The problem is that the first links to a 2005 data sheet for 90nm SLC flash. Samsung’s 90nm flash was 1Gb per die (128MB). The packages were available with up to 4 dies each, and scaling up to a typical 16-chip SSD, that only gives you an 8GB SSD. Not very practical. That’s not to say 100k is an inaccurate figure for SLC endurance. It’s just a really bad reference to use is all. Here's a better one from the Flash Memory Summit a couple of years back:
The second link was a 2008 PR blast from Micron, based on their proposed pushing of the 34nm process to its limits. “One Million Write Cycles” was nothing more than a tag line for an achievement accomplished in a lab under ideal conditions. That figure was never reached in anything you could actually buy in a SATA SSD. A better reference would be from that same presentation at the Summit:
This shows larger process nodes hitting even beyond 1 million cycles (given sufficient additional error bits used for error correction), but remember it has to be something that is available and in a usable capacity to be practical for real world use, and that’s just not the case for the flash in the above chart.
At the end of the day, manufacturers must balance cost, capacity, and longevity. This forces a push towards smaller processes (for more capacity per cost), with the limit being how much endurance they are willing to give up in the process. In the end they choose based on what the customer needs. Enterprise use leans towards SLC or eMLC, as they are willing to spend more for the gain in endurance. Typical PC users get standard MLC and now even TLC, which are *good enough* for that application. It's worth noting that most SSD failures are not due to burning out all of the available flash P/E cycles. The vast majority are due to infant mortality failures of the controller or even due to buggy firmware. I've never written enough to any single consumer SSD (in normal operation) to wear out all of the flash. The closest I've come to a flash-related failure was when I had an ioDrive fail during testing by excessive heat causing a solder pad to lift on one of the flash chips.
All of this said, I’d love to see a revisit to the author’s well-structured paper – only based on the corrected assumptions I’ve outlined above. *That* is the type of paper I would reference when attempting to make *accurate* arguments for SSD endurance.
Subject: Storage | July 3, 2012 - 12:21 AM | Tim Verry
Tagged: ssd, slc, server, sandisk, PCIe SSD, flash, enterprise, caching
Flash storage company Sandisk has recently jumped into the world of enterprise PCI-E caching SSDs – what they are calling Solid State Accelerators. Currently, they are offering a 200GB and 400GB model under the company’s Lightning PCIe series. The SSDs feature a proprietary Sandisk controller driving 24nm SLC NAND flash, a PCI-E 2.0 x4 interface, and maximum power draw of 15 watts.
The Lightning Accelerators use the NAND flash for Sandisk’s own foundry and offer a large performance boost for servers and workstations over hard drives and SATA SSDs. It is capable of 410 MB/s sequential reads or 110,000 IOPS. Further, when using 4KB and 8KB blocks, the drives can reach 23,000 and 17,000 read/write IOPS respectively. Other specifications include an average response time of 245 microseconds, and less than 30 millisecond maximum response times. The Solid State Accelerators also feature sustained read and write latencies as low as 50 microseconds.
Sandisk has built the drives so that they can be configured as boot drives, storage drives, or caching drives. The company supports up to 5 drives in a single system, for a maximum of 2TB of flash storage. In addition, Sandisk is offering up its Flashsoft software that allows the Lightning Accelerators to be used as caching drives on Windows-based systems. Unfortunately, that is an additional cost which is not included in the already pricey SSDs (good thing for corporate expense accounts!).
Speaking of pricing, the 200GB LP206M has an MSRP of $1,350 while the 400GB LP406M has an MSRP of $2,350. Both cards have five year warranties and a MTBF rating of 2 million hours. You can find more information on the Sandisk Website.
It will be interesting to see how this Sandisk accelerator stacks up to the likes of the Intel 910 and FusioIO drives! The FusionIO FX, for example, gives you 420GB of QDP MLC NAND for $2,495, which works out such that Sandisk has a slightly lower cost-per-gigabyte value and SLC flash. We will have to wait for some independant reviews to say which drive is actually faster, however.
Subject: Storage | May 3, 2012 - 08:10 PM | Jeremy Hellstrom
Tagged: TCS, Galatea Ultra-Rugged SSD, ssd, 100GB, slc, SandForce SF-1565
Just by their very nature SSDs are physically tough, with no moving parts like you find in platter based disks, so they are able to withstand much great acceleration forces ... or deceleration depending on how you look at it. TeleCommunication Systems is not a name you are likely to recognize when it comes to SSDs so you should take note of the Galatea Ultra Rugged SSD. The flash is just as tough, with 20,000 terabytes of write guaranteed along with 10 year data retention also guaranteed. Performance is also guaranteed thanks to the SandForce SF-1565 controller and Micron 25nm SLC flash. If there is an SSD likely to make it into orbit soon, this will probably be the one to do it. Check it out at SSD Review.
"This report covers the Telecommunications Systems (TCS) Galatea line of ultra-rugged SLC SSDs. Adhering to the MIL-STD-810 military specifications governing a multitude of ultra-ruggedized requirements, this SSD is designed for ultimate reliability in the harshest of environments. Designed and tested with the most hostile environments imaginable in mind, these SSDs are surely amongst the toughest storage mediums available."
Here are some more Storage reviews from around the web:
- Intel 910 400/800GB PCIe SSD Quick Preview - On The Bench and Pushing Out 1.9GB/s Performance @ The SSD Review
- Corsair Force Series 3 180GB @ Tweaktown
- Intel SSD 330 120GB / 180GB review @ Hardware.Info
- Intel 330 Series 120GB @ SSD Review
- ADATA Premier Pro SP900 (0-provision) 256GB @ Tweaktown
- Crucial Adrenaline 50GB m4 Cache SSD Review @ Legit Reviews
- Patriot Pyro SE 240GB SSD Review @ Hardware Canucks
- RunCore Pro V MAX 240GB @ Tweaktown
- Corsair Force GT 180GB SATA III SandForce SF-2282 SSD Review @ Hi Tech Legion
- MemoRight FTM Plus Slim 7mm 240GB @ Tweaktown
- Plextor M3P 256GB SATA 3 SSD @ SSD Review
- Crucial Adrenaline 50GB Solid State Cache Review @ circuitREMIX
- Kingston HyperX 3k 240GB SATA III SSD Upgrade Kit Review @ NikKTech
- Corsair Accelerator Series 60GB Cache SSD @ SSD Review
- Adaptec RAID 6805E RAID Controller @ TechwareLabs
- Western Digital VelociRaptor 1TB (WD1000DHTZ) Review @ TechwareLabs
- Synology DS212j, DS212, and RS212 review @ Hardware.Info
- 16 4- and 5-bay NAS devices roundup test @ Hardware.Info
- QNAP TurboNAS TS-259 Pro+ NAS Server Review @ NikKTech
- Hitachi 7K4000 / 5K4000 4 TB review @ Hardware.Info
- QNAP TS-879 Pro @ Legion Hardware
- Kingston Wi-Fi Drive @ Hardwarebistro
- Kingston USB-Flash Drive Roundup @ Rbmods
Subject: Storage | April 27, 2011 - 10:06 PM | Allyn Malventano
Tagged: tlc, ssd, slc, ocz, mlc, flash
A while back, Intel and Micron jointly announced the beginnings of 20nm flash memory production, promising a 50% increase in die count per wafer (or a 50% reduction in per die production cost, depending on how you slice it). This shrink only did just that - shrink the die. Capacity remained at 64Gbit (8GB).
A few days ago IMFT also announced another way to shrink that die, but this time keeping with the now 'old' 25nm process. It turns out they have refined 25nm to the point where consumer-grade TLC flash can be produced. TLC is Triple-Level-Cell. While SLC (Single) holds 1 bit per cell, and MLC (Multi) holds two, TLC holds 3 bits per cell. Compared to the MLC 25nm dies, this gives a capacity increase without changing much else. IMFT, however, is happy with the 8GB 'sweet spot', so instead of jumping to a 12GB die of the same physical size, they are opting to instead shrink the current 25nm die to 131mm^2.
25nm TLC die, same 8GB capacity, but less area than the 25nm MLC die.
This gives Intel and Micron two options for ultimately reducing the price of flash - either by shrinking the process and getting more 8GB MLC dies out of a 20nm wafer, or by squeezing more bits into each cell of existing 25nm flash.
This is good stuff. Let's hope it gets even more SSD's into even more machines this holiday season.