Jump to content

Hierarchical storage management: Difference between revisions

From Wikipedia, the free encyclopedia
Browse history interactively
← Previous edit
Content deleted Content added
VisualWikitext
Betacommand (talk | contribs)
86,927 edits
adding {{DEFAULTSORT}}
Pdrq (talk | contribs)
1 edit
m Corrected a spelling error
Tags: Visual edit Mobile edit Mobile web edit
 
(237 intermediate revisions by more than 100 users not shown)
Line 1: Line 1:
{{mergefrom|Tiered storage|date=September 2007}}
{{Short description|Data storage technique}}
{{redirect|System Managed Storage|the IBM implementation|Data Facility Storage Management Subsystem (MVS)#DFSMShsm}}
'''Hierarchical Storage Management''' ('''HSM''') is a [[data storage]] technique which automatically moves data between high-cost and low-cost storage media. HSM systems exist because high-speed storage devices, such as [[hard disk drive]] arrays, are more expensive (per [[byte]] stored) than slower devices, such as [[optical disc]]s and magnetic [[tape drive]]s. While it would be ideal to have all data available on high-speed devices all the time, this is prohibitively expensive for many organizations. Instead, HSM systems store the bulk of the enterprise's data on slower devices, and then copy data to faster disk drives when needed. In effect, HSM turns the fast disk drives into [[cache]]s for the slower mass storage devices. The HSM system monitors the way data is used and makes best guesses as to which data can safely be moved to slower devices and which data should stay on the fast devices.
'''Hierarchical storage management''' ('''HSM'''), also known as '''tiered storage''',<ref name="Freeman"/> is a [[Computer data storage|data storage]] and [[data management]] technique that automatically moves data between high-cost and low-cost [[data storage media|storage media]]. HSM systems exist because high-speed storage devices, such as [[solid-state drive]] arrays, are more expensive (per [[byte]] stored) than slower devices, such as [[hard disk drive]]s, [[optical disc]]s and magnetic [[tape drive]]s. While it would be ideal to have all data available on high-speed devices all the time, this is prohibitively expensive for many organizations. Instead, HSM systems store the bulk of the enterprise's data on slower devices, and then copy data to faster disk drives when needed. The HSM system monitors the way data is used and makes best guesses as to which data can safely be moved to slower devices and which data should stay on the fast devices.


HSM may also be used where more robust storage is available for long-term archiving, but this is slow to access. This may be as simple as an [[off-site backup]], for protection against a building fire.
In a typical HSM scenario, data files which are frequently used are stored on disk drives, but are eventually ''migrated'' to tape if they are not used for a certain period of time, typically a few months. If a user does reuse a file which is on tape, it is automatically moved back to disk storage. The advantage is that the total amount of stored data can be much larger than the capacity of the disk storage available, but since only rarely-used files are on tape, most users will usually not notice any slowdown.


HSM is a long-established concept, dating back to the beginnings of commercial data processing. The techniques used though have changed significantly as new technology becomes available, for both storage and for long-distance communication of large data sets. The scale of measures such as 'size' and 'access time' have changed dramatically. Despite this, many of the underlying concepts keep returning to favour years later, although at much larger or faster scales.<ref name="Freeman"/>
HSM is sometimes referred to as [[tiered storage]].


== Implementation ==
HSM was first implemented by [[IBM]] on their [[mainframe computer]]s to reduce the cost of data storage, and to simplify the retrieval of data from slower media. The user would not need to know where the data was stored and how to get it back; the computer would retrieve the data automatically. The only difference to the user was the speed at which data was returned.
In a typical HSM scenario, data which is frequently used are stored on warm storage device, such as solid-state disk (SSD). Data that is infrequently accessed is, after some time ''migrated'' to a slower, high capacity cold storage tier. If a user does access data which is on the cold storage tier, it is automatically moved back to warm storage. The advantage is that the total amount of stored data can be much larger than the capacity of the warm storage device, but since only rarely used files are on cold storage, most users will usually not notice any slowdown.


Conceptually, HSM is analogous to the [[CPU cache|cache]] found in most computer [[central processing unit|CPU]]s, where small amounts of expensive [[static random access memory|SRAM]] memory running at very high speeds is used to store frequently used data, but the [[cache algorithms|least recently used]] data is evicted to the slower but much larger main [[DRAM]] memory when new data has to be loaded.
Later, IBM ported HSM to its [[AIX operating system]], and then to other [[Unix-like]] operating systems such as [[Solaris (operating system)|Solaris]], [[HP-UX]] and [[Linux]].


In practice, HSM is typically performed by dedicated software, such as [[IBM Tivoli Storage Manager]], or [[Oracle Corporation|Oracle's]] [[QFS|SAM-QFS]].
Recently, the development of [[Serial ATA]] (SATA) disks has created a significant market for three-stage HSM: files are migrated from high-performance [[Fibre Channel]] [[Storage Area Network]] devices to somewhat slower but much cheaper SATA [[Redundant array of independent disks|disks arrays]] totalling several [[terabytes]] or more, and then eventually from the SATA disks to tape.


The deletion of files from a higher level of the hierarchy (e.g. magnetic disk) after they have been moved to a lower level (e.g. optical media) is sometimes called '''file grooming'''.<ref name="DillonLeonard1998">{{cite book|author1=Patrick M. Dillon|author2=David C. Leonard|title=Multimedia and the Web from A to Z|url=https://books.google.com/books?id=LjVyJ8RuGtMC&pg=PA116|year=1998|publisher=ABC-CLIO|isbn=978-1-57356-132-7|page=116}}</ref>
Conceptually, HSM is analogous to the [[cache]] found in most computer [[Central Processing Unit|CPUs]], where small amounts of expensive [[Static random access memory|SRAM]] memory running at very high speeds is used to store frequently used data, but the [[Cache algorithms|least recently used]] data is evicted to the slower but much larger main [[DRAM]] memory when new data has to be loaded.


== History ==
In practice, HSM is typically performed by dedicated software, such as [[CommVault Systems|CommVault]] [http://www.commvault.com/products.asp?pid=2 DataMigrator], [[VERITAS Software|VERITAS]] [http://www.veritas.com/kvs/ Enterprise Vault], Sun Microsystems [http://www.sun.com/storagetek/management_software/data_management/qfs SAMFS/QFS] or [[Quantum Corporation|Quantum]] [[StorNext File System|StorNext]].
Hierarchical Storage Manager (HSM, then DFHSM and finally [[DFSMShsm]]) was first{{Citation needed|date=January 2009}} implemented by [[IBM]] on March 31, 1978 for [[MVS]] to reduce the cost of data storage, and to simplify the retrieval of data from slower media. The user would not need to know where the data was stored and how to get it back; the computer would retrieve the data automatically. The only difference to the user was the speed at which data was returned. HSM could originally migrate datasets only to disk volumes and virtual volumes on a [[IBM 3850]] Mass Storage Facility, but a latter release supported magnetic tape volumes for migration level 2 (ML2).


Later, IBM ported HSM to its [[IBM AIX|AIX operating system]], and then to other [[Unix-like]] operating systems such as [[Solaris (operating system)|Solaris]], [[HP-UX]] and [[Linux]].
= Use Case =


CSIRO Australia's Division of Computing Research implemented an HSM in its DAD (Drums and Display) operating system with its Document Region in the 1960s, with copies of documents being written to 7-track tape and automatic retrieval upon access to the documents.
HSM is often used for deep archival storage of data to be held long term at low cost. Automated tape robots can silo large quantities of data efficiently with low power consumption.


HSM was also implemented on the DEC [[OpenVMS|VAX/VMS]] systems and the Alpha/VMS systems. The first implementation date should be readily determined from the VMS System Implementation Manuals or the VMS Product Description Brochures.
Some HSM software products allow the user to place portions of data files on high-speed disk cache and the rest on tape. This is used in applications that stream video over the internet -- the initial portion of a video is delivered immediately from disk while a robot finds, mounts and stream the rest of the file to the end user. Such a system greatly reduces disk cost for large content provision systems.


More recently, the development of [[Serial ATA]] (SATA) disks has created a significant market for three-stage HSM: files are migrated from high-performance [[Fibre Channel]] [[storage area network]] devices to somewhat slower but much cheaper SATA [[redundant array of independent disks|disk array]]s totaling several [[terabyte]]s or more, and then eventually from the SATA disks to tape.
== See also ==

* [[Archive]]
==Use cases==
* [[Backup]]
HSM is often used for deep archival storage of data to be held long term at low cost. Automated tape robots can silo large quantities of data efficiently with low power consumption.
*[[Computer data storage]]

Some HSM software products allow the user to place portions of data files on high-speed disk cache and the rest on tape. This is used in applications that stream video over the internet—the initial portion of a video is delivered immediately from disk while a robot finds, mounts and streams the rest of the file to the end user. Such a system greatly reduces disk cost for large content provision systems.

HSM software is today used also for tiering between [[hard disk drive]]s and [[flash memory]], with flash memory being over 30 times faster than magnetic disks, but disks being considerably cheaper.

==Algorithms==
The key factor behind HSM is a data migration policy that controls the file transfers in the system. More precisely, the policy decides which tier a file should be stored in, so that the entire storage system can be well-organized and have a shortest response time to requests. There are several algorithms realizing this process, such as least recently used replacement (LRU),<ref>{{Cite journal|last1=O'Neil|first1=Elizabeth J.|last2=O'Neil|first2=Patrick E.|last3=Weikum|first3=Gerhard|date=1993-06-01|title=The LRU-K page replacement algorithm for database disk buffering|url=https://doi.org/10.1145/170036.170081|journal=ACM SIGMOD Record|volume=22|issue=2|pages=297–306|doi=10.1145/170036.170081|s2cid=207177617 |issn=0163-5808}}</ref> Size-Temperature Replacement(STP), Heuristic Threshold(STEP)<ref>{{Cite book|last1=Verma|first1=A.|last2=Pease|first2=D.|last3=Sharma|first3=U.|last4=Kaplan|first4=M.|last5=Rubas|first5=J.|last6=Jain|first6=R.|last7=Devarakonda|first7=M.|last8=Beigi|first8=M.|title=22nd IEEE / 13th NASA Goddard Conference on Mass Storage Systems and Technologies (MSST'05) |chapter=An Architecture for Lifecycle Management in Very Large File Systems |date=2005|chapter-url=https://ieeexplore.ieee.org/document/1410732|location=Monterey, CA, US|publisher=IEEE|pages=160–168|doi=10.1109/MSST.2005.4|isbn=978-0-7695-2318-7|s2cid=7082285}}</ref> etc. In research of recent years, there are also some intelligent policies coming up by using machine learning technologies.<ref>{{Cite journal |last=Zhang |first=Tianru |last2=Hellander |first2=Andreas |last3=Toor |first3=Salman |date=2022 |title=Efficient Hierarchical Storage Management Empowered by Reinforcement Learning |url=https://ieeexplore.ieee.org/document/9779953/ |journal=IEEE Transactions on Knowledge and Data Engineering |pages=1–1 |doi=10.1109/TKDE.2022.3176753 |issn=1041-4347}}</ref>

== Tiering vs. caching ==
While tiering solutions and caching may look the same on the surface, the fundamental differences lie in the way the faster storage is utilized and the algorithms used to detect and accelerate frequently accessed data.<ref name="brand1">{{cite web |url=https://medium.com/p/12fa7c30959d|title=Hot Storage vs Cold Storage: Choosing the Right Tier for Your Data |work=Medium.com |first=Aron |last=Brand |date=June 20, 2022|access-date=June 20, 2022}}</ref>

Caching operates by making a copy of frequently accessed blocks of data, and storing the copy in the faster storage device and use this copy instead of the original data source on the slower, high capacity backend storage. Every time a storage read occurs, the caching software look to see if a copy of this data already exists on the cache and uses that copy, if available. Otherwise, the data is read from the slower, high capacity storage.<ref name="brand1"/>

Tiering on the other hand operates very differently. Rather than making a ''copy'' of frequently accessed data into fast storage, tiering ''moves'' data across tiers, for example, by relocating [[cold data]] to low cost, high capacity nearline storage devices.<ref name="posey1">{{cite web |url=https://www.techtarget.com/searchstorage/tip/Differences-between-SSD-caching-and-tiering-technologies|title=Differences between SSD caching and tiering technologies |work=TechTarget |first=Brien |last=Posey |date=November 8, 2016|access-date=Jun 21, 2022}}</ref><ref name="brand1"/> The basic idea is, mission-critical and highly accesses or "hot" data is stored in expensive medium such as SSD to take advantage of high I/O performance, while [[nearline storage|nearline]] or rarely accessed or "cold" data is stored in [[nearline storage|nearline storage medium]] such as HDD and [[tape drive|tapes]] which are inexpensive.{{sfn|Winnard|Biondo|2016|p=5}} Thus, the "data temperature" or activity levels determines the [[Memory_hierarchy|primary storage hierarchy]].{{sfn|Winnard|Biondo|2016|p=6}}

==Implementations==
*[[Alluxio]]
*AMASS/DATAMGR from ADIC (Was available on SGI IRIX, Sun and HP-UX)
*[[IBM 3850]] IBM 3850 Mass Storage Facility
*IBM DFSMS for z/VM<ref>{{cite web |last1=IBM Corporation |title=Abstract for DFSMS/VM Planning Guide |url=https://www.ibm.com/docs/en/zvm/7.1?topic=guide-abstract-dfsmsvm-planning |website=ibm.com |access-date=Sep 16, 2021}}</ref>
*IBM [[Data Facility Storage Management Subsystem (MVS)#DFSMShsm|DFSMShsm]], originally Hierarchical Storage Manager (HSM), 5740-XRB, and later Data Facility Hierarchical Storage Manager Version 2 (DFHSM), 5665-329<ref>{{cite manual
| title = z/OS 2.5 DFSMShsm Storage Administration
| id = SC23-6871-50
| year = 2022
| url = https://www-40.ibm.com/servers/resourcelink/svc00100.nsf/pages/zOSV2R5sc236871/$file/arcf000_v2r5.pdf
| publisher = IBM
| access-date = February 24, 2022
}}
</ref>
*[[IBM Tivoli Storage Manager]] for Space Management (HSM available on [[UNIX]] ([[IBM AIX]], [[HP UX]], [[Solaris (operating system)|Solaris]]) & [[Linux]])
*[[IBM TSM HSM for Windows|IBM Tivoli Storage Manager HSM for Windows]] formerly OpenStore for File Servers (OS4FS) (HSM available on Microsoft [[Windows Server]])
*[[High Performance Storage System|HPSS]] by [http://www.hpss-collaboration.org HPSS collaboration]
*[[Infinite Disk]], an early PC system (defunct)
*[[EMC Corporation|EMC]] [[DiskXtender]], formerly Legato DiskXtender, formerly OTG DiskXtender
*Moonwalk for Windows, NetApp, OES Linux
*[[Oracle Corporation|Oracle]] [[QFS|SAM-QFS]] (Open source under Opensolaris,<ref>[SAM/QFS at OpenSolaris.org [https://web.archive.org/web/20081219143935/http://www.opensolaris.org/os/project/samqfs/]</ref> then proprietary)
*[[Oracle Corporation|Oracle]] [[QFS|HSM]] (Proprietary, renamed from SAM-QFS)
*[[Versity Storage Manager]] for Linux, [[open-core model]] license
*[[Compellent Technologies|Dell Compellent]] Data Progression
*[[Zarafa (software)|Zarafa]] Archiver (component of ZCP, application specific archiving solution marketed as a 'HSM' solution)
*[[Hewlett Packard Enterprise|HPE]] [[Data Management Framework]] (DMF, formerly [[Silicon Graphics International|SGI]] Data Migration Facility) for [[SUSE Linux Enterprise Server|SLES]] and [[Red Hat Enterprise Linux|RHEL]]
* [[Quantum Corporation|Quantum's]] [[StorNext File System|StorNext]]
*[[Apple Inc.|Apple]] [[Fusion Drive]] for [[macOS]]
*[[Microsoft]] [[Features new to Windows 8#Storage|Storage Spaces]] since version shipped with [[Windows Server 2012 R2#Windows Server 2012 R2|Windows Server 2012 R2]]. An older Microsoft product was [[Windows_2000#Server_family_features|Remote Storage]], included with [[Windows 2000]] and [[Windows 2003]].<ref name="MorimotoNoel2008">{{cite book|author1=Rand Morimoto|author2=Michael Noel|author3=Omar Droubi|author4=Ross Mistry |author5=Chris Amaris|title=Windows Server 2008 Unleashed|url=https://books.google.com/books?id=xAz2niEHWmsC&pg=PA938|year=2008|publisher=Sams Publishing|isbn=978-0-13-271563-8|page=938}}</ref><ref>{{Cite web|url=http://windowsitpro.com/storage/remote-storage-service|title=ITPro Today: IT News, How-Tos, Trends, Case Studies, Career Tips, More}}</ref>

==See also==
*[[Active Archive Alliance]]
*[[Archive]]
*[[Backup]]
*[[Hybrid cloud storage]]
*[[Data proliferation]]
*[[Data proliferation]]
*[[Disk storage]]
*[[Disk storage]]
*[[Information Lifecycle Management]]
*[[Information lifecycle management]]
*[[Information repository]]
*[[Information repository]]
*[[Magnetic tape data storage]]
*[[Magnetic tape data storage]]
*[[Repository]]
*[[Memory hierarchy]]
*[[Storage virtualization]]
*[[Storage virtualization]]
*[[Cloud storage gateway]]


==References==
== Implementations ==
{{Notelist-lr}}
* [[IBM Tivoli Storage Manager]] for Space Management (HSM)
* [[OpenStore for File Servers]] by Intercope (resold as IBM TSM for HSM for Windows)
* GRAU ArchiveManager (GAM) by Grau Data Storage for Windows/Linux [http://www.graudatastorage.de]
* [[EMC Corporation|EMC]] [[DiskXtender]], formerly Legato DiskXtender, formerly OTG DiskXtender
* [[Caminosoft Corporation]], [http://www.caminosoft.com/solutions/managed/ Caminosoft Managed Server] Netware/Windows/Linux
* [[Moonwalk]] [http://www.moonwalkinc.com/] Moonwalk (Columbia and Eagle), for NetWare/Windows/Linux
* [[QFS|SAM-QFS]]
* [[CommVault Systems|CommVault]] QiNetix DataMigrator
* [[Silicon Graphics|SGI]] DMF [http://www.sgi.com/products/storage/tech/dmf.html] (Data Migration Facility)
* [[Symantec]] [[VERITAS Software|VERITAS]] [http://www.veritas.com/kvs/ Enterprise Vault] (KVS acquisition and Veritas acquisition)
* [[QStar Technologies Inc|QStar]] [http://www.QStar.com/pro2.html]
* [[Quantum Corporation|Quantum]] StorNext Storage Manager [http://www.quantum.com/stornext/]
* Compellent Data Progression [[Automated Tiered Storage]] [http://www.compellent.com]


{{reflist|30em|refs=

<ref name="Freeman">{{Cite web |title=What's Old Is New Again - Storage Tiering |author=Larry Freeman |url=http://www.snia.org/sites/default/education/tutorials/2012/spring/storman/LarryFreeman_What_Old_Is_New_Again.pdf
{{DEFAULTSORT:*}}
}}</ref>
}}
* {{cite book|first1=Keith|last1=Winnard|first2=Josh|last2=Biondo|date=6 June 2016|publisher=[[IBM Press]]|isbn=9780738455372|lang=en-US|title=DFSMS: From Storage Tears to Storage Tiers|url=https://www.redbooks.ibm.com/abstracts/redp5341.html}}


[[Category:Business software]]
[[Category:Business software]]
[[Category:Computer storage]]
[[Category:Computer data storage]]
[[Category:Content management systems]]
[[Category:Management frameworks]]
[[Category:Information technology management]]

[[de:Hierarchisches Speichermanagement]]
[[fr:Hierarchical Storage Management]]
[[ru:Иерархическое управление носителями]]

Latest revision as of 12:46, 26 October 2024

"System Managed Storage" redirects here. For the IBM implementation, see Data Facility Storage Management Subsystem (MVS) § DFSMShsm.

Hierarchical storage management (HSM), also known as tiered storage,[1] is a data storage and data management technique that automatically moves data between high-cost and low-cost storage media. HSM systems exist because high-speed storage devices, such as solid-state drive arrays, are more expensive (per byte stored) than slower devices, such as hard disk drives, optical discs and magnetic tape drives. While it would be ideal to have all data available on high-speed devices all the time, this is prohibitively expensive for many organizations. Instead, HSM systems store the bulk of the enterprise's data on slower devices, and then copy data to faster disk drives when needed. The HSM system monitors the way data is used and makes best guesses as to which data can safely be moved to slower devices and which data should stay on the fast devices.

HSM may also be used where more robust storage is available for long-term archiving, but this is slow to access. This may be as simple as an off-site backup, for protection against a building fire.

HSM is a long-established concept, dating back to the beginnings of commercial data processing. The techniques used though have changed significantly as new technology becomes available, for both storage and for long-distance communication of large data sets. The scale of measures such as 'size' and 'access time' have changed dramatically. Despite this, many of the underlying concepts keep returning to favour years later, although at much larger or faster scales.[1]

Implementation

[edit]

In a typical HSM scenario, data which is frequently used are stored on warm storage device, such as solid-state disk (SSD). Data that is infrequently accessed is, after some time migrated to a slower, high capacity cold storage tier. If a user does access data which is on the cold storage tier, it is automatically moved back to warm storage. The advantage is that the total amount of stored data can be much larger than the capacity of the warm storage device, but since only rarely used files are on cold storage, most users will usually not notice any slowdown.

Conceptually, HSM is analogous to the cache found in most computer CPUs, where small amounts of expensive SRAM memory running at very high speeds is used to store frequently used data, but the least recently used data is evicted to the slower but much larger main DRAM memory when new data has to be loaded.

In practice, HSM is typically performed by dedicated software, such as IBM Tivoli Storage Manager, or Oracle's SAM-QFS.

The deletion of files from a higher level of the hierarchy (e.g. magnetic disk) after they have been moved to a lower level (e.g. optical media) is sometimes called file grooming.[2]

History

[edit]

Hierarchical Storage Manager (HSM, then DFHSM and finally DFSMShsm) was first[citation needed] implemented by IBM on March 31, 1978 for MVS to reduce the cost of data storage, and to simplify the retrieval of data from slower media. The user would not need to know where the data was stored and how to get it back; the computer would retrieve the data automatically. The only difference to the user was the speed at which data was returned. HSM could originally migrate datasets only to disk volumes and virtual volumes on a IBM 3850 Mass Storage Facility, but a latter release supported magnetic tape volumes for migration level 2 (ML2).

Later, IBM ported HSM to its AIX operating system, and then to other Unix-like operating systems such as Solaris, HP-UX and Linux.

CSIRO Australia's Division of Computing Research implemented an HSM in its DAD (Drums and Display) operating system with its Document Region in the 1960s, with copies of documents being written to 7-track tape and automatic retrieval upon access to the documents.

HSM was also implemented on the DEC VAX/VMS systems and the Alpha/VMS systems. The first implementation date should be readily determined from the VMS System Implementation Manuals or the VMS Product Description Brochures.

More recently, the development of Serial ATA (SATA) disks has created a significant market for three-stage HSM: files are migrated from high-performance Fibre Channel storage area network devices to somewhat slower but much cheaper SATA disk arrays totaling several terabytes or more, and then eventually from the SATA disks to tape.

Use cases

[edit]

HSM is often used for deep archival storage of data to be held long term at low cost. Automated tape robots can silo large quantities of data efficiently with low power consumption.

Some HSM software products allow the user to place portions of data files on high-speed disk cache and the rest on tape. This is used in applications that stream video over the internet—the initial portion of a video is delivered immediately from disk while a robot finds, mounts and streams the rest of the file to the end user. Such a system greatly reduces disk cost for large content provision systems.

HSM software is today used also for tiering between hard disk drives and flash memory, with flash memory being over 30 times faster than magnetic disks, but disks being considerably cheaper.

Algorithms

[edit]

The key factor behind HSM is a data migration policy that controls the file transfers in the system. More precisely, the policy decides which tier a file should be stored in, so that the entire storage system can be well-organized and have a shortest response time to requests. There are several algorithms realizing this process, such as least recently used replacement (LRU),[3] Size-Temperature Replacement(STP), Heuristic Threshold(STEP)[4] etc. In research of recent years, there are also some intelligent policies coming up by using machine learning technologies.[5]

Tiering vs. caching

[edit]

While tiering solutions and caching may look the same on the surface, the fundamental differences lie in the way the faster storage is utilized and the algorithms used to detect and accelerate frequently accessed data.[6]

Caching operates by making a copy of frequently accessed blocks of data, and storing the copy in the faster storage device and use this copy instead of the original data source on the slower, high capacity backend storage. Every time a storage read occurs, the caching software look to see if a copy of this data already exists on the cache and uses that copy, if available. Otherwise, the data is read from the slower, high capacity storage.[6]

Tiering on the other hand operates very differently. Rather than making a copy of frequently accessed data into fast storage, tiering moves data across tiers, for example, by relocating cold data to low cost, high capacity nearline storage devices.[7][6] The basic idea is, mission-critical and highly accesses or "hot" data is stored in expensive medium such as SSD to take advantage of high I/O performance, while nearline or rarely accessed or "cold" data is stored in nearline storage medium such as HDD and tapes which are inexpensive.[8] Thus, the "data temperature" or activity levels determines the primary storage hierarchy.[9]

Implementations

[edit]

See also

[edit]

References

[edit]
  1. ^ a b Larry Freeman. "What's Old Is New Again - Storage Tiering" (PDF).
  2. ^ Patrick M. Dillon; David C. Leonard (1998). Multimedia and the Web from A to Z. ABC-CLIO. p. 116. ISBN 978-1-57356-132-7.
  3. ^ O'Neil, Elizabeth J.; O'Neil, Patrick E.; Weikum, Gerhard (1993-06-01). "The LRU-K page replacement algorithm for database disk buffering". ACM SIGMOD Record. 22 (2): 297–306. doi:10.1145/170036.170081. ISSN 0163-5808. S2CID 207177617.
  4. ^ Verma, A.; Pease, D.; Sharma, U.; Kaplan, M.; Rubas, J.; Jain, R.; Devarakonda, M.; Beigi, M. (2005). "An Architecture for Lifecycle Management in Very Large File Systems". 22nd IEEE / 13th NASA Goddard Conference on Mass Storage Systems and Technologies (MSST'05). Monterey, CA, US: IEEE. pp. 160–168. doi:10.1109/MSST.2005.4. ISBN 978-0-7695-2318-7. S2CID 7082285.
  5. ^ Zhang, Tianru; Hellander, Andreas; Toor, Salman (2022). "Efficient Hierarchical Storage Management Empowered by Reinforcement Learning". IEEE Transactions on Knowledge and Data Engineering: 1–1. doi:10.1109/TKDE.2022.3176753. ISSN 1041-4347.
  6. ^ a b c Brand, Aron (June 20, 2022). "Hot Storage vs Cold Storage: Choosing the Right Tier for Your Data". Medium.com. Retrieved June 20, 2022.
  7. ^ Posey, Brien (November 8, 2016). "Differences between SSD caching and tiering technologies". TechTarget. Retrieved Jun 21, 2022.
  8. ^ Winnard & Biondo 2016, p. 5.
  9. ^ Winnard & Biondo 2016, p. 6.
  10. ^ IBM Corporation. "Abstract for DFSMS/VM Planning Guide". ibm.com. Retrieved Sep 16, 2021.
  11. ^ z/OS 2.5 DFSMShsm Storage Administration (PDF). IBM. 2022. SC23-6871-50. Retrieved February 24, 2022.
  12. ^ [SAM/QFS at OpenSolaris.org [1]
  13. ^ Rand Morimoto; Michael Noel; Omar Droubi; Ross Mistry; Chris Amaris (2008). Windows Server 2008 Unleashed. Sams Publishing. p. 938. ISBN 978-0-13-271563-8.
  14. ^ "ITPro Today: IT News, How-Tos, Trends, Case Studies, Career Tips, More".
Retrieved from "https://en.wikipedia.org/enwiki/w/index.php?title=Hierarchical_storage_management&oldid=1253521722"