Content: .......................................1By:www.bestsolidstatedrive.org .......................................................................................................1Content: ............................................................................................................................................2MLC vs SLC: Which flash SSD is right for you?...................................................................................2SSD installation tips...........................................................................................................................7KNOW SSD TRIM ......................................................................................................................11SSD vs HDD: Whats the Difference?...............................................................................................13 MLC vs SLC: Which flash SSD is right for you? As with any technology, there are trade‐offs, depending on which of the two types of flash SSD you select. Multi‐level cell (MLC) flash is most common and is often found in consumer‐grade products such as cameras, phones, USB memory sticks and portable music players but is also present in some enterprise storage products.
The main characteristic of MLC flash is its low price, but it suffers from higher wear rates and lower write performance compared with single‐level cell (SLC) technology. SLC is faster and much more reliable ‐‐ but also more expensive ‐‐ and is featured in the best‐performing storage arrays. In practice, however, the differences are not quite as clear as you may expect. To see how this technology is developing, its application and where it is heading, we need to look at how the two types of flash memory work and how they are sold. Storage sales discussions are not normally about the trade‐offs of MLC vs SLC, said Valdis Filks, storage technologies director at research firm Gartner. "This is normally hidden by implementation," he said. "In other words, its up to the enclosure manufacturer of the storage array, and its the controller thats more important than the underlying storage technology." MLC vs SLC head to head Vendors may prefer not to discuss the differences between the technologies, but understanding the underlying technology can influence deployment strategies. So, what are the key differences between MLC and SLC flash SSD? Sansung 840 use TLC FlashAll flash memory suffers from wear, which occurs because erasing or programming a cell subjects it to wear due to the voltage applied. Each time this happens, a charge is trapped in the transistors gate dielectric and causes a permanent shift in the cells characteristics, which, after a number of cycles, manifests as a failed cell. SLC uses a single cell to store one bit of data. MLC memory is more complex and can interpret four digital states from a signal stored in a single cell. This makes it denser for a given area and so cheaper to produce, but it wears out faster.
So, an MLC cell is typically rated at 10,000 erase/write cycles, while an SLC cell might last 10 times that before failing. However, manufacturers of products consisting of MLC cells can and do have ameliorating technologies and techniques at their disposal. According to Andrew Buss, service director at analyst firm Freeform Dynamics, amelioration techniques used by most vendors include wear‐levelling, which moves write cycles around the chip so that cells wear evenly; on‐device deduplication, which reduces the volumes of data written and so lowers wear; redundancy, which reserves a portion of the devices capacity to replace cells as they fail; and write optimisation, which stores data writes so they can be made in large chunks to reduce the number of write operations. The emerging term for MLC products that incorporate such techniques is enterprise MLC, or eMLC. Most such techniques are implemented in the device controller ‐‐ the interface between device and computer ‐‐ with companies such as SandForce and Intel among the most advanced in implementing such techniques, according to Buss. And despite the endurance issues related to SSDs, they remain, say vendors, more reliable than spinning media. Now we have to take one more technical step and take you right into the heart of what makes SSDs tick. (OK, they don’t tick per se. With no moving parts, SSDs are actually completely silent—another advantage over hard drives.) We said previously that SSDs use NAND flash chips. Within each of these chips are millions of cells. There are only two types of NAND cells today: single‐layer (SLC) or multi‐layer (MLC). An SLC cell can hold one data bit, yielding a value of either 0 or 1. An MLC cell can hold more than one, with today’s technologies generally yielding two bits per cell, yielding values of 00, 01, 10, or 11. Because you can fit four times as many possible values in a cell, the data density in MLC chips is higher. This is why MLC drives inevitably have higher capacities than their SLC cousins.
Vendor market share STEC, which sells 49.9 percent of all SSDs globally, according to Gartner, was the SSD product market leader in 2009 (Gartner was unable to break out UK figures). Fusion‐io, Intel, Texas Memory Systems, Samsung and Sun Microsystems follow with shares all below 9 percent. All the main storage array vendors include SSDs in their product offerings, pitching them as Tier 1 or Tier 0 in policy‐managed tiered storage systems. Use cases According to Filks, the implementation determines the technology. So applications such as high‐speed databases, whose performance is measured in terms of transactions per second, should be matched to the appropriate technology selected on the basis of price/performance. "Its about serving more customers in a given time. Thats what SSD vendors talk about," said Filks. Despite this, MLC and SLC tend to find themselves used for different applications, due largely to the four‐fold price difference per gigabyte between them. As we have seen, MLC can be found in consumer‐grade products but also in the enterprise where performance, while important, is not the primary consideration. When used in the same storage system, the two types of SSD can be tiered in the same way as tiering with spinning media; most storage product vendors include a form of automated SSD tiering, according to Buss. SLC typically tops the storage tier tree in financial services organisations, where high‐speed access to large databases is essential and price is a secondary issue. Buss said he sees future products
increasingly integrating and both flash SSD types and spinning media in performance/cost‐based tiers. Buss said, "Most enterprise applications will rely on a form of database and so will need SSDs. An example is content management systems, where an end user is waiting for things to happen; also Exchange servers, websites, media storage ‐‐ all of which you can use MLC for. However, you still need to do due diligence and buy appropriately. There are new solutions coming along to make MLC better." End‐user Roger Bearpark, assistant head of ICT at the London Borough of Hillingdon, has installed 520 GB of MLC‐based SSD‐based storage into his Compellent arrays. He said, "MLC is poorer on endurance and performance but is up to three or four [times] better on price. We got a phenomenal rate of return on investment by putting small amounts of active data on SSD, which produced a 13‐fold improvement in access times." Futures According to Filks, SSDs will not replace spinning disks. "Everyone says SSDs will replace disks ‐‐ maybe in about 15 to 20 years time ‐‐ but as SSD prices drop, so do those of disks. And SSD prices will never fall as far as disk because factories cant make enough. It means only the working data set needs to be on SSD, and thats about 5 to 15 percent of the total." However, Filks predicted that SSD could eventually replace tape as a deep archive technology because it offers similar benefits ‐‐ nonvolatility and zero power usage when not in use ‐‐ although this will take some 10 to 20 years. As prices fall and reliability techniques improve, it seems likely that MLC technologys price advantage will see it stay ahead of SLC for all but the most demanding of applications, as it remains significantly faster and more robust than spinning media.
SSD installation tips With more organizations opting for a DIY approach when it comes to installing solid‐state drives, here are a half‐dozen helpful tips to consider when debating whether to take such an approach with SSD installation in an enterprise environment. Determine which applications/workloads benefit most from SSD installation Latency‐sensitive applications with random‐access patterns benefit the most from performance‐boosting SSDs, and prime flash candidates include online transaction processing, email and virtual desktop infrastructure, according to Tony Palmer, senior lab analyst at Enterprise Strategy Group Inc. in Milford, Mass. "As organizations virtualize and host more applications on fewer servers, the I/O workload begins quickly to look much more random, so a small to midsize business with Exchange, SQL Server, SharePoint and other applications all sitting on one or two servers might benefit from SSD," Palmer wrote in an email. Dennis Martin, founder and president of Arvada, Colo.‐based consulting and testing firm Demartek LLC, said hard disk drives (HDDs) are fine with sequential reads and writes, whereas SSDs do well with random I/O patterns, including database updates and online analytical processing. He noted that Demartek tested email servers with SSDs and found the performance was significantly better than even the best hard drives could deliver. He said those that take the do‐it‐yourself approach could put an SSD in an email server either as the boot or the storage drive as long as they buy good‐quality drives with adequate capacity for all the email. "I think just about anywhere is a good place for an SSD," added Martin, noting that he "quite frequently boots a little VMware on [an SSD] and runs it from there." Gartner Inc.s principal research analyst Sergis Mushell recommended that IT shops choose applications or workloads that arent mission‐critical. He suggested putting metadata on SSDs to accelerate searches, or running highly read websites or pages with popular videos on SSDs. "While you get acceleration, your risk is minimal," Mushell said. "But as soon as youre getting into the primary storage mode and youre endeavoring into do it yourself, you could be dealing with environments which could be very highly risky for you." Research the major types of SSDs and form factors One of the limitations of SSDs is the wear‐out factor. Bits in a NAND flash block must be erased before data can be programmed or written, and the program/erase process eventually breaks down the oxide layer that traps the electrons, causing
NAND flash to wear out. Wear‐out projections differ for the three main types of NAND flash drives currently in use in enterprise scenarios ‐‐ single‐level cell (SLC), multi‐level cell (MLC) and enterprise multi‐level cell (eMLC). The traditionally cited figure is 100,000 program/erase (P/E) cycles (which are also known as "write/erase cycles" or "endurance cycles") for SLC; about 30,000 for eMLC; and 10,000 or considerably less for MLC. Storage and server manufacturers initially favored SLC flash for enterprise use but began to incorporate less‐expensive MLC and eMLC after drive‐makers found ways to improve their reliability through smarter algorithms for wear leveling and error correction, overprovisioning, and other mechanisms of increasing sophistication. MLC can store two or more bits per cell and affords greater capacity than SLC drives. "Almost everybodys going MLC today," said Marc Staimer, president of Dragon Slayer Consulting in Beaverton, Ore. "Very few people go SLC unless youre in the high‐performance compute space." More expensive SLC flash might be necessary in high‐write scenarios since it features better performance, reliability and endurance. Cheaper, slower MLC is generally best suited for read‐intensive workloads that have limited write needs, such as Web content hosting, video streaming and booting drives in servers. The middle‐ground option is eMLC. "MLC and eMLC are the most cost‐effective, but you have to consider the write cliff," Palmer wrote. "If you are deploying only one device, SLC might be a better choice, although more pricey." Martin said he is comfortable using consumer‐grade MLC for server boot drives because the drives dont get a lot of writes. Demartek tends to go with eMLC or SLC in servers with enterprise application data. Gartners Mushell added that the "magic" with solid‐state storage is in the wear leveling and the data integrity, and with about 100 different providers in the market, customers need to do a careful evaluation of the product manufacturers. Several form factor options are available for solid‐state storage, but users will likely find themselves choosing between SAS‐ and SATA‐based SSDs that fit into HDD slots or PCI Express (PCIe) flash cards that connect directly to the PCIe bus. One of the main advantages of directly connected PCIe cards is that they bypass the traditional storage protocol overhead for lower latency. But, Staimer claimed DIY users may need greater skill to use PCIe cards than SAS‐based SSDs in the HDD form
factor. Staimer said SSDs in the HDD form factor are "a much less risky play than the PCIe play because youre connecting to a SAS controller thats already in the system." On the other hand, users will have lower performance because theyre limited by the SAS controller. Select the optimal location for solid‐state storage High‐end arrays from well‐known manufacturers arent the ideal place to tinker with SSDs purchased on the open market. Thats because uncertified drives could have an impact on the warranty and possibly even the system operation. For those that DIY, Staimer advised SSD installation on desktops, laptops and servers, in that order. "Just a bunch of disks"‐‐ several disks in a chassis that connect to a server ‐‐ are also good candidates. "Storage [arrays], not so much. Anything that has a brand name it, youll void the warranty if you open it up." Options for sharing embedded‐server SSDs and PCIe flash cards between multiple servers include Sanbolic Inc.s Melio software and QLogic Corp.s Mt. Rainier host bus adapter (HBA) technology, which is due in 2013. But, such products tack on costs for DIYers. Dont rule out flash cache When it comes to installing SSDs, DIYers may be inclined to favor SSDs for primary storage, but Martin said they shouldnt rule out flash cache. He noted that caching is a simple addition that requires no application or storage changes and provides a significant performance boost. Caching does, however, require software sold through an SSD vendor, storage/server vendor or a separate software company. Options include server‐based products from Fusion‐io Inc., LSI Corp., OCZ Technology Group Inc., SanDisk Corp. and VeloBit Inc.; and software from EMC Corp., NetApp Inc. and smaller vendors. Also, QLogics upcoming Mt. Rainier HBA technology aims to allow sharing of cached data among multiple servers equipped with its PCIe cards or SAS‐based SSDs in environments that use SAN storage. Caching software typically determines the most frequently accessed data and shifts a copy to the flash cache. Flash cache products tend to use PCIe cards connected directly to the CPU and system memory rather than SAS‐ or SATA‐based SSDs. Server‐based flash cache options reduce the latency associated with the network hop. Check warranty and support agreements with your server/storage vendor Vendors of name‐brand storage arrays and servers may have tested and certified
their products with only select SSDs and PCIe cards, so enterprise IT shops need to check support contracts and warranties before installing SSDs to see if drives purchased on the open market will affect their agreements. "If youre talking about a big name‐brand storage system, you cant just go and swap out the drives. You need to get the right drive," Martin said. But the IT shop may be able to buy the drives from a secondary source rather than from the server or storage vendor. Staimer said potential DIYers need to be careful. "Many server vendors will say, If it doesnt come from us, your warranty will be voided, and it will invalidate your service contracts, too," he said. "Theyll fix [a problem], but its coming out of your pocket completely." Buy spares Drives fail, whether theyre HDDs, SSDs or PCIe flash cards, so IT shops that take the DIY approach need to buy spares. And because the SSDs and PCIe flash cards are more expensive than HDDs, they might want to check a number of data points to help determine the number of spares to keep on hand. Martin advised looking at the lengths of warranties with the expectation that enterprise SSDs carry longer guarantees than consumer‐grade products. He further suggested looking for manufacturer‐supplied figures such as terabytes written (TBW). "Although the SSD vendors provide that data, very few end users have done that calculation on their hard drives, so they dont really have any point of comparison," Martin said. "With hard drives, you dont really think about terabytes written per day, so most people dont know what a good number would be." TBW represents the maximum number of terabytes that a host can write to an SSD using a specified workload and application class (client or enterprise). The JEDEC Solid State Technology Association, formerly known as the Joint Electron Devices Engineering Council (JEDEC), offers guidelines for determining TBW, which is also known as an "endurance rating," to allow comparison between different SSDs and vendors through a standard mechanism.
KNOW SSD TRIMNow that solid‐state drives (SSDs) are becoming an affordable alternative to hard drives, certain terms are being used quite often. One of these terms is "TRIM support." To understand what TRIM support is, you first need to understand how solid‐state drives work. SSDs use NAND flash memory to store and transfer information. This flash memory is created up of small "pages" and groups of pages are called "blocks." When you tell your computer to delete a page on the solid‐state drive the page isnt actually deleted ‐ it is merely marked for deletion. This is because data can only be deleted in blocks. You cannot delete individual pages on an SSD. Later on, when you tell your computer that you need the space, the pages marked for deletion are grouped into a block and the whole block is wiped clean. This process slows down the solid‐state drive when it is writing. Let us explain in a different way. Imagine, if you will, that you have a stack of blank papers on your desk at work. Each workday you keep the papers with important information on them, but get rid of the unnecessary papers, like the one you doodled on during a boring meeting, by putting them in the "To Be Recycled" tray on your desk. Its not worth going all the way down to the recycling center for a few sheets of paper, so you wait until you have a stack that is worth the travel time. Eventually, you run out of blank paper. Since you have a project due that day, it is now time to use the paper from the "To Be Recycled" tray. You take out your eraser and get to work. Erasing takes a lot of effort, so you decide to only clean up a portion of the stack to tide you over for a while. Eventually you will run out of paper again and youll have to erase another portion, but you plan on crossing that bridge when you come to it. That is why solid‐state drives slow down while writing after prolonged use. They have to clean the files marked for deletion before they can be written on, and erasing takes time. This can cause serious delays, depending on how much data youre trying to save and how much needs to be deleted. Luckily, TRIM alleviates this problem and is supported on many of the SSDs and operating systems made today. A TRIM command enables your operating system to find the marked pages before you need them and wipe them clean. Cleaning these data pages beforehand saves you time when you need to write on the data pages again. Its like you have your own recycling guy next to your desk, recycling the pieces of paper as they come. In order to work correctly, TRIM has to be supported by both the solid‐state drive and the operating system you are using. When both the OS and the SSD support TRIM individual pages can be cleaned and your solid‐state drive will be informed that
the pages are now blank and can be written on. This kind of cleaning and communication is essential to keep your drive performing to the best of its abilities. SSDs such as the OCZ Vertex 2, the OCZ Agility 2 and the Corsair Force, as well as most of the other storage devices on our solid‐state drive review, all feature native TRIM support. TRIM support is essential for an SSD to run the way it should. To avoid slow writing times, and to save yourself from frustration, make sure that the solid‐state drive you are buying includes TRIM support.
SSD vs HDD: Whats the Difference? Up until this year, PC buyers had very little choice for what kind of primary storage they got with their laptop, nettop, netbook, or desktop. If you bought a netbook or ultraportable, you likely had a solid‐state drive (SSD) as the primary drive (C: on Windows, Macintosh HD on a Mac). Everything other desktop or laptop form factor had a hard disk drive (HDD). Now, you can configure your system with either an HDD, SSD, or in some cases both. But how do you choose? We explain the differences between SSDs and HDDs, and walk you through the advantages and disadvantage of both to help you come to your decision. What is a HDD, What is a SSD? The traditional spinning hard drive (HDD) is the basic nonvolatile storage on a computer. That is, it doesnt "go away" like the data on the system memory when you turn the system off. Hard drives are essentially metal platters with a magnetic coating. That coating stores your data, whether that data consists weather reports from the last century, a high‐definition copy of the Star Wars trilogy, or your digital music collection. A read/write head on an arm accesses the data while the platters are spinning in a hard drive enclosure. An SSD does much the same job functionally (saving your data while the system is off, booting your system, etc.) as an HDD, but instead of a magnetic coating on top of platters, the data is stored on interconnected flash memory chips that retain the data even when theres no power present. The chips can either be permanently installed on the systems motherboard (like on some small laptops and netbooks), on a PCI/PCIe card (in some high‐end workstations), or in a box thats sized, shaped, and wired to slot in for a laptop or desktops hard drive (common on everything else). These flash memory chips differ from the flash memory in USB thumb drives in the type and speed of the memory. Thats the subject of a totally separate technical treatise, but suffice it to say that the flash memory in SSDs is faster and more reliable than the flash memory in USB thumb drives. SSDs are consequently more expensive than USB thumb drives for the same capacities. Hard drive technology is relatively ancient (in terms of computer history). There are well known pictures of the infamous IBM 350 RAMAC hard drive from 1956 that used 50 24‐inch wide platters to hold a whopping 3.75MB of storage space. This, of course, is the size of an average 128Kbps MP3 file, in the physical space that could hold two commercial refrigerators. The IBM 350 was only used by government and industrial users, and was obsolete by 1969. Aint progress wonderful? The PC hard drive form factor standardized in the early 1980s with the desktop‐class 5.25‐inch form factor, with 3.5‐inch desktop and 2.5‐inch notebook‐class drives coming soon thereafter. The internal cable interface has changed from Serial to IDE to SCSI to SATA over the years, but it essentially does the same thing: connects the hard drive to the PCs motherboard so your data can be processed. Todays 2.5‐ and 3.5‐inch drives use SATA interfaces almost exclusively (at least on most PCs and Macs). Capacities have grown from multiple megabytes to multiple terabytes, an increase of millions fold. Current 3.5‐inch HDDs max out at 4TB, with 2.5‐inch drives at 2TB max.
The SSD has a much more recent history. There was always an infatuation with non‐moving storage from the beginning of personal computing, with technologies like bubble memory flashing (pun intended) and dying in the 1970s and 80s. Current flash memory is the logical extension of the same idea. The flash memory chips store your data and dont require constant power to retain that data. The first primary drives that we know as SSDs started during the rise of netbooks in the late 2000s. In 2007, the OLPC XO‐1 used a 1GB SSD, and the Asus Eee PC 700 series used a 2GB SSD as primary storage. The SSD chips on low end Eee PC units and the XO‐1 were permanently soldered to the motherboard. As netbooks and other ultraportables became more capable, the SSD capacities rose, and eventually standardized on the 2.5‐inch notebook form factor. This way, you could pop a 2.5‐inch hard drive out of your laptop or desktop and replace it easily with a SSD. Other form factors emerged, like the DIMM‐like SSDs in the Apple MacBook Air, but today many SSDs are built into the 2.5‐inch form factor. The 2.5‐inch SSD capacity tops out at 1TB currently, but theyre undoubtedly going to grow as time goes by. Advantages/Disadvantages Both SSDs and HDDs do the same job: They boot your system, store your applications, and store your personal files. But each type of storage has its own unique feature set. The question is whats the difference, and why would a user get one over the other? We break it down: Price: To put it bluntly, SSDs are frakking expensive in terms of dollar per GB. For the same capacity and form factor 1TB internal 2.5‐inch drive, youll be paying about $100 for a HDD, but as of this writing, youll be paying a whopping $900 for an SSD. That translates into ten‐cents‐per‐GB for the HDD and ninety cents per GB for the SSD. Other capacities are slightly more affordable (250 to 256GB: $250 SSD, $70 HDD), but you get the idea. Since HDDs are older, more established technologies, they will remain to be less expensive for the near future. Those extra hundreds may push your system price over budget. Maximum and Common Capacity: As seen above, SSD units top out at 1TB, but those are very rare and expensive. Youre more likely to find 128GB to 500GB units as primary drives in systems. Youd be hard pressed to find a 128GB HDD in a PC these days, as 250 or even 500GB is considered a "base" system in 2012. Multimedia users will require even more, with 1TB to 4TB drives as common in high‐end systems. Basically, the more storage capacity, the more stuff (photos, music, videos, etc) you can hold on your PC. While the (Internet) cloud may be a good place to share these files between your phone, tablet, and PC, local storage is less expensive, and you only have to buy it once. Speed: This is where SSDs shine. A SSD‐equipped PC will boot in seconds, certainly under a minute. A hard drive requires time to speed up to operating specs, and will continue to be slower than a SSD during normal operation. A PC or Mac with an SSD boots faster, launches apps faster, and has higher overall performance. Witness the higher PCMark scores on laptops and desktops with SSD drives, plus the much higher scores and transfer times for external SSDs vs. HDDs. Whether its for fun, school, or business, the extra speed may be the difference between finishing on time or failing.
Fragmentation: Because of their spiral‐like recording surfaces, HDD surfaces work best with larger files that are laid down in contiguous blocks. That way, the drive head can start and end its read in one continuous motion. When hard drives start to fill up, large files can become scattered around the disk platter, which is otherwise known as fragmentation. While read/write algorithms have improved where the effect in minimized, the fact of the matter is that HDDs can become fragmented, while SSDs dont care where the data is stored on its chips, since theres no physical read head. SSDs are inherently faster. Durability: An SSD has no moving parts, so it is more likely to keep your data safe in the event that you drop your laptop bag or your system is shaken about by an earthquake while its operating. Most hard drives park their read/write heads when the system is off, but they are flying over the drive platter at hundreds of miles an hour when they are in operation. Besides, even parking brakes have limits. If youre rough on your equipment, a SSD is recommended. Availability: Even taking the flooding in Thailand in late 2011 (a major HDD manufacturing center) into account, hard drives are simply more plentiful. Look at the product lists from Western Digital, Toshiba, Seagate, Samsung, and Hitachi, and youll see many more HDD model numbers than SSDs. For PCs and Macs, HDDs wont be going away, at least for the next couple of years. Youll also see many more HDD choices than SSDs from different manufacturers for the same capacities. Form Factors: Because HDDs rely on spinning platters, there is a limit to how small they can be manufactured. There was an initiative to make smaller 1.8‐inch spinning hard drives, but thats stalled at about 320GB, since the MP3 player and smartphone manufacturers have settled on flash memory for their primary storage. SSDs have no such limitation, so they can continue to shrink as time goes on. SSDs are available in 2.5‐inch laptop drive sized boxes, but thats only for convenience, as stated above. As laptops become slimmer and tablets take over as primary web surfing platforms, youll start to see the adoption of SSDs skyrocket. Noise: Even the quietest HDD will emit a bit of noise when it is in use from the drive spinning or the read arm moving back and forth, particularly if its in a system thats been banged about or in an all‐metal system where its been shoddily installed. Faster hard drives will make more noise than slower ones. SSDs make virtually no noise at all, since theyre non‐mechanical. Overall: HDDs win on price, capacity, and availability. SSDs work best if speed, ruggedness, form factor, noise, or fragmentation (technically part of speed) are important factors to you. If it werent for the price and capacity issues, SSDs would be the winner hands down. As far as longevity goes, while it is true that SSDs wear out over time (each cell in a flash memory bank has a limited number of times it can be written and erased), thanks to TRIM technology built into SSDs that dynamically optimizes these read/write cycles, youre more likely to discard the system for obsolescence before you start running into read/write errors. The possible exception are high‐end multimedia users like video editors who read and write data constantly, but those users will need the larger capacities of hard drives anyway. Hard drives will
eventually wear out from constant use as well, since they use physical recording methods. Longevity is a wash when its separated from travel and ruggedness concerns.