Faster startup - Since no spin-up required.
Far faster than conventional disks on random I/O
Extremely low read and write latency (seek) times, roughly 15 times faster than the best current mechanical disks.
Faster boot and application launch time when hard disk seeks are the limiting factor. See Amdahl's law.
In some cases, somewhat longer lifetime - Flash storage typically has a data lifetime on the order of 10 years before degradation. If data is periodically refreshed, it can store data indefinitely. Flash drives have limited endurance (typically, 100,000-300,000 write cycles), which, if a single block is written once per second, leads to failure in a few days at most. However, all flash drives employ a technique known as wear levelling, where writes are smoothly distibuted over all blocks. This means that if one write occurs per second, and n is the number of writes before failure and m is the number of blocks on the disk, failure no longer occurs in n seconds, but in (n*m) seconds. Given that blocks are typically on the order of 1kb and an 8 GB disk will have 8,192 blocks, this gives about 9,500 days before failure; remember also this is with one write per second for that entire time [1]. In consumer level devices you can expect the drive's data storage component to last roughly 10 years in normal use [4]
Far faster than conventional disks on random I/O
Extremely low read and write latency (seek) times, roughly 15 times faster than the best current mechanical disks.
Faster boot and application launch time when hard disk seeks are the limiting factor. See Amdahl's law.
In some cases, somewhat longer lifetime - Flash storage typically has a data lifetime on the order of 10 years before degradation. If data is periodically refreshed, it can store data indefinitely. Flash drives have limited endurance (typically, 100,000-300,000 write cycles), which, if a single block is written once per second, leads to failure in a few days at most. However, all flash drives employ a technique known as wear levelling, where writes are smoothly distibuted over all blocks. This means that if one write occurs per second, and n is the number of writes before failure and m is the number of blocks on the disk, failure no longer occurs in n seconds, but in (n*m) seconds. Given that blocks are typically on the order of 1kb and an 8 GB disk will have 8,192 blocks, this gives about 9,500 days before failure; remember also this is with one write per second for that entire time [1]. In consumer level devices you can expect the drive's data storage component to last roughly 10 years in normal use [4]
[image : The disassembled components of a hard disk drive (left) and of the PCB and components of a solid state drive (right). ]
However, it should be noted that certain SCSI hard drives have MTBF of 1.5
million hours (~175 years) and normal SATA harddrives have MTBF of 500,000 hours (~57 years). [5] The actual expected time-to-failure is typically several years, with manufacturers giving warranties of up to and around 5 years in consumer level products [6]. The high MTBFs are not calculated based on expected hard drive time to failure, but rather based on failure rates of hard drives without much wear.Few to no mechanical parts
For small drives, lower power consumption and heat production.
For small hard drives, no noise - Lack of mechanical parts makes the SSD completely silent (many high-end SSDs include cooling fans).
Better mechanical reliability - Lack of mechanical parts results in less wear and tear. High level of ability to endure extreme shock, high altitude, vibration and temperatures[citation needed], which apply to laptops and other mobile devices, or when transported.
Security - allowing a very quick "wipe" of all data stored. [citation needed]
Relatively deterministic performance [7] - unlike mechanical hard drives, performance of SSDs is almost constant and deterministic across the entire storage. "Seek" time can be constant, and performance does not deteriorate as the media fills up (See: Fragmentation).
However, this is not always the case, as explained below. Flash memory is organised in blocks which can be erased, written or read, but only as whole blocks. The access time is the same for each block. If one or more blocks are used as Access Unit (AU), fragmentation has no harmful effect on access speed. However, for high capacity flash memories the AU would be too big, causing a lot of wasted bytes due to unused space within allocated AU's. Hence, in these cases each block is split up in a number of AU's. Initially AU's will be used sequentially within blocks. So a file with a size of N blocks will use no more than N+2 blocks, the first and last block only partially. However, after some time a situation will occur where no block is available of which all AU's are free, so that one or more extra blocks are needed The result is that said file will need more than N+2 blocks and accessing more blocks takes more time. In the worst case only one AE per block is free and said file will need S*N blocks, where S is the number of AE's per block. The conclusion is that, with bigger flash memory, fragmentation has a detoriating effect on access time.
For very low-capacity drives, lower weight and size. Size and weight per unit storage are still better for traditional hard drives, and microdrives allow up to 20GB storage in a CompactFlash 42.8×36.4×5 mm (1.7×1.4×.2 in) form factor.
댓글 없음:
댓글 쓰기