Movatterモバイル変換


[0]ホーム

URL:


Jump to content
WikipediaThe Free Encyclopedia
Search

Non-standard RAID levels

From Wikipedia, the free encyclopedia
(Redirected fromRAID-Z)

This article is about non-standard RAID configurations. For RAID in general, seeRAID. For basic RAID configurations, seeStandard RAID levels.

Although allRAID implementations differ from the specification to some extent, some companies and open-source projects have developednon-standard RAID implementations that differ substantially from the standard. Additionally, there arenon-RAID drive architectures, providing configurations of multiple hard drives not referred to by RAID acronyms.

RAID-DP

[edit]

Row diagonal parity is a scheme where one dedicated disk of parity is in a horizontal "row" like inRAID 4, but the other dedicated parity is calculated from blocks permuted ("diagonal") like in RAID 5 and 6.[1] Alternative terms for "row" and "diagonal" include "dedicated" and "distributed".[2] Invented byNetApp, it is offered asRAID-DP in theirONTAP systems.[3] The technique can be considered RAID 6 in the broad SNIA definition[4] and has the same failure characteristics as RAID 6. The performance penalty of RAID-DP is typically under 2% when compared to a similar RAID 4 configuration.[5]

RAID 5E, RAID 5EE, and RAID 6E

[edit]

RAID 5E, RAID 5EE, and RAID 6E (with the addedE standing forEnhanced) generally refer to variants of RAID 5 or 6 with an integratedhot-spare drive, where the spare drive is an active part of the block rotation scheme. This spreads I/O across all drives, including the spare, thus reducing the load on each drive, increasing performance. It does, however, prevent sharing the spare drive among multiple arrays, which is occasionally desirable.[6]

Intel Matrix RAID

[edit]
Diagram of an Intel Matrix RAID setup
Main article:Intel Matrix RAID

Intel Matrix RAID (a feature of Intel Rapid Storage Technology) is a feature (not a RAID level) present in theICH6R and subsequent Southbridge chipsets from Intel, accessible and configurable via the RAIDBIOS setup utility. Matrix RAID supports as few as two physical disks or as many as the controller supports. The distinguishing feature of Matrix RAID is that it allows any assortment of RAID 0, 1, 5, or 10 volumes in the array, to which a controllable (and identical) portion of each disk is allocated.[7][8][9]

As such, a Matrix RAID array can improve both performance and data integrity. A practical instance of this would use a small RAID 0 (stripe) volume for theoperating system, program, and paging files; second larger RAID 1 (mirror) volume would store critical data.Linux MD RAID is also capable of this.[7][8][9]

Linux MD RAID 10

[edit]

The software RAID subsystem provided by theLinux kernel, calledmd, supports the creation of bothclassic (nested) RAID 1+0 arrays, and non-standard RAID arrays that use a single-level RAID layout with some additional features.[10][11]

The standard "near" layout, in which each chunk is repeatedn times in ak-way stripe array, is equivalent to the standard RAID 10 arrangement, but it does not require thatn evenly dividesk. For example, ann2 layout on two, three, and four drives would look like:[12][13]

2 drives        3 drives          4 drives--------        ----------        --------------A1  A1          A1  A1  A2        A1  A1  A2  A2A2  A2          A2  A3  A3        A3  A3  A4  A4A3  A3          A4  A4  A5        A5  A5  A6  A6A4  A4          A5  A6  A6        A7  A7  A8  A8..  ..          ..  ..  ..        ..  ..  ..  ..

The four-drive example is identical to a standard RAID 1+0 array, while the three-drive example is a software implementation of RAID 1E. The two-drive example is equivalent to RAID 1.[13]

The driver also supports a "far" layout, in which all the drives are divided intof sections. All the chunks are repeated in each section but are switched in groups (for example, in pairs). For example,f2 layouts on two-, three-, and four-drive arrays would look like this:[12][13]

2 drives        3 drives          4 drives--------        ------------      ------------------A1  A2          A1   A2   A3      A1   A2   A3   A4A3  A4          A4   A5   A6      A5   A6   A7   A8A5  A6          A7   A8   A9      A9   A10  A11  A12..  ..          ..   ..   ..      ..   ..   ..   ..A2  A1          A3   A1   A2      A2   A1   A4   A3A4  A3          A6   A4   A5      A6   A5   A8   A7A6  A5          A9   A7   A8      A10  A9   A12  A11..  ..          ..   ..   ..      ..   ..   ..   ..

"Far" layout is designed for offering striping performance on a mirrored array; sequential reads can be striped, as in RAID 0 configurations.[14] Random reads are somewhat faster, while sequential and random writes offer about equal speed to other mirrored RAID configurations. "Far" layout performs well for systems in which reads are more frequent than writes, which is a common case. For a comparison, regular RAID 1 as provided byLinux software RAID, does not stripe reads, but can perform reads in parallel.[15]

The md driver also supports an "offset" layout, in which each stripe is repeatedo times and offset byf (far) devices. For example,o2 layouts on two-, three-, and four-drive arrays are laid out as:[12][13]

2 drives        3 drives          4 drives--------        ----------        ---------------A1  A2          A1  A2  A3        A1  A2  A3  A4A2  A1          A3  A1  A2        A4  A1  A2  A3A3  A4          A4  A5  A6        A5  A6  A7  A8A4  A3          A6  A4  A5        A8  A5  A6  A7A5  A6          A7  A8  A9        A9  A10 A11 A12A6  A5          A9  A7  A8        A12 A9  A10 A11..  ..          ..  ..  ..        ..  ..  ..  ..

It is also possible to combine "near" and "offset" layouts (but not "far" and "offset").[13]

In the examples above,k is the number of drives, whilen#,f#, ando# are given as parameters tomdadm's--layout option. Linux software RAID (Linux kernel'smd driver) also supports creation of standard RAID 0, 1, 4, 5, and 6 configurations.[16][17]

RAID 1E

[edit]
Diagram of a RAID 1E setup

SomeRAID 1 implementations treat arrays with more than two disks differently, creating a non-standard RAID level known asRAID 1E. In this layout, data striping is combined with mirroring, by mirroring each written stripe to one of the remaining disks in the array. Usable capacity of a RAID 1E array is 50% of the total capacity of all drives forming the array; if drives of different sizes are used, only the portions equal to the size of smallest member are utilized on each drive.[18][19]

One of the benefits of RAID 1E over usual RAID 1 mirrored pairs is that the performance of random read operations remains above the performance of a single drive even in a degraded array.[18]

RAID-Z

[edit]
See also:ZFS § ZFS's approach: RAID-Z and mirroring

TheZFS filesystem providesRAID-Z, a data/parity distribution scheme similar toRAID 5, but using dynamic stripe width: every block is its own RAID stripe, regardless of blocksize, resulting in every RAID-Z write being a full-stripe write. This, when combined with the copy-on-write transactional semantics of ZFS, eliminates thewrite hole error. RAID-Z is also faster than traditional RAID 5 because it does not need to perform the usualread–modify–write sequence. RAID-Z does not require any special hardware, such as NVRAM for reliability, or write buffering for performance.[20]

Given the dynamic nature of RAID-Z's stripe width, RAID-Z reconstruction must traverse the filesystem metadata to determine the actual RAID-Z geometry. This would be impossible if the filesystem and the RAID array were separate products, whereas it becomes feasible when there is an integrated view of the logical and physical structure of the data. Going through the metadata means that ZFS can validate every block against its 256-bit checksum as it goes, whereas traditional RAID products usually cannot do this.[20]

In addition to handling whole-disk failures, RAID-Z can also detect and correctsilent data corruption, offering "self-healing data": when reading a RAID-Z block, ZFS compares it against its checksum, and if the data disks did not return the right answer, ZFS reads the parity and then figures out which disk returned bad data. Then, it repairs the damaged data and returns good data to the requestor.[20]

There are five different RAID-Z modes:RAID-Z0 (similar to RAID 0, offers no redundancy),RAID-Z1 (similar to RAID 5, allows one disk to fail),RAID-Z2 (similar to RAID 6, allows two disks to fail),RAID-Z3 (a RAID 7[a] configuration, allows three disks to fail), andmirror (similar to RAID 1, allows all but one of the disks to fail).[22]

Drive Extender

[edit]

Windows Home Server Drive Extender is a specialized case ofJBOD RAID 1 implemented at thefile system level.[23]

Microsoft announced in 2011 that Drive Extender would no longer be included as part ofWindows Home Server Version 2,Windows Home Server 2011 (codename VAIL).[24] As a result, there has been a third-party vendor move to fill the void left by DE. Included competitors are Division M, the developers of Drive Bender, and StableBit's DrivePool.[25][26]

BeyondRAID

[edit]

BeyondRAID is not a true RAID extension, but consolidates up to 12 SATA hard drives into one pool of storage.[27] It has the advantage of supporting multiple disk sizes at once, much like JBOD, while providing redundancy for all disks and allowing a hot-swap upgrade at any time. Internally it uses a mix of techniques similar to RAID 1 and 5. Depending on the fraction of data in relation to capacity, it can survive up to three drive failures,[citation needed] if the "array" can be restored onto the remaining good disks before another drive fails. The amount of usable storage can be approximated by summing the capacities of the disks and subtracting the capacity of the largest disk. For example, if a 500, 400, 200, and 100 GB drive were installed, the approximate usable capacity would be 500 + 400 + 200 + 100 − 500 = 700 GB of usable space. Internally the data would be distributed in two RAID 5–like arrays and two RAID 1-like sets:

           Drives | 100 GB |  | 200 GB |  | 400 GB |  | 500 GB |                                     ----------                                     |   x    | unusable space (100 GB)                                     ----------                         ----------  ----------                         |   A1   |  |   A1   | RAID 1 set (2× 100 GB)                         ----------  ----------                         ----------  ----------                         |   B1   |  |   B1   | RAID 1 set (2× 100 GB)                         ----------  ----------             ----------  ----------  ----------             |   C1   |  |   C2   |  |   Cp   | RAID 5 array (3× 100 GB)             ----------  ----------  ---------- ----------  ----------  ----------  ---------- |   D1   |  |   D2   |  |   D3   |  |   Dp   | RAID 5 array (4× 100 GB) ----------  ----------  ----------  ----------

BeyondRaid offers a RAID 6–like feature and can perform hash-based compression using 160-bitSHA-1 hashes to maximize storage efficiency.[28]

Unraid

[edit]
Main article:Unraid

Unraid is a proprietary Linux-based operating system optimized for media file storage.[29]
Unfortunately Unraid doesn't provide information about its storage technology, but some[who?] say its parity array is a rewrite of the mdadm module.

Disadvantages include closed-source code,high price[citation needed],slower write performance than a single disk[citation needed] and bottlenecks when multiple drives are written concurrently. However, Unraid allows support of a cache pool which can dramatically speed up the write performance. Cache pool data can be temporarily protected usingBtrfs RAID 1 until Unraid moves it to the array based on a schedule set within the software.[citation needed]

Advantages include lower power consumption than standard RAID levels, the ability to use multiple hard drives with differing sizes to their full capacity and in the event of multiple concurrent hard drive failures (exceeding the redundancy), only losing the data stored on the failed hard drives compared to standard RAID levels which offer striping in which case all of the data on the array is lost when more hard drives fail than the redundancy can handle.[30]

CRYPTO softraid

[edit]

InOpenBSD, CRYPTO is an encrypting discipline for the softraid subsystem. It encrypts data on a single chunk toprovide for data confidentiality. CRYPTO does not provide redundancy.[31]RAID 1C provides both redundancy and encryption.[31]

DUP profile

[edit]

Some filesystems, such as Btrfs,[32] and ZFS/OpenZFS (with per-dataset copies=1|2|3 property),[33] support creating multiple copies of the same data on a single drive or disks pool, protecting from individual bad sectors, but not from large numbers of bad sectors or complete drive failure. This allows some of the benefits of RAID on computers that can only accept a single drive, such as laptops.

Declustered RAID

[edit]

Declustered RAID allows for arbitrarily sized disk arrays while reducing the overhead to clients when recovering from disk failures. It uniformly spreads or declusters user data, redundancy information, and spare space across all the disks of a declustered array. Under traditional RAID, an entire disk storage system of, say, 100 disks would be split into multiple arrays each of, say, 10 disks. By contrast, under declustered RAID, the entire storage system is used to make one array. Every data item is written twice, as in mirroring, but logically adjacent data and copies are spread arbitrarily. When a disk fails, erased data is rebuilt using all the operational disks in the array, the bandwidth of which is greater than that of the fewer disks of a conventional RAID group. Furthermore, if an additional disk fault occurs during a rebuild, the number of impacted tracks requiring repair is markedly less than the previous failure and less than the constant rebuild overhead of a conventional array. The decrease in declustered rebuild impact and client overhead can be a factor of three to four times less than a conventional RAID. File system performance becomes less dependent upon the speed of any single rebuilding storage array.[34]

Dynamic disk pooling (DDP), also known as D-RAID, maintains performance even when up to 2 drives fail simultaneously.[35]DDP is a high performance type of declustered RAID.[36]

See also

[edit]

Explanatory notes

[edit]
  1. ^While RAID 7 is not a standard RAID level, it has been proposed as a catch-all term for any >2 parity RAID configuration[21]

References

[edit]
  1. ^Peter Corbett; Bob English; Atul Goel; Tomislav Grcanac; Steven Kleiman; James Leong & Sunitha Sankar (2004)."Row-Diagonal Parity for Double Disk Failure Correction"(PDF). USENIX Association.Archived(PDF) from the original on 2013-11-22. Retrieved2013-11-22.
  2. ^Fischer, Werner."RAID-DP".thomas-krenn. Retrieved26 May 2023.
  3. ^White, Jay; Lueth, Chris; Bell, Jonathan (March 2003)."RAID-DP: NetApp Implementation of Double-Parity RAID for Data Protection"(PDF).NetApp.com. Network Appliance. Retrieved2014-06-07.
  4. ^"Dictionary R".SNIA.org. Storage Networking Industry Association. Retrieved2007-11-24.
  5. ^White, Jay; Alvarez, Carlos (October 2011)."Back to Basics: RAID-DP | NetApp Community".NetApp.com. NetApp. Retrieved2014-08-25.
  6. ^"Non-standard RAID levels".RAIDRecoveryLabs.com. Archived fromthe original on 2013-12-15. Retrieved2013-12-15.
  7. ^ab"Intel's Matrix RAID Explored". The Tech Report. 2005-03-09. Retrieved2014-04-02.
  8. ^ab"Setting Up RAID Using Intel Matrix Storage Technology".HP.com. Hewlett Packard. Retrieved2014-04-02.
  9. ^ab"Intel Matrix Storage Technology".Intel.com. Intel. 2011-11-05. Retrieved2014-04-02.
  10. ^"Creating Software RAID 10 Devices". SUSE. Retrieved11 May 2016.
  11. ^"Nested RAID Levels". Arch Linux. Retrieved11 May 2016.
  12. ^abc"Creating a Complex RAID 10". SUSE. Retrieved11 May 2016.
  13. ^abcde"Linux Software RAID 10 Layouts Performance: Near, Far, and Offset Benchmark Analysis".Ilsistemista.net. 2012-08-28. Archived fromthe original on 2023-03-24. Retrieved2014-03-08.
  14. ^Jon Nelson (2008-07-10)."RAID5,6 and 10 Benchmarks on 2.6.25.5".Jamponi.net. Retrieved2014-01-01.
  15. ^"Performance, Tools & General Bone-Headed Questions".TLDP.org. Retrieved2014-01-01.
  16. ^"mdadm(8): manage MD devices aka Software RAID - Linux man page".Linux.Die.net. Retrieved2014-03-08.
  17. ^"md(4): Multiple Device driver aka Software RAID - Linux man page".Die.net. Retrieved2014-03-08.
  18. ^ab"Which RAID Level is Right for Me?: RAID 1E (Striped Mirroring)".Adaptec. Retrieved2014-01-02.
  19. ^"LSI 6 Gb/s Serial Attached SCSI (SAS) Integrated RAID: A Product Brief"(PDF).LSI Corporation. 2009. Archived fromthe original(PDF) on 2011-06-28. Retrieved2015-01-02.
  20. ^abcBonwick, Jeff (2005-11-17)."RAID-Z".Jeff Bonwick's Blog.Oracle Blogs. Archived fromthe original on 2014-12-16. Retrieved2015-02-01.
  21. ^Leventhal, Adam (2009-12-17)."Triple-Parity RAID and Beyond".Queue.7 (11): 30.doi:10.1145/1661785.1670144.
  22. ^"ZFS Raidz Performance, Capacity and integrity".calomel.org. Archived fromthe original on 27 November 2017. Retrieved23 June 2017.
  23. ^Separate from Windows'Logical Disk Manager
  24. ^"MS drops drive pooling from Windows Home Server".The Register.
  25. ^"Drive Bender Public Release Arriving This Week". We Got Served. Archived fromthe original on 2017-08-20. Retrieved2014-01-15.
  26. ^"StableBit DrivePool 2 Year Review".Home Media Tech. December 2013.
  27. ^Data Robotics, Inc. implements BeyondRaid in theirDrobostorage device.
  28. ^Detailed technical information about BeyondRaid, including how it handles adding and removing drives, is:US 20070266037, Julian Terry; Geoffrey Barrall & Neil Clarkson, "Filesystem-Aware Block Storage System, Apparatus, and Method", assigned toDROBO Inc 
  29. ^"What is unRAID?".Lime-Technology.com. Lime Technology. 2013-10-17. Archived fromthe original on 2014-01-05. Retrieved2014-01-15.
  30. ^"LimeTech – Technology".Lime-Technology.com. Lime Technology. 2013-10-17. Archived fromthe original on 2014-01-05. Retrieved2014-02-09.
  31. ^ab"Manual Pages: softraid(4)".OpenBSD.org. 2022-09-06. Retrieved2022-09-08.
  32. ^"Manual Pages: mkfs.btrfs(8)".btrfs-progs. 2018-01-08. Retrieved2018-08-17.
  33. ^"Maintenance Commands zfs - configures ZFS file system".illumos: manual page: zfs.1m.
  34. ^"Declustered RAID". IBM. 14 June 2019. Retrieved1 February 2020.
  35. ^IBM."Dynamic Disk Pooling (DDP)".
  36. ^"High Performance Computing: NEC GxFS Storage Appliance".p. 6.
Redundantarray of independentdisks
Disk arrays
RAID levels
Principles
Interfaces
Retrieved from "https://en.wikipedia.org/w/index.php?title=Non-standard_RAID_levels&oldid=1276563558#RAID-Z"
Category:
Hidden categories:

[8]ページ先頭

©2009-2025 Movatter.jp