{{Short description|Operating principle for certain storage media}} thumb|alt=A fragment of a road surface, heavily rutted by car wheels following the same path.|Deep ruts from car wheels following the same path. Repetitive use of memory cells leads to a similar effect. Wear leveling attempts to distribute "traffic" more evenly. '''Wear leveling''' (also written as '''wear levelling''') is a technique<ref name="Fundamental Patent">{{US patent|6850443}} Wear leveling techniques for flash memory systems.</ref> for prolonging the service life of some kinds of erasable computer storage media, such as flash memory, which is used in solid-state drives (SSDs) and USB flash drives, and phase-change memory.
thumb|alt=A view on stairs, where the central part deteriorated from people using mostly the middle section of each step.|Uneven wear on the central section of stairs, from pedestrians following a single path. Another everyday-life example of a similar issue. The idea underpinning wear leveling is similar to changing position of car tires, avoiding repetitive load from being used on the same wheel. Wear leveling algorithms distribute writes more evenly across the entire device, so no block is used more often than others.
The term ''preemptive wear leveling'' (PWL) has been used by Western Digital to describe their preservation technique used on hard disk drives (HDDs) designed for storing audio and video data.<ref>{{cite web |url=http://wdc.com/en/products/products.asp?driveid=285 |archive-url=https://web.archive.org/web/20100102045638/http://wdc.com/en/products/products.asp?driveid=285 |url-status=dead |archive-date=2010-01-02 |title=Western Digital AV Hard Drive Product Information |publisher=Western Digital |access-date=2010-06-01}}</ref> However, HDDs generally are not wear-leveled devices in the context of this article.
== {{Anchor|ERASE-BLOCK}}Rationale == EEPROM and flash memory media have individually erasable segments, each of which can be put through a limited number of erase cycles before becoming unreliable. This is usually around 3,000/5,000 cycles<ref>{{Cite web|url=https://hardwarecanucks.com/forum/threads/so-you-wanna-buy-a-ssd-read-this-first.39762/|title=So you wanna buy a SSD? Read this first.|website=Hardware Canucks|date=10 January 2011 }}</ref><ref>{{Cite web|url=https://www.storagereview.com/ssds_shifting_to_25nm_nand_what_you_need_to_know|title=SSDs Shifting to 25nm NAND - What You Need to Know | StorageReview.com - Storage Reviews|date=February 12, 2011|website=www.storagereview.com|access-date=December 5, 2019|archive-date=December 5, 2019|archive-url=https://web.archive.org/web/20191205222622/https://www.storagereview.com/ssds_shifting_to_25nm_nand_what_you_need_to_know|url-status=dead}}</ref> but many flash devices have one block with a specially extended life of 100,000+ cycles that can be used by the flash memory controller to track wear and movement of data across segments.{{cn|date=February 2025}} Erasable optical media such as CD-RW and DVD-RW are rated at up to 1,000 cycles (100,000 cycles for DVD-RAM media).
Wear leveling attempts to work around these limitations by arranging data so that erasures and re-writes are distributed evenly across the medium. In this way, no single erase block prematurely fails due to a high concentration of write cycles.<ref>"Algorithms and data structures for flash memories", E. Gal, and S. Toledo, ACM Computing Surveys, 2005</ref> In flash memory, a single block on the chip is designed for longer life than the others so that the memory controller can store operational data with less chance of its corruption.<ref name=Corsair /><ref>{{cite web | url = https://lwn.net/Articles/428584/ | title = Optimizing Linux with cheap flash drives | date = 2011-02-18 | access-date = 2013-10-03 | author = Arnd Bergmann | publisher = LWN.net }}</ref>
Conventional file systems such as FAT, UFS, HFS/HFS+, EXT, and NTFS were originally designed for magnetic disks and as such rewrite many of their data structures (such as their directories) repeatedly to the same area. When these systems are used on flash memory media, this becomes a problem. The problem is aggravated by the fact that some file systems track last-access times, which can lead to file metadata being constantly rewritten in-place.<ref>{{Cite web | url = https://lwn.net/Articles/244829/ | title = Once upon atime | date = 2007-08-08 | access-date = 2014-01-21 | author = Jonathan Corbet | publisher = LWN.net }}</ref>
== Types == There are several wear leveling mechanisms that provide varying levels of longevity enhancement in such memory systems.<ref name=Spansion>{{cite web|last=Perdue|first=Ken|title=Wear Leveling Application Note|url=http://www.eettaiwan.com/STATIC/PDF/200808/EETOL_2008IIC_Spansion_AN_13.pdf|publisher=Spansion|access-date=12 August 2010|date=2010-04-30|archive-date=2011-06-07|archive-url=https://web.archive.org/web/20110607212139/http://www.eettaiwan.com/STATIC/PDF/200808/EETOL_2008IIC_Spansion_AN_13.pdf|url-status=dead}}</ref><ref name=Corsair>{{cite web|title=USB Flash Wear-Leveling and Life Span|url=http://www.corsair.com/_faq/FAQ_flash_drive_wear_leveling.pdf|publisher=Corsair|access-date=27 July 2013|archive-url=https://web.archive.org/web/20071013150729/http://www.corsair.com/_faq/FAQ_flash_drive_wear_leveling.pdf|archive-date=13 October 2007|date=June 2007}}</ref>
=== No wear leveling === A flash memory storage system with ''no wear leveling'' will not last very long if data is written to the flash. Without wear leveling, the underlying flash controller must permanently assign the logical addresses from the operating system (OS) to the physical addresses of the flash memory. This means that every write to a previously written block must first be read, erased, modified, and re-written to the same location. This approach is very time-consuming and frequently written locations will wear out quickly, while other locations will not be used at all. Once a few blocks reach their end of life, such a device becomes inoperable.<ref name=Spansion/>
=== Dynamic wear leveling === The first type of wear leveling is called ''dynamic wear leveling'' and it uses a map to link logical block addresses (LBAs) from the OS to the physical flash memory. Each time the OS writes replacement data, the map is updated so the original physical block is marked as ''invalid'' data, and a new block is linked to that map entry. Each time a block of data is re-written to the flash memory, it is written to a new location. However, flash memory blocks that never get replacement data would sustain no additional wear, thus the name comes only from the dynamic data being recycled. Such a device may last longer than one with no wear leveling, but there are blocks still remaining as active even though the device is no longer operable.<ref name=Spansion/><ref name=Corsair/>
=== Static wear leveling === The other type of wear leveling is called ''static wear leveling'' which also uses a map to link the LBA to physical memory addresses. Static wear leveling works the same as dynamic wear leveling except the static blocks that do not change are periodically moved so that these low usage cells are able to be used by other data. This rotational effect enables an SSD to continue to operate until most of the blocks are near their end of life.<ref name=Spansion/><ref name=Corsair/>
=== Global wear leveling === Both dynamic and static wear leveling are implemented at the local level. This simply means that in a multi-chip product, every chip is managed as a single resource. The number of defective blocks in different chips within a NAND flash memory varies: a given chip could have all its data blocks worn out while another chip in the same device could have all its blocks still active. Global wear leveling addresses this problem by managing all blocks from all chips in the flash memory together―in a single pool. It ensures that all the cells in all the chips within the product are worn out evenly.<ref>{{cite web |title=Wear Leveling |url=https://www.transcend-info.com/Embedded/Essay-22 |website=Transcend |access-date=20 November 2019}}</ref><ref>{{cite journal |website=Cactus |title=Wear Leveling – Static, Dynamic and Global |page=5 |url=https://www.cactus-tech.com/wp-content/uploads/2019/03/Wear-Leveling-Static-Dynamic-Global.pdf |access-date=20 November 2019}}</ref>
=== Comparison === The following table compares static and dynamic wear leveling:<ref name=Corsair/>
{| class="wikitable sortable" |- ! Item ! Static ! Dynamic |- | Endurance | Longer life expectancy | Shorter life expectancy |- | Performance | Slower | Faster |- | Design complexity | More complex | Less complex |- | Typical use | SSDs,<ref name=Spansion/> <br/>industrial-grade flash drives<ref name=":0">{{cite web|url=http://eu.mouser.com/new/Swissbit/swissbit-industrial-SD-memory/|title=Swissbit Industrial SD Memory Cards|publisher=Mouser Electronics|access-date=21 April 2017}}</ref> | Consumer-grade flash drives |}
== Techniques == There are several techniques for extending the media life:
* A checksum or error-correcting code can be kept for each block or sector in order to detect errors or correct errors. * A pool of overprovisioned reserve space can also be kept. When a block or sector does fail, future reads and writes to it can be redirected to a replacement in that pool. * Blocks or sectors on the media can be tracked in a least frequently used (LFU) queue. The data structures for the queue itself must either be stored off-device or in such a way that the space it uses is itself wear-leveled or, in the case of flash memory, in a block with a specially extended life. However, usual cache algorithms are designed to manage the data flow into and out of RAM-based caches, making them not directly suitable for flash-based storage devices as they have an asymmetrical nature{{snd}} reads are usually much faster than writes, and erase operations can be performed only one "block" at a time.<ref>{{cite web | url = http://www.velobit.com/storage-performance-blog/bid/118134/Why-Standard-Cache-Algorithms-Won-t-Work-For-SSDs | title = Why Standard Cache Algorithms Won't Work For SSDs | date = 2012-02-25 | access-date = 2013-11-26 | author = Qing Yang | publisher = velobit.com }}</ref> * Garbage collection
On Secure Digital cards and USB flash drives,<ref name=":0" /> techniques are implemented in hardware by a built-in microcontroller. On such devices, wear leveling is transparent, and conventional file system such as FAT can be used on them as-is.
Wear leveling can also be implemented in software by special-purpose file systems such as JFFS2 and YAFFS on flash media or UDF on optical media. All three are log-structured file systems in that they treat their media as circular logs and write to them in sequential passes. File systems which implement copy-on-write strategies, such as ZFS, also implement a form of wear leveling.
== See also == * Flash file system * Battery balancing
== References == {{Reflist|40em}}
== External links == * [https://web.archive.org/web/20070202230957/http://www.bitmicro.com/press_resources_flash_ssd.php Flash SSDs{{snd}} Inferior Technology or Closet Superstar?], bitmicro.com, archived from the original on February 2, 2007
{{Solid-state drive|state=collapsed}}
{{DEFAULTSORT:Wear Leveling}} Category:Computer memory Category:Non-volatile memory Category:Flash file systems Category:Solid-state computer storage Category:Balancing technology