SlideShare ist ein Scribd-Unternehmen logo
1 von 44
Andrew Robinson
                           University of Michigan
                         <androbin@umich.edu>


  Redundant Arrays of
Inexpensive Disks (RAID)
     What a cool idea!
Authors
• David A Patterson
• Garth Gibson
• Randy H Katz




Officially published in 1988.
Overview
•   What is RAID?
•   Why bother?
•   What is RAID, really?
•   How well does it work?
•   How’s it holding up?
What is RAID?
• Take a bunch of disks and make them appear
  as one disk.
• Put data on all of them
• Use all at once to gain performance
• Duplicate data to gain reliability
• Buy cheap disks to gain dollars
This seems like a lot of work…

why bother?
Let’s go back to 1987
CPUs and Memory kept getting faster…

• Exponential growth everywhere!
• CPU Performance: 1.4X increase per year
  – More transistors
  – Better architecture
• Memory Performance: 1.4-2X increase per
  year
  – Invention of caches
  – SRAM technology
… but disks did not.
• It’s hard to make things spin exponentially
  faster every year (they tend to fly apart).
• Disk seek time improved at a rate of
  approximately 7% a year.
• Caching had been employed to buffer I/O
  activity, this works reasonably well for
  predictable workloads.
Slow I/O Makes Slow Computers
• Amdahl’s Law describes the impact of only
  improving some pieces, while leaving others.



           1
  S=
                         S – The effective speedup
                         F – Fraction of work in faster mode
     (1- f ) + f / k     K – Speedup while in faster mode
…really slow.
• If applications spend 10% of their time in I/O,
  when computers are 10 times faster, they will
  only appear 5% faster.


         Something needed to be done.
What should we do?
• Single Large Expensive Disks (SLED) are not
  improving fast enough.
• Larger memory or solid state drives weren’t
  practical

• Small personal hard drives are emerging… can
  we do something with those?
Inexpensive Disks Rock
Visual Comparison
Why didn’t someone do this before?
• Standards like SCSI have finally allowed drive
  makers to integrate features seen in
  traditional mainframe controllers.
There is a problem…
• A hundredfold increase in number of disks
  means a hundredfold increase decrease in
  total reliability



                       MTTFSingleDisk
       MTTFDiskArray =
                         nDisks
that’s all really nice, but

what is RAID, really?
A couple levels… a single idea
• RAID manages the tradeoff between
  performance and reliability
• RAID comes in levels (RAID1 to RAID5)
• These levels represent points in the
  performance reliability space
Groups, Disks, and Check Disks
• RAID organizes disks into groups of reliability
• Some of the disks in a group store error
  correcting data

  D = Total disks with data
  G = Disks in a group
  C = Number of check disks in a group
Metrics
• Useable Storage – Percent of storage that
  holds data, excluding parity information
• Performance – Tough to make one number:
  – Reads, Writes, and Read-Modify-Write Access
    Patterns
  – Sequential and Random Data Distribution
RAID1 – The Naive Approach
• Mirroring of all data
• To read:
   – Use either disk
• To write:
   – Send to both disks
     simultaneously


• Minor read
  performance increase.
Evaluation
Pros                         Cons
• Reads can occur            • Useable storage is cut in
  simultaneously               half
• Seek times can improve     • All other performance
  with special controllers     metrics are left the same
• Predictable performance


    Alright for large sequential jobs and transaction
                      processing jobs
RAID2 – Bit Level Striping
• Uses Hamming Code for Error Detection
• Requires many check disks
  – For 10 data disks, 4 check disks
  – For 25 data disks, 5 check disks
• Can detect errors, and determine the at-fault
  disk
RAID2 - Visually
Evaluation
Pros                            Cons
• Better useable storage, 71%   • Dismal small random data
  for G=10, 83% for G=25          access performance: 3-9%
                                  of RAID1 or SLED




   Good for large sequential jobs, bad for transaction
                  processing systems.
RAID3 – Byte Level Striping
• Simpler parity error correction
• Only a single check disk required for error
  detection
• Cannot determine which disk failed, but that’s
  usually pretty obvious
• Transfers of large continuous blocks is good
RAID3
Evaluation
Pros                           Cons
• Even better useable          • Small random data access
  storage, 91% for G=10, 96%     performance: Just as bad as
  for G=25                       RAID2




      Even better for large sequential jobs, bad for
            transaction processing systems.
What is parity?
• Parity is calculated as an XOR of the data
  blocks.
• XOR is reversible:
  – 1011 (A1) XOR 1100 (A2) => 0111 (AP) “parity”
  – 0111 (AP) XOR 1011 (A1) => 1100 (A2)
  – 0111 (AP) XOR 1100 (A2) => 1011 (A1)

• This makes error detection and reconstruction
  possible!
RAID4 - Block Level Striping
• Like RAID3, but more parallelly
• Interleave data at sector level rather than bit
  level
• Allows for servicing of multiple block requests
  by different drives
• Still keeps all the parity information on a
  single drive
RAID4
Evaluation
Pros                            Cons
• Finally better small random   • Small writes, and read-
  access. Reads are fast!         write-modifies are still slow.




    Good for large sequential jobs, still not great for
           transaction processing systems.
RAID5 – Block Level Striping with
          Distributed Parity
• Instead of checksums on a single disk, we
  distribute them across all disks.
• Allows us to support multiple writes per group
RAID5
Evaluation
Pros                            Cons
• Really good usable storage    • Slightly worse write
• Finally decent small random     performance, data must be
  data access performance         written to two disks
  across the board!               simultaneously




Finally, a system that works well for both applications!
sounds complicated,

how well does it work?
As a Whole
• RAID has many different levels that achieve
  different tradeoffs in reliability and
  performance
• Almost all of them, for some (or many) use
  cases will outperform a SLED for the same
  cost.
Read-Modify-Write Per Disk
      Performance
wow, raid sounds awesome,

how’s it holding up?
Arriving back in 2012 now…
RAID has held up remarkably well
• Data centers around the world use RAID
  technology.
• The small, inexpensive disk is the de facto
  standard of storage
• The ideas developed for RAID have been
  applied to many not-RAID things
Some open questions
• What will become of RAID as new, super fast
  storage mediums start to become cost
  effective?
• How does it fit in with massive internet-scale
  storage farms?
Take Aways
• RAID offers significant advantage over SLED for
  the same cost
  – RAID5 offers 10x improvement in performance,
    reliability, and power consumption while reducing size
    of array.
• RAID allows for modular growth (add more disks)
• Cost effective option to meet challenge of
  exponential growth in processor and memory
  speeds
References
• “A Case for Redundant Arrays of Inexpensive
  Disks” by David A Patterson, Garth Gibson,
  and Randy H Katz
• “RAID: A Personal Recollection of How Storage
  Became a System” by Randy H Katz
• Slides by David Luo and Ramasubramanian K.
• Images generously borrowed from Wikipedia
  <http://en.wikipedia.org/wiki/RAID>
Thank you!

Weitere ähnliche Inhalte

Was ist angesagt?

Raid Technology
Raid TechnologyRaid Technology
Raid TechnologyAman Sadhwani
 
RedisConf18 - Ultra Scaling with Redis Enterprise
RedisConf18 - Ultra Scaling with Redis EnterpriseRedisConf18 - Ultra Scaling with Redis Enterprise
RedisConf18 - Ultra Scaling with Redis EnterpriseRedis Labs
 
Vancouver bug enterprise storage and zfs
Vancouver bug   enterprise storage and zfsVancouver bug   enterprise storage and zfs
Vancouver bug enterprise storage and zfsRami Jebara
 
Raid_intro.ppt
Raid_intro.pptRaid_intro.ppt
Raid_intro.pptwebhostingguy
 
How to size up an Apache Cassandra cluster (Training)
How to size up an Apache Cassandra cluster (Training)How to size up an Apache Cassandra cluster (Training)
How to size up an Apache Cassandra cluster (Training)DataStax Academy
 
Webinar: Eventual Consistency != Hopeful Consistency
Webinar: Eventual Consistency != Hopeful ConsistencyWebinar: Eventual Consistency != Hopeful Consistency
Webinar: Eventual Consistency != Hopeful ConsistencyDataStax
 
MySQL Performance Tuning
MySQL Performance TuningMySQL Performance Tuning
MySQL Performance TuningFromDual GmbH
 
CD presentation march 12th, 2018
CD presentation march 12th, 2018CD presentation march 12th, 2018
CD presentation march 12th, 2018Ran Levy
 
CRDTs with Akka Distributed Data
CRDTs with Akka Distributed DataCRDTs with Akka Distributed Data
CRDTs with Akka Distributed DataMarkus Jura
 
Azure + DataStax Enterprise (DSE) Powers Office365 Per User Store
Azure + DataStax Enterprise (DSE) Powers Office365 Per User StoreAzure + DataStax Enterprise (DSE) Powers Office365 Per User Store
Azure + DataStax Enterprise (DSE) Powers Office365 Per User StoreDataStax Academy
 
Apache Cassandra Certification
Apache Cassandra CertificationApache Cassandra Certification
Apache Cassandra CertificationVskills
 
SQL Server Reporting Services Disaster Recovery Webinar
SQL Server Reporting Services Disaster Recovery WebinarSQL Server Reporting Services Disaster Recovery Webinar
SQL Server Reporting Services Disaster Recovery WebinarDenny Lee
 
Introduction to DataStax Enterprise Advanced Replication with Apache Cassandra
Introduction to DataStax Enterprise Advanced Replication with Apache CassandraIntroduction to DataStax Enterprise Advanced Replication with Apache Cassandra
Introduction to DataStax Enterprise Advanced Replication with Apache CassandraDataStax Academy
 

Was ist angesagt? (20)

SEMINAR
SEMINARSEMINAR
SEMINAR
 
Raid
RaidRaid
Raid
 
Raid Technology
Raid TechnologyRaid Technology
Raid Technology
 
Raid
RaidRaid
Raid
 
Raid
RaidRaid
Raid
 
Raid
Raid Raid
Raid
 
RedisConf18 - Ultra Scaling with Redis Enterprise
RedisConf18 - Ultra Scaling with Redis EnterpriseRedisConf18 - Ultra Scaling with Redis Enterprise
RedisConf18 - Ultra Scaling with Redis Enterprise
 
raid technology
raid technologyraid technology
raid technology
 
Vancouver bug enterprise storage and zfs
Vancouver bug   enterprise storage and zfsVancouver bug   enterprise storage and zfs
Vancouver bug enterprise storage and zfs
 
Raid_intro.ppt
Raid_intro.pptRaid_intro.ppt
Raid_intro.ppt
 
How to size up an Apache Cassandra cluster (Training)
How to size up an Apache Cassandra cluster (Training)How to size up an Apache Cassandra cluster (Training)
How to size up an Apache Cassandra cluster (Training)
 
Raid
RaidRaid
Raid
 
Webinar: Eventual Consistency != Hopeful Consistency
Webinar: Eventual Consistency != Hopeful ConsistencyWebinar: Eventual Consistency != Hopeful Consistency
Webinar: Eventual Consistency != Hopeful Consistency
 
MySQL Performance Tuning
MySQL Performance TuningMySQL Performance Tuning
MySQL Performance Tuning
 
CD presentation march 12th, 2018
CD presentation march 12th, 2018CD presentation march 12th, 2018
CD presentation march 12th, 2018
 
CRDTs with Akka Distributed Data
CRDTs with Akka Distributed DataCRDTs with Akka Distributed Data
CRDTs with Akka Distributed Data
 
Azure + DataStax Enterprise (DSE) Powers Office365 Per User Store
Azure + DataStax Enterprise (DSE) Powers Office365 Per User StoreAzure + DataStax Enterprise (DSE) Powers Office365 Per User Store
Azure + DataStax Enterprise (DSE) Powers Office365 Per User Store
 
Apache Cassandra Certification
Apache Cassandra CertificationApache Cassandra Certification
Apache Cassandra Certification
 
SQL Server Reporting Services Disaster Recovery Webinar
SQL Server Reporting Services Disaster Recovery WebinarSQL Server Reporting Services Disaster Recovery Webinar
SQL Server Reporting Services Disaster Recovery Webinar
 
Introduction to DataStax Enterprise Advanced Replication with Apache Cassandra
Introduction to DataStax Enterprise Advanced Replication with Apache CassandraIntroduction to DataStax Enterprise Advanced Replication with Apache Cassandra
Introduction to DataStax Enterprise Advanced Replication with Apache Cassandra
 

Ähnlich wie Overview of Redundant Disk Arrays

Understanding RAID Levels (RAID 0, RAID 1, RAID 2, RAID 3, RAID 4, RAID 5)
Understanding RAID Levels (RAID 0, RAID 1, RAID 2, RAID 3, RAID 4, RAID 5)Understanding RAID Levels (RAID 0, RAID 1, RAID 2, RAID 3, RAID 4, RAID 5)
Understanding RAID Levels (RAID 0, RAID 1, RAID 2, RAID 3, RAID 4, RAID 5)Raid Data Recovery
 
RAID (redundant array of independent disks)
RAID  (redundant array of independent disks)RAID  (redundant array of independent disks)
RAID (redundant array of independent disks)manditalaskar123
 
RAID--16112022-093218am-16022024-061222pm.pdf
RAID--16112022-093218am-16022024-061222pm.pdfRAID--16112022-093218am-16022024-061222pm.pdf
RAID--16112022-093218am-16022024-061222pm.pdfzainm7032
 
Raid+controllers
Raid+controllersRaid+controllers
Raid+controllersismaelhaider
 
Hadoop - Disk Fail In Place (DFIP)
Hadoop - Disk Fail In Place (DFIP)Hadoop - Disk Fail In Place (DFIP)
Hadoop - Disk Fail In Place (DFIP)mundlapudi
 
Secondary Storage - General Knowledge
Secondary Storage - General KnowledgeSecondary Storage - General Knowledge
Secondary Storage - General KnowledgeSamat
 
5 Steps to PostgreSQL Performance
5 Steps to PostgreSQL Performance5 Steps to PostgreSQL Performance
5 Steps to PostgreSQL PerformanceCommand Prompt., Inc
 
RAID LEVELS
RAID LEVELSRAID LEVELS
RAID LEVELSUzair Khan
 
Ceph Day London 2014 - Best Practices for Ceph-powered Implementations of Sto...
Ceph Day London 2014 - Best Practices for Ceph-powered Implementations of Sto...Ceph Day London 2014 - Best Practices for Ceph-powered Implementations of Sto...
Ceph Day London 2014 - Best Practices for Ceph-powered Implementations of Sto...Ceph Community
 
End of RAID as we know it with Ceph Replication
End of RAID as we know it with Ceph ReplicationEnd of RAID as we know it with Ceph Replication
End of RAID as we know it with Ceph ReplicationCeph Community
 
DAS RAID NAS SAN
DAS RAID NAS SANDAS RAID NAS SAN
DAS RAID NAS SANGhassen Smida
 

Ähnlich wie Overview of Redundant Disk Arrays (20)

Understanding RAID Levels (RAID 0, RAID 1, RAID 2, RAID 3, RAID 4, RAID 5)
Understanding RAID Levels (RAID 0, RAID 1, RAID 2, RAID 3, RAID 4, RAID 5)Understanding RAID Levels (RAID 0, RAID 1, RAID 2, RAID 3, RAID 4, RAID 5)
Understanding RAID Levels (RAID 0, RAID 1, RAID 2, RAID 3, RAID 4, RAID 5)
 
Raid
Raid Raid
Raid
 
Raid 5
Raid 5Raid 5
Raid 5
 
RAID (redundant array of independent disks)
RAID  (redundant array of independent disks)RAID  (redundant array of independent disks)
RAID (redundant array of independent disks)
 
RAID--16112022-093218am-16022024-061222pm.pdf
RAID--16112022-093218am-16022024-061222pm.pdfRAID--16112022-093218am-16022024-061222pm.pdf
RAID--16112022-093218am-16022024-061222pm.pdf
 
Raid+controllers
Raid+controllersRaid+controllers
Raid+controllers
 
Hadoop - Disk Fail In Place (DFIP)
Hadoop - Disk Fail In Place (DFIP)Hadoop - Disk Fail In Place (DFIP)
Hadoop - Disk Fail In Place (DFIP)
 
Secondary Storage - General Knowledge
Secondary Storage - General KnowledgeSecondary Storage - General Knowledge
Secondary Storage - General Knowledge
 
Raid 1 3
Raid 1 3Raid 1 3
Raid 1 3
 
RAID
RAIDRAID
RAID
 
Five steps perform_2009 (1)
Five steps perform_2009 (1)Five steps perform_2009 (1)
Five steps perform_2009 (1)
 
5 Steps to PostgreSQL Performance
5 Steps to PostgreSQL Performance5 Steps to PostgreSQL Performance
5 Steps to PostgreSQL Performance
 
Raid
Raid Raid
Raid
 
Class2
Class2Class2
Class2
 
1.2 raid
1.2  raid1.2  raid
1.2 raid
 
RAID LEVELS
RAID LEVELSRAID LEVELS
RAID LEVELS
 
Ceph Day London 2014 - Best Practices for Ceph-powered Implementations of Sto...
Ceph Day London 2014 - Best Practices for Ceph-powered Implementations of Sto...Ceph Day London 2014 - Best Practices for Ceph-powered Implementations of Sto...
Ceph Day London 2014 - Best Practices for Ceph-powered Implementations of Sto...
 
End of RAID as we know it with Ceph Replication
End of RAID as we know it with Ceph ReplicationEnd of RAID as we know it with Ceph Replication
End of RAID as we know it with Ceph Replication
 
SQL 2005 Disk IO Performance
SQL 2005 Disk IO PerformanceSQL 2005 Disk IO Performance
SQL 2005 Disk IO Performance
 
DAS RAID NAS SAN
DAS RAID NAS SANDAS RAID NAS SAN
DAS RAID NAS SAN
 

KĂźrzlich hochgeladen

🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘RTylerCroy
 
Tech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfTech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfhans926745
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoffsammart93
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Enterprise Knowledge
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...apidays
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Scriptwesley chun
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProduct Anonymous
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century educationjfdjdjcjdnsjd
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CVKhem
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationMichael W. Hawkins
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsJoaquim Jorge
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processorsdebabhi2
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUK Journal
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
HTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation StrategiesHTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation StrategiesBoston Institute of Analytics
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...Neo4j
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptxHampshireHUG
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 

KĂźrzlich hochgeladen (20)

🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
Tech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfTech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdf
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
HTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation StrategiesHTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation Strategies
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 

Overview of Redundant Disk Arrays

  • 1. Andrew Robinson University of Michigan <androbin@umich.edu> Redundant Arrays of Inexpensive Disks (RAID) What a cool idea!
  • 2. Authors • David A Patterson • Garth Gibson • Randy H Katz Officially published in 1988.
  • 3. Overview • What is RAID? • Why bother? • What is RAID, really? • How well does it work? • How’s it holding up?
  • 4. What is RAID? • Take a bunch of disks and make them appear as one disk. • Put data on all of them • Use all at once to gain performance • Duplicate data to gain reliability • Buy cheap disks to gain dollars
  • 5. This seems like a lot of work… why bother?
  • 7. CPUs and Memory kept getting faster… • Exponential growth everywhere! • CPU Performance: 1.4X increase per year – More transistors – Better architecture • Memory Performance: 1.4-2X increase per year – Invention of caches – SRAM technology
  • 8. … but disks did not. • It’s hard to make things spin exponentially faster every year (they tend to fly apart). • Disk seek time improved at a rate of approximately 7% a year. • Caching had been employed to buffer I/O activity, this works reasonably well for predictable workloads.
  • 9. Slow I/O Makes Slow Computers • Amdahl’s Law describes the impact of only improving some pieces, while leaving others. 1 S= S – The effective speedup F – Fraction of work in faster mode (1- f ) + f / k K – Speedup while in faster mode
  • 10. …really slow. • If applications spend 10% of their time in I/O, when computers are 10 times faster, they will only appear 5% faster. Something needed to be done.
  • 11. What should we do? • Single Large Expensive Disks (SLED) are not improving fast enough. • Larger memory or solid state drives weren’t practical • Small personal hard drives are emerging… can we do something with those?
  • 14. Why didn’t someone do this before? • Standards like SCSI have finally allowed drive makers to integrate features seen in traditional mainframe controllers.
  • 15. There is a problem… • A hundredfold increase in number of disks means a hundredfold increase decrease in total reliability MTTFSingleDisk MTTFDiskArray = nDisks
  • 16. that’s all really nice, but what is RAID, really?
  • 17. A couple levels… a single idea • RAID manages the tradeoff between performance and reliability • RAID comes in levels (RAID1 to RAID5) • These levels represent points in the performance reliability space
  • 18. Groups, Disks, and Check Disks • RAID organizes disks into groups of reliability • Some of the disks in a group store error correcting data D = Total disks with data G = Disks in a group C = Number of check disks in a group
  • 19. Metrics • Useable Storage – Percent of storage that holds data, excluding parity information • Performance – Tough to make one number: – Reads, Writes, and Read-Modify-Write Access Patterns – Sequential and Random Data Distribution
  • 20. RAID1 – The Naive Approach • Mirroring of all data • To read: – Use either disk • To write: – Send to both disks simultaneously • Minor read performance increase.
  • 21. Evaluation Pros Cons • Reads can occur • Useable storage is cut in simultaneously half • Seek times can improve • All other performance with special controllers metrics are left the same • Predictable performance Alright for large sequential jobs and transaction processing jobs
  • 22. RAID2 – Bit Level Striping • Uses Hamming Code for Error Detection • Requires many check disks – For 10 data disks, 4 check disks – For 25 data disks, 5 check disks • Can detect errors, and determine the at-fault disk
  • 24. Evaluation Pros Cons • Better useable storage, 71% • Dismal small random data for G=10, 83% for G=25 access performance: 3-9% of RAID1 or SLED Good for large sequential jobs, bad for transaction processing systems.
  • 25. RAID3 – Byte Level Striping • Simpler parity error correction • Only a single check disk required for error detection • Cannot determine which disk failed, but that’s usually pretty obvious • Transfers of large continuous blocks is good
  • 26. RAID3
  • 27. Evaluation Pros Cons • Even better useable • Small random data access storage, 91% for G=10, 96% performance: Just as bad as for G=25 RAID2 Even better for large sequential jobs, bad for transaction processing systems.
  • 28. What is parity? • Parity is calculated as an XOR of the data blocks. • XOR is reversible: – 1011 (A1) XOR 1100 (A2) => 0111 (AP) “parity” – 0111 (AP) XOR 1011 (A1) => 1100 (A2) – 0111 (AP) XOR 1100 (A2) => 1011 (A1) • This makes error detection and reconstruction possible!
  • 29. RAID4 - Block Level Striping • Like RAID3, but more parallelly • Interleave data at sector level rather than bit level • Allows for servicing of multiple block requests by different drives • Still keeps all the parity information on a single drive
  • 30. RAID4
  • 31. Evaluation Pros Cons • Finally better small random • Small writes, and read- access. Reads are fast! write-modifies are still slow. Good for large sequential jobs, still not great for transaction processing systems.
  • 32. RAID5 – Block Level Striping with Distributed Parity • Instead of checksums on a single disk, we distribute them across all disks. • Allows us to support multiple writes per group
  • 33. RAID5
  • 34. Evaluation Pros Cons • Really good usable storage • Slightly worse write • Finally decent small random performance, data must be data access performance written to two disks across the board! simultaneously Finally, a system that works well for both applications!
  • 36. As a Whole • RAID has many different levels that achieve different tradeoffs in reliability and performance • Almost all of them, for some (or many) use cases will outperform a SLED for the same cost.
  • 38. wow, raid sounds awesome, how’s it holding up?
  • 39. Arriving back in 2012 now…
  • 40. RAID has held up remarkably well • Data centers around the world use RAID technology. • The small, inexpensive disk is the de facto standard of storage • The ideas developed for RAID have been applied to many not-RAID things
  • 41. Some open questions • What will become of RAID as new, super fast storage mediums start to become cost effective? • How does it fit in with massive internet-scale storage farms?
  • 42. Take Aways • RAID offers significant advantage over SLED for the same cost – RAID5 offers 10x improvement in performance, reliability, and power consumption while reducing size of array. • RAID allows for modular growth (add more disks) • Cost effective option to meet challenge of exponential growth in processor and memory speeds
  • 43. References • “A Case for Redundant Arrays of Inexpensive Disks” by David A Patterson, Garth Gibson, and Randy H Katz • “RAID: A Personal Recollection of How Storage Became a System” by Randy H Katz • Slides by David Luo and Ramasubramanian K. • Images generously borrowed from Wikipedia <http://en.wikipedia.org/wiki/RAID>

Hinweis der Redaktion

  1. ----- Meeting Notes (1/21/12 13:53) -----Invented around 1987.
  2. ----- Meeting Notes (1/21/12 13:53) -----Patterson - BerkeleyGibson – Currently at CMUKatz - Berkeley
  3. Exploits clever XOR trick to not require reading data off of all the disks to recalculate parity.Each small write requires 2 disks and 4 accesses, 2 reads and 2 writes.Each small read requires only 1 access.