SlideShare ist ein Scribd-Unternehmen logo
1 von 31
Downloaden Sie, um offline zu lesen
Beyond Tuning:
Getting the most out of your
     Oracle application
 Mike Ault, Oracle Guru, TMS Inc.



     Texas Memory Systems, Inc. - The World's Fastest Storage®
Michael R. Ault
         Oracle Guru

- Nuclear Navy 6 years
- Nuclear Chemist/Programmer 10 years
- Kennedy Western University Graduate
- Bachelors Degree Computer Science
- Certified in all Oracle Versions Since 6
- Oracle DBA, author, since 1990


   Texas Memory Systems, Inc. - The World's Fastest Storage®
Books by Michael R. Ault




 Texas Memory Systems, Inc. - The World's Fastest Storage®
Statspackanalyzer.com

     Free Statspack/AWR Analysis
               Sponsored by Texas Memory Systems


-Looks for IO bottlenecks and other
configuration issues.
-Straightforward tuning advice



    Texas Memory Systems, Inc. - The World's Fastest Storage®
Introduction
            Ok, You’ve Tuned:
• Indexes
• Partitioning
• Parallel Query
• Memory areas
• Sort and Hash areas
• OS
• Bandwidth
 But…Performance is still not satisfactory!
          Texas Memory Systems, Inc. - The World's Fastest Storage®
Introduction
• What now?
• Tune or replace IO subsystem?




          Texas Memory Systems, Inc. - The World's Fastest Storage®
What Now?
• If you don’t have CPU or Memory Issues
• If you don’t have SQL tuning issues
  – Or, can’t tune due to third party issues
  – Or, can’t use automatic Oracle tuning
  – Or, automatic tuning still results in IO stress
• Look at supplementing or replacing IO
  subsystem.


            Texas Memory Systems, Inc. - The World's Fastest Storage®
Basic IO Subsystems
• JBOD – Just a Bunch of Disks
• Basic SAN – Stripe and Mirror or RAID5
• Advanced SAN – Basic SAN plus cache, plus hot
  blocking
• Advanced SAN + SSD – Tiered approach with hot
  files on SSD or SSD as advanced caching
• Pure SSD – either DDR+Flash or Pure Flash




           Texas Memory Systems, Inc. - The World's Fastest Storage®
Problems with Striping
• Most JBOD or SAN will be fronted by a
  RAID controller or software such as ASM
• Stripe widths are limited to 64k in most
  controllers
• ASM uses 1 megabyte
• Small stripe widths cause IO blocking



           Texas Memory Systems, Inc. - The World's Fastest Storage®
IO Blocking




Texas Memory Systems, Inc. - The World's Fastest Storage®
Non-Blocking




Texas Memory Systems, Inc. - The World's Fastest Storage®
So….
• Maximize bandwidth
    – More HBAs
    – Infiniband
    – Most SANs can’t utilize existing bandwidth due to disk limits
•   Use luns to map hot/cold disk areas (11g ASM does this)
•   Tune RAID set stripe depth to IO size
•   Tune to max expected IO size
•   Reduces blocking reads and writes
    – Oracle says it doesn’t block reads
    – This is internal to Oracle once block is in cache
    – Blocking reads are due to physical issues with disk



                  Texas Memory Systems, Inc. - The World's Fastest Storage®
What causes blocking?




Rotational Latency                             Armature Motion
                                               (positional) Latency


              Texas Memory Systems, Inc. - The World's Fastest Storage®
Other IO Issues
• Redo log issues
  – Solve by moving or isolating redo logs
• Archive issues
  – Improve tuning of archive location
     • Network or Storage Network
     • Faster IO in archive location
• Temporary Issues
  – Tune sorts, GTT, Bitmap, etc.
  – Move temp areas to lower latency write IO

             Texas Memory Systems, Inc. - The World's Fastest Storage®
How do I tell if
          My System has Issues?
• OEM, AWR or Statspack
  – Top waits are IO related (DB file, Log)
  – Average latencies in Tablespoace IO area are
    >5-10 ms
  – Average latencies are 2-5 ms and IO waits
    dominate wait profile




            Texas Memory Systems, Inc. - The World's Fastest Storage®
How do SANs Overcome These
         Forms of Latency?
• More disks – May not help latency
• Caching into Flash or DDR – Good until
  cache is flooded
• Selective files (hot) moved to Flash
• Hot blocks moved to faster portions of
  disk – still limited to 2-5 ms



           Texas Memory Systems, Inc. - The World's Fastest Storage®
What are the Pros and Cons?
• JBOD
  – Pros
    • Easy to implement
    • Easy to add capacity
  – Cons
    •   Difficult to manage
    •   Requires third party or OS tools
    •   Doesn’t handle hot blocks/files
    •   Latency issues
    •   Bandwidth issues

              Texas Memory Systems, Inc. - The World's Fastest Storage®
What are the Pros and Cons?
• Simple SAN
  – Pros
    • Easy to manage
    • Easy to expand
  – Cons
    •   Requires licenses for management software
    •   Doesn’t address hot blocks/files
    •   Still has latency issues
    •   Bandwidth issues

              Texas Memory Systems, Inc. - The World's Fastest Storage®
What are the Pros and Cons?
• Advanced SAN
  – Pros
    • Relatively easy to manage
    • Handles hot blocks/files
  – Cons
    •   Expensive
    •   Expensive to expand
    •   Licensing of software and support costs
    •   Still has latency issues
    •   Still has bandwidth issues

              Texas Memory Systems, Inc. - The World's Fastest Storage®
What are the Pros and Cons?
• Advanced SAN with Caching
  – Pros
    • Easy to manage
    • Handles hot blocking/files
    • Provides some relief from latency issues
  – Cons
    •   Once cache is flooded has latency issues
    •   Expensive to implement and expand
    •   Licensing of software
    •   May have bandwidth issues

              Texas Memory Systems, Inc. - The World's Fastest Storage®
What are the Pros and Cons?
• Advanced San with SSD
  – Pros
    • Easy to manage
    • Solves most latency issues up to a point
    • Solves hot blocking issues
  – Cons
    •   Expensive to implement and expand
    •   License of software costs
    •   Usually shoehorns SSDs into existing architecture
    •   Bandwidth issues

              Texas Memory Systems, Inc. - The World's Fastest Storage®
What are the Pros and Cons?
• Mixed DDR and Flash
  – Pros
    •   Tier solution for hot blocks
    •   Usually has outstanding latency
    •   Usually has great bandwidth
    •   Usually Automatically managed
  – Cons
    • Expensive due to DDR
    • DDR requires battery backup if used as a storage
      tier
    • License costs


              Texas Memory Systems, Inc. - The World's Fastest Storage®
What are the Pros and Cons?
• Pure Flash
  – Pros
     •   Usually doesn’t require tiering
     •   Great Latency
     •   Using eMLC – Lower costs than SLC or DDR
     •   Easily managed
     •   Easily expanded
  – Cons
     • More expensive than JBOD, less expensive than
       Advanced SAN
     • Needs management software such as ASM

               Texas Memory Systems, Inc. - The World's Fastest Storage®
How About some Numbers?




     IOPS Comparison for Various SANs
   (Source: www.storageperformance.org)

       Texas Memory Systems, Inc. - The World's Fastest Storage®
Looking Forward
•   You have tuned
•   You have tuned the existing IO subsystem
•   Performance is still borderline
•   How do you determine what system
    should be next?




             Texas Memory Systems, Inc. - The World's Fastest Storage®
Object Intensity
•Combines both throughput and capacity
requirements
•IOPS/GB
•At a high enough IOPS/GB SSD is the cheapest
solution
•At a low enough IOPS/GB Capacity oriented disk
drives meet the performance requirement
•In between is performance optimized drives (15K
RPM)

            Texas Memory Systems, Inc. - The World's Fastest Storage®
Based on performance AND price
                      per GB

                                                                          SSD
                                                                        Territory




                              Fast HDD
                              Territory




                         Capacity Oriented
                           HDD Territory




With eMLC the ratio is now around 1 IOPS/GB or less!
                  Texas Memory Systems, Inc. - The World's Fastest Storage®
The Adjusted Storage Value Index
• Takes into account:
  –   Cost (USD)
  –   Warrantee (years)
  –   Capacity (Terabytes)
  –   Performance (IOPS)
  –   Latency (ms) (not in original SVI)
• The higher the number, the better the
  value

              Texas Memory Systems, Inc. - The World's Fastest Storage®
Calculation of ASVI
Adjusted Storage Value Index =

(TUC*IOPS*WY)/(cost*L)

Where:

TUC      = Total usable capacity in Terabytes
IOPS     = Validated IOs per second (SPC-1 results for
   example)
WY= Warranty years (or years of paid maintenance if added
   to cost)
Cost     = Cost of validated system
L        = Latency at measured IOPS level




         Texas Memory Systems, Inc. - The World's Fastest Storage®
Comparison of Storage Values
                          Adjusted Storage Value Index

       20.0000
       18.0000
       16.0000
       14.0000
       12.0000
ASVI




       10.0000
        8.0000
        6.0000
        4.0000
        2.0000
        0.0000

                                   d




                                                                                   O
                                   0

                                   0




                                                                             0
                                  ar

                                 re




                                                                            80
                                   0




                                   0
                                 2s




                                                             r
                                en
                                40




                                                            lla




                                                                          62
                                60
                                50




                                                                                 XI
                               17
                               co
                              3p




                              6n




                                                                         67
                                                          Pi
                             rtr
                            S5
                            X8


                             i2




                            S3




                                                                        n
                            ta




                           fo
                          ch




                         00




                                                                      Sa
                                                               N
                        Da


                          D




                        FA
                         ei




                                                             SU
                        In
                       ta
                       su




                      87




                                                                     m
                    aw




                   pp
                   Hi




                                                                  Ra
                   jit




                 ds
                Hu
                Fu




                tA
               M




             Ne
             IB




                                        Manufacturer
                                                                                 ASVI/Manufacturer

                  All data taken from published SPC-1 Results
                  Texas Memory Systems, Inc. - The World's Fastest Storage®
Summary
• Once all other tuning is done, tune IO
• Low latency high bandwidth architectures
  give the best performance
• Almost all advancements in SAN
  technology are to overcome rotating disk
  limitations
• Pure SSD solutions (at least at the main
  level) are the future

           Texas Memory Systems, Inc. - The World's Fastest Storage®

Weitere ähnliche Inhalte

Was ist angesagt?

Sql saturday powerpoint dc_san
Sql saturday powerpoint dc_sanSql saturday powerpoint dc_san
Sql saturday powerpoint dc_sanJoseph D'Antoni
 
PostgreSQL Portland Performance Practice Project - Database Test 2 Filesystem...
PostgreSQL Portland Performance Practice Project - Database Test 2 Filesystem...PostgreSQL Portland Performance Practice Project - Database Test 2 Filesystem...
PostgreSQL Portland Performance Practice Project - Database Test 2 Filesystem...Mark Wong
 
Performance Whack A Mole
Performance Whack A MolePerformance Whack A Mole
Performance Whack A Moleoscon2007
 
Exadata 12c New Features RMOUG
Exadata 12c New Features RMOUGExadata 12c New Features RMOUG
Exadata 12c New Features RMOUGFuad Arshad
 
Strata London 2019 Scaling Impala
Strata London 2019 Scaling ImpalaStrata London 2019 Scaling Impala
Strata London 2019 Scaling ImpalaManish Maheshwari
 
High Performance Hardware for Data Analysis
High Performance Hardware for Data AnalysisHigh Performance Hardware for Data Analysis
High Performance Hardware for Data AnalysisMike Pittaro
 
High Performance Hardware for Data Analysis
High Performance Hardware for Data AnalysisHigh Performance Hardware for Data Analysis
High Performance Hardware for Data AnalysisMike Pittaro
 
SSDs - Improving Performance of Storage Arrays
SSDs - Improving Performance of Storage ArraysSSDs - Improving Performance of Storage Arrays
SSDs - Improving Performance of Storage Arraysnomathjobs
 
Linux and H/W optimizations for MySQL
Linux and H/W optimizations for MySQLLinux and H/W optimizations for MySQL
Linux and H/W optimizations for MySQLYoshinori Matsunobu
 
Raid data recovery Tips
Raid data recovery TipsRaid data recovery Tips
Raid data recovery TipsHone Software
 
Performance evolution of raid
Performance evolution of raidPerformance evolution of raid
Performance evolution of raidZubair Sami
 
Presentation implementing oracle asm successfully
Presentation    implementing oracle asm successfullyPresentation    implementing oracle asm successfully
Presentation implementing oracle asm successfullyxKinAnx
 
Prepare for the Worst: Reliable Data Protection with Oracle RMAN and Oracle D...
Prepare for the Worst: Reliable Data Protection with Oracle RMAN and Oracle D...Prepare for the Worst: Reliable Data Protection with Oracle RMAN and Oracle D...
Prepare for the Worst: Reliable Data Protection with Oracle RMAN and Oracle D...Szymon Skorupinski
 

Was ist angesagt? (20)

Raid
RaidRaid
Raid
 
Sql saturday powerpoint dc_san
Sql saturday powerpoint dc_sanSql saturday powerpoint dc_san
Sql saturday powerpoint dc_san
 
PostgreSQL Portland Performance Practice Project - Database Test 2 Filesystem...
PostgreSQL Portland Performance Practice Project - Database Test 2 Filesystem...PostgreSQL Portland Performance Practice Project - Database Test 2 Filesystem...
PostgreSQL Portland Performance Practice Project - Database Test 2 Filesystem...
 
Performance Whack A Mole
Performance Whack A MolePerformance Whack A Mole
Performance Whack A Mole
 
Exadata 12c New Features RMOUG
Exadata 12c New Features RMOUGExadata 12c New Features RMOUG
Exadata 12c New Features RMOUG
 
Raid
RaidRaid
Raid
 
Strata London 2019 Scaling Impala
Strata London 2019 Scaling ImpalaStrata London 2019 Scaling Impala
Strata London 2019 Scaling Impala
 
High Performance Hardware for Data Analysis
High Performance Hardware for Data AnalysisHigh Performance Hardware for Data Analysis
High Performance Hardware for Data Analysis
 
SEMINAR
SEMINARSEMINAR
SEMINAR
 
Raid_intro.ppt
Raid_intro.pptRaid_intro.ppt
Raid_intro.ppt
 
Raid
RaidRaid
Raid
 
High Performance Hardware for Data Analysis
High Performance Hardware for Data AnalysisHigh Performance Hardware for Data Analysis
High Performance Hardware for Data Analysis
 
SSDs - Improving Performance of Storage Arrays
SSDs - Improving Performance of Storage ArraysSSDs - Improving Performance of Storage Arrays
SSDs - Improving Performance of Storage Arrays
 
Linux and H/W optimizations for MySQL
Linux and H/W optimizations for MySQLLinux and H/W optimizations for MySQL
Linux and H/W optimizations for MySQL
 
Oracle Exadata X2-8: A Critical Review
Oracle Exadata X2-8: A Critical ReviewOracle Exadata X2-8: A Critical Review
Oracle Exadata X2-8: A Critical Review
 
Raid level 4
Raid level 4Raid level 4
Raid level 4
 
Raid data recovery Tips
Raid data recovery TipsRaid data recovery Tips
Raid data recovery Tips
 
Performance evolution of raid
Performance evolution of raidPerformance evolution of raid
Performance evolution of raid
 
Presentation implementing oracle asm successfully
Presentation    implementing oracle asm successfullyPresentation    implementing oracle asm successfully
Presentation implementing oracle asm successfully
 
Prepare for the Worst: Reliable Data Protection with Oracle RMAN and Oracle D...
Prepare for the Worst: Reliable Data Protection with Oracle RMAN and Oracle D...Prepare for the Worst: Reliable Data Protection with Oracle RMAN and Oracle D...
Prepare for the Worst: Reliable Data Protection with Oracle RMAN and Oracle D...
 

Andere mochten auch

Spiceworks Interop 2012
Spiceworks Interop 2012Spiceworks Interop 2012
Spiceworks Interop 2012Auskosh
 
Nonlinear power point
Nonlinear power pointNonlinear power point
Nonlinear power pointSchmity50
 
Las clases de energía
Las clases de energíaLas clases de energía
Las clases de energíamayi12
 
La energía y sus fuentes
La energía y sus fuentes La energía y sus fuentes
La energía y sus fuentes mayi12
 
Модули в zend framework 2.ростислав михайлив
Модули в zend framework 2.ростислав михайливМодули в zend framework 2.ростислав михайлив
Модули в zend framework 2.ростислав михайливAndrey Tokarchuk
 
Edmonton oilers ppt
Edmonton oilers pptEdmonton oilers ppt
Edmonton oilers pptLeoneC717
 
7 mediakasvatus ja_ops
7 mediakasvatus ja_ops7 mediakasvatus ja_ops
7 mediakasvatus ja_opsMikko Horila
 
Ten Things You May Have Not Known About Your Chamber
Ten Things You May Have Not Known About Your ChamberTen Things You May Have Not Known About Your Chamber
Ten Things You May Have Not Known About Your ChamberKristen Smith
 
Presentation on Quarter-Cent Sales Tax
Presentation on Quarter-Cent Sales TaxPresentation on Quarter-Cent Sales Tax
Presentation on Quarter-Cent Sales TaxKristen Smith
 
Presentation to UNC Employee Forum
Presentation to UNC Employee ForumPresentation to UNC Employee Forum
Presentation to UNC Employee ForumKristen Smith
 
ΑΝΤΑΓΩΝΙΣΤΙΚΟΤΗΤΑ ΚΑΙ ΑΝΑΠΤΥΞΗ ΤΗΣ ΕΛΛΗΝΙΚΗΣ ΟΙΚΟΝΟΜΙΑΣ ΥΠΟ ΤΟ ΠΡΙΣΜΑ ΤΗΣ ΕΣΩ...
ΑΝΤΑΓΩΝΙΣΤΙΚΟΤΗΤΑ ΚΑΙ ΑΝΑΠΤΥΞΗ ΤΗΣ ΕΛΛΗΝΙΚΗΣ ΟΙΚΟΝΟΜΙΑΣ ΥΠΟ ΤΟ ΠΡΙΣΜΑ ΤΗΣ ΕΣΩ...ΑΝΤΑΓΩΝΙΣΤΙΚΟΤΗΤΑ ΚΑΙ ΑΝΑΠΤΥΞΗ ΤΗΣ ΕΛΛΗΝΙΚΗΣ ΟΙΚΟΝΟΜΙΑΣ ΥΠΟ ΤΟ ΠΡΙΣΜΑ ΤΗΣ ΕΣΩ...
ΑΝΤΑΓΩΝΙΣΤΙΚΟΤΗΤΑ ΚΑΙ ΑΝΑΠΤΥΞΗ ΤΗΣ ΕΛΛΗΝΙΚΗΣ ΟΙΚΟΝΟΜΙΑΣ ΥΠΟ ΤΟ ΠΡΙΣΜΑ ΤΗΣ ΕΣΩ...onned-economy
 
Tour of Spiceworks 6: Partner Edition
Tour of Spiceworks 6: Partner EditionTour of Spiceworks 6: Partner Edition
Tour of Spiceworks 6: Partner EditionAuskosh
 
Conflict resolution
Conflict resolutionConflict resolution
Conflict resolutionsharonfajou
 

Andere mochten auch (20)

Spiceworks Interop 2012
Spiceworks Interop 2012Spiceworks Interop 2012
Spiceworks Interop 2012
 
Nonlinear power point
Nonlinear power pointNonlinear power point
Nonlinear power point
 
Las clases de energía
Las clases de energíaLas clases de energía
Las clases de energía
 
La energía y sus fuentes
La energía y sus fuentes La energía y sus fuentes
La energía y sus fuentes
 
Модули в zend framework 2.ростислав михайлив
Модули в zend framework 2.ростислав михайливМодули в zend framework 2.ростислав михайлив
Модули в zend framework 2.ростислав михайлив
 
Edmonton oilers ppt
Edmonton oilers pptEdmonton oilers ppt
Edmonton oilers ppt
 
7 mediakasvatus ja_ops
7 mediakasvatus ja_ops7 mediakasvatus ja_ops
7 mediakasvatus ja_ops
 
Ten Things You May Have Not Known About Your Chamber
Ten Things You May Have Not Known About Your ChamberTen Things You May Have Not Known About Your Chamber
Ten Things You May Have Not Known About Your Chamber
 
Algebra
AlgebraAlgebra
Algebra
 
Im gnueva
Im gnuevaIm gnueva
Im gnueva
 
Food+of+the+incas
Food+of+the+incasFood+of+the+incas
Food+of+the+incas
 
Movement
MovementMovement
Movement
 
Presentation on Quarter-Cent Sales Tax
Presentation on Quarter-Cent Sales TaxPresentation on Quarter-Cent Sales Tax
Presentation on Quarter-Cent Sales Tax
 
Presentation to UNC Employee Forum
Presentation to UNC Employee ForumPresentation to UNC Employee Forum
Presentation to UNC Employee Forum
 
Rcl
RclRcl
Rcl
 
Slide data logging
Slide data logging Slide data logging
Slide data logging
 
ΑΝΤΑΓΩΝΙΣΤΙΚΟΤΗΤΑ ΚΑΙ ΑΝΑΠΤΥΞΗ ΤΗΣ ΕΛΛΗΝΙΚΗΣ ΟΙΚΟΝΟΜΙΑΣ ΥΠΟ ΤΟ ΠΡΙΣΜΑ ΤΗΣ ΕΣΩ...
ΑΝΤΑΓΩΝΙΣΤΙΚΟΤΗΤΑ ΚΑΙ ΑΝΑΠΤΥΞΗ ΤΗΣ ΕΛΛΗΝΙΚΗΣ ΟΙΚΟΝΟΜΙΑΣ ΥΠΟ ΤΟ ΠΡΙΣΜΑ ΤΗΣ ΕΣΩ...ΑΝΤΑΓΩΝΙΣΤΙΚΟΤΗΤΑ ΚΑΙ ΑΝΑΠΤΥΞΗ ΤΗΣ ΕΛΛΗΝΙΚΗΣ ΟΙΚΟΝΟΜΙΑΣ ΥΠΟ ΤΟ ΠΡΙΣΜΑ ΤΗΣ ΕΣΩ...
ΑΝΤΑΓΩΝΙΣΤΙΚΟΤΗΤΑ ΚΑΙ ΑΝΑΠΤΥΞΗ ΤΗΣ ΕΛΛΗΝΙΚΗΣ ΟΙΚΟΝΟΜΙΑΣ ΥΠΟ ΤΟ ΠΡΙΣΜΑ ΤΗΣ ΕΣΩ...
 
Tour of Spiceworks 6: Partner Edition
Tour of Spiceworks 6: Partner EditionTour of Spiceworks 6: Partner Edition
Tour of Spiceworks 6: Partner Edition
 
Conflict resolution
Conflict resolutionConflict resolution
Conflict resolution
 
Fazendavinicius
FazendaviniciusFazendavinicius
Fazendavinicius
 

Ähnlich wie Beyond Tuning: Getting the most out of your Oracle Application

Deploying ssd in the data center 2014
Deploying ssd in the data center 2014Deploying ssd in the data center 2014
Deploying ssd in the data center 2014Howard Marks
 
Presentation database on flash
Presentation   database on flashPresentation   database on flash
Presentation database on flashxKinAnx
 
2015 deploying flash in the data center
2015 deploying flash in the data center2015 deploying flash in the data center
2015 deploying flash in the data centerHoward Marks
 
2015 deploying flash in the data center
2015 deploying flash in the data center2015 deploying flash in the data center
2015 deploying flash in the data centerHoward Marks
 
IMC Summit 2016 Breakout - Per Minoborg - Work with Multiple Hot Terabytes in...
IMC Summit 2016 Breakout - Per Minoborg - Work with Multiple Hot Terabytes in...IMC Summit 2016 Breakout - Per Minoborg - Work with Multiple Hot Terabytes in...
IMC Summit 2016 Breakout - Per Minoborg - Work with Multiple Hot Terabytes in...In-Memory Computing Summit
 
Building Data Pipelines with SMACK: Designing Storage Strategies for Scale an...
Building Data Pipelines with SMACK: Designing Storage Strategies for Scale an...Building Data Pipelines with SMACK: Designing Storage Strategies for Scale an...
Building Data Pipelines with SMACK: Designing Storage Strategies for Scale an...DataStax
 
HBase: Extreme Makeover
HBase: Extreme MakeoverHBase: Extreme Makeover
HBase: Extreme MakeoverHBaseCon
 
Best Practices with PostgreSQL on Solaris
Best Practices with PostgreSQL on SolarisBest Practices with PostgreSQL on Solaris
Best Practices with PostgreSQL on SolarisJignesh Shah
 
Výhody a benefity nasazení Oracle Database Appliance
Výhody a benefity nasazení Oracle Database ApplianceVýhody a benefity nasazení Oracle Database Appliance
Výhody a benefity nasazení Oracle Database ApplianceMarketingArrowECS_CZ
 
Storage talk
Storage talkStorage talk
Storage talkchristkv
 
VMworld 2013: Just Because You Could, Doesn't Mean You Should: Lessons Learne...
VMworld 2013: Just Because You Could, Doesn't Mean You Should: Lessons Learne...VMworld 2013: Just Because You Could, Doesn't Mean You Should: Lessons Learne...
VMworld 2013: Just Because You Could, Doesn't Mean You Should: Lessons Learne...VMworld
 
Army of arm - NYC downtown tech meetup
Army of arm - NYC downtown tech meetupArmy of arm - NYC downtown tech meetup
Army of arm - NYC downtown tech meetupAndy Pernsteiner
 
Red Hat Storage Day Dallas - Red Hat Ceph Storage Acceleration Utilizing Flas...
Red Hat Storage Day Dallas - Red Hat Ceph Storage Acceleration Utilizing Flas...Red Hat Storage Day Dallas - Red Hat Ceph Storage Acceleration Utilizing Flas...
Red Hat Storage Day Dallas - Red Hat Ceph Storage Acceleration Utilizing Flas...Red_Hat_Storage
 
Need for Speed: Using Flash Storage to Optimise Performance and Reduce Costs
Need for Speed: Using Flash Storage to Optimise Performance and Reduce CostsNeed for Speed: Using Flash Storage to Optimise Performance and Reduce Costs
Need for Speed: Using Flash Storage to Optimise Performance and Reduce CostsNetApp
 
S016828 storage-tiering-nola-v1710b
S016828 storage-tiering-nola-v1710bS016828 storage-tiering-nola-v1710b
S016828 storage-tiering-nola-v1710bTony Pearson
 
Nimble storage investor_deck_public
Nimble storage investor_deck_publicNimble storage investor_deck_public
Nimble storage investor_deck_publicSequoia Capital
 
Is This Really a SAN Problem? Understanding the Performance of Your IO Subsy...
Is This Really a SAN Problem? Understanding the Performance of  Your IO Subsy...Is This Really a SAN Problem? Understanding the Performance of  Your IO Subsy...
Is This Really a SAN Problem? Understanding the Performance of Your IO Subsy...Embarcadero Technologies
 
Percona live linux filesystems and my sql
Percona live   linux filesystems and my sqlPercona live   linux filesystems and my sql
Percona live linux filesystems and my sqlMichael Zhang
 

Ähnlich wie Beyond Tuning: Getting the most out of your Oracle Application (20)

Deploying ssd in the data center 2014
Deploying ssd in the data center 2014Deploying ssd in the data center 2014
Deploying ssd in the data center 2014
 
Presentation database on flash
Presentation   database on flashPresentation   database on flash
Presentation database on flash
 
2015 deploying flash in the data center
2015 deploying flash in the data center2015 deploying flash in the data center
2015 deploying flash in the data center
 
2015 deploying flash in the data center
2015 deploying flash in the data center2015 deploying flash in the data center
2015 deploying flash in the data center
 
IMC Summit 2016 Breakout - Per Minoborg - Work with Multiple Hot Terabytes in...
IMC Summit 2016 Breakout - Per Minoborg - Work with Multiple Hot Terabytes in...IMC Summit 2016 Breakout - Per Minoborg - Work with Multiple Hot Terabytes in...
IMC Summit 2016 Breakout - Per Minoborg - Work with Multiple Hot Terabytes in...
 
Building Data Pipelines with SMACK: Designing Storage Strategies for Scale an...
Building Data Pipelines with SMACK: Designing Storage Strategies for Scale an...Building Data Pipelines with SMACK: Designing Storage Strategies for Scale an...
Building Data Pipelines with SMACK: Designing Storage Strategies for Scale an...
 
Thiru
ThiruThiru
Thiru
 
HBase: Extreme Makeover
HBase: Extreme MakeoverHBase: Extreme Makeover
HBase: Extreme Makeover
 
Best Practices with PostgreSQL on Solaris
Best Practices with PostgreSQL on SolarisBest Practices with PostgreSQL on Solaris
Best Practices with PostgreSQL on Solaris
 
Výhody a benefity nasazení Oracle Database Appliance
Výhody a benefity nasazení Oracle Database ApplianceVýhody a benefity nasazení Oracle Database Appliance
Výhody a benefity nasazení Oracle Database Appliance
 
Storage talk
Storage talkStorage talk
Storage talk
 
VMworld 2013: Just Because You Could, Doesn't Mean You Should: Lessons Learne...
VMworld 2013: Just Because You Could, Doesn't Mean You Should: Lessons Learne...VMworld 2013: Just Because You Could, Doesn't Mean You Should: Lessons Learne...
VMworld 2013: Just Because You Could, Doesn't Mean You Should: Lessons Learne...
 
Army of arm - NYC downtown tech meetup
Army of arm - NYC downtown tech meetupArmy of arm - NYC downtown tech meetup
Army of arm - NYC downtown tech meetup
 
Red Hat Storage Day Dallas - Red Hat Ceph Storage Acceleration Utilizing Flas...
Red Hat Storage Day Dallas - Red Hat Ceph Storage Acceleration Utilizing Flas...Red Hat Storage Day Dallas - Red Hat Ceph Storage Acceleration Utilizing Flas...
Red Hat Storage Day Dallas - Red Hat Ceph Storage Acceleration Utilizing Flas...
 
Need for Speed: Using Flash Storage to Optimise Performance and Reduce Costs
Need for Speed: Using Flash Storage to Optimise Performance and Reduce CostsNeed for Speed: Using Flash Storage to Optimise Performance and Reduce Costs
Need for Speed: Using Flash Storage to Optimise Performance and Reduce Costs
 
S016828 storage-tiering-nola-v1710b
S016828 storage-tiering-nola-v1710bS016828 storage-tiering-nola-v1710b
S016828 storage-tiering-nola-v1710b
 
A better storage solution
A better storage solutionA better storage solution
A better storage solution
 
Nimble storage investor_deck_public
Nimble storage investor_deck_publicNimble storage investor_deck_public
Nimble storage investor_deck_public
 
Is This Really a SAN Problem? Understanding the Performance of Your IO Subsy...
Is This Really a SAN Problem? Understanding the Performance of  Your IO Subsy...Is This Really a SAN Problem? Understanding the Performance of  Your IO Subsy...
Is This Really a SAN Problem? Understanding the Performance of Your IO Subsy...
 
Percona live linux filesystems and my sql
Percona live   linux filesystems and my sqlPercona live   linux filesystems and my sql
Percona live linux filesystems and my sql
 

Kürzlich hochgeladen

Decarbonising Buildings: Making a net-zero built environment a reality
Decarbonising Buildings: Making a net-zero built environment a realityDecarbonising Buildings: Making a net-zero built environment a reality
Decarbonising Buildings: Making a net-zero built environment a realityIES VE
 
All These Sophisticated Attacks, Can We Really Detect Them - PDF
All These Sophisticated Attacks, Can We Really Detect Them - PDFAll These Sophisticated Attacks, Can We Really Detect Them - PDF
All These Sophisticated Attacks, Can We Really Detect Them - PDFMichael Gough
 
Generative Artificial Intelligence: How generative AI works.pdf
Generative Artificial Intelligence: How generative AI works.pdfGenerative Artificial Intelligence: How generative AI works.pdf
Generative Artificial Intelligence: How generative AI works.pdfIngrid Airi González
 
Microservices, Docker deploy and Microservices source code in C#
Microservices, Docker deploy and Microservices source code in C#Microservices, Docker deploy and Microservices source code in C#
Microservices, Docker deploy and Microservices source code in C#Karmanjay Verma
 
React Native vs Ionic - The Best Mobile App Framework
React Native vs Ionic - The Best Mobile App FrameworkReact Native vs Ionic - The Best Mobile App Framework
React Native vs Ionic - The Best Mobile App FrameworkPixlogix Infotech
 
Microsoft 365 Copilot: How to boost your productivity with AI – Part one: Ado...
Microsoft 365 Copilot: How to boost your productivity with AI – Part one: Ado...Microsoft 365 Copilot: How to boost your productivity with AI – Part one: Ado...
Microsoft 365 Copilot: How to boost your productivity with AI – Part one: Ado...Nikki Chapple
 
Connecting the Dots for Information Discovery.pdf
Connecting the Dots for Information Discovery.pdfConnecting the Dots for Information Discovery.pdf
Connecting the Dots for Information Discovery.pdfNeo4j
 
Accelerating Enterprise Software Engineering with Platformless
Accelerating Enterprise Software Engineering with PlatformlessAccelerating Enterprise Software Engineering with Platformless
Accelerating Enterprise Software Engineering with PlatformlessWSO2
 
A Framework for Development in the AI Age
A Framework for Development in the AI AgeA Framework for Development in the AI Age
A Framework for Development in the AI AgeCprime
 
Time Series Foundation Models - current state and future directions
Time Series Foundation Models - current state and future directionsTime Series Foundation Models - current state and future directions
Time Series Foundation Models - current state and future directionsNathaniel Shimoni
 
Top 10 Hubspot Development Companies in 2024
Top 10 Hubspot Development Companies in 2024Top 10 Hubspot Development Companies in 2024
Top 10 Hubspot Development Companies in 2024TopCSSGallery
 
4. Cobus Valentine- Cybersecurity Threats and Solutions for the Public Sector
4. Cobus Valentine- Cybersecurity Threats and Solutions for the Public Sector4. Cobus Valentine- Cybersecurity Threats and Solutions for the Public Sector
4. Cobus Valentine- Cybersecurity Threats and Solutions for the Public Sectoritnewsafrica
 
Genislab builds better products and faster go-to-market with Lean project man...
Genislab builds better products and faster go-to-market with Lean project man...Genislab builds better products and faster go-to-market with Lean project man...
Genislab builds better products and faster go-to-market with Lean project man...Farhan Tariq
 
Long journey of Ruby standard library at RubyConf AU 2024
Long journey of Ruby standard library at RubyConf AU 2024Long journey of Ruby standard library at RubyConf AU 2024
Long journey of Ruby standard library at RubyConf AU 2024Hiroshi SHIBATA
 
Testing tools and AI - ideas what to try with some tool examples
Testing tools and AI - ideas what to try with some tool examplesTesting tools and AI - ideas what to try with some tool examples
Testing tools and AI - ideas what to try with some tool examplesKari Kakkonen
 
Arizona Broadband Policy Past, Present, and Future Presentation 3/25/24
Arizona Broadband Policy Past, Present, and Future Presentation 3/25/24Arizona Broadband Policy Past, Present, and Future Presentation 3/25/24
Arizona Broadband Policy Past, Present, and Future Presentation 3/25/24Mark Goldstein
 
A Journey Into the Emotions of Software Developers
A Journey Into the Emotions of Software DevelopersA Journey Into the Emotions of Software Developers
A Journey Into the Emotions of Software DevelopersNicole Novielli
 
Emixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native developmentEmixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native developmentPim van der Noll
 
QCon London: Mastering long-running processes in modern architectures
QCon London: Mastering long-running processes in modern architecturesQCon London: Mastering long-running processes in modern architectures
QCon London: Mastering long-running processes in modern architecturesBernd Ruecker
 
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...Wes McKinney
 

Kürzlich hochgeladen (20)

Decarbonising Buildings: Making a net-zero built environment a reality
Decarbonising Buildings: Making a net-zero built environment a realityDecarbonising Buildings: Making a net-zero built environment a reality
Decarbonising Buildings: Making a net-zero built environment a reality
 
All These Sophisticated Attacks, Can We Really Detect Them - PDF
All These Sophisticated Attacks, Can We Really Detect Them - PDFAll These Sophisticated Attacks, Can We Really Detect Them - PDF
All These Sophisticated Attacks, Can We Really Detect Them - PDF
 
Generative Artificial Intelligence: How generative AI works.pdf
Generative Artificial Intelligence: How generative AI works.pdfGenerative Artificial Intelligence: How generative AI works.pdf
Generative Artificial Intelligence: How generative AI works.pdf
 
Microservices, Docker deploy and Microservices source code in C#
Microservices, Docker deploy and Microservices source code in C#Microservices, Docker deploy and Microservices source code in C#
Microservices, Docker deploy and Microservices source code in C#
 
React Native vs Ionic - The Best Mobile App Framework
React Native vs Ionic - The Best Mobile App FrameworkReact Native vs Ionic - The Best Mobile App Framework
React Native vs Ionic - The Best Mobile App Framework
 
Microsoft 365 Copilot: How to boost your productivity with AI – Part one: Ado...
Microsoft 365 Copilot: How to boost your productivity with AI – Part one: Ado...Microsoft 365 Copilot: How to boost your productivity with AI – Part one: Ado...
Microsoft 365 Copilot: How to boost your productivity with AI – Part one: Ado...
 
Connecting the Dots for Information Discovery.pdf
Connecting the Dots for Information Discovery.pdfConnecting the Dots for Information Discovery.pdf
Connecting the Dots for Information Discovery.pdf
 
Accelerating Enterprise Software Engineering with Platformless
Accelerating Enterprise Software Engineering with PlatformlessAccelerating Enterprise Software Engineering with Platformless
Accelerating Enterprise Software Engineering with Platformless
 
A Framework for Development in the AI Age
A Framework for Development in the AI AgeA Framework for Development in the AI Age
A Framework for Development in the AI Age
 
Time Series Foundation Models - current state and future directions
Time Series Foundation Models - current state and future directionsTime Series Foundation Models - current state and future directions
Time Series Foundation Models - current state and future directions
 
Top 10 Hubspot Development Companies in 2024
Top 10 Hubspot Development Companies in 2024Top 10 Hubspot Development Companies in 2024
Top 10 Hubspot Development Companies in 2024
 
4. Cobus Valentine- Cybersecurity Threats and Solutions for the Public Sector
4. Cobus Valentine- Cybersecurity Threats and Solutions for the Public Sector4. Cobus Valentine- Cybersecurity Threats and Solutions for the Public Sector
4. Cobus Valentine- Cybersecurity Threats and Solutions for the Public Sector
 
Genislab builds better products and faster go-to-market with Lean project man...
Genislab builds better products and faster go-to-market with Lean project man...Genislab builds better products and faster go-to-market with Lean project man...
Genislab builds better products and faster go-to-market with Lean project man...
 
Long journey of Ruby standard library at RubyConf AU 2024
Long journey of Ruby standard library at RubyConf AU 2024Long journey of Ruby standard library at RubyConf AU 2024
Long journey of Ruby standard library at RubyConf AU 2024
 
Testing tools and AI - ideas what to try with some tool examples
Testing tools and AI - ideas what to try with some tool examplesTesting tools and AI - ideas what to try with some tool examples
Testing tools and AI - ideas what to try with some tool examples
 
Arizona Broadband Policy Past, Present, and Future Presentation 3/25/24
Arizona Broadband Policy Past, Present, and Future Presentation 3/25/24Arizona Broadband Policy Past, Present, and Future Presentation 3/25/24
Arizona Broadband Policy Past, Present, and Future Presentation 3/25/24
 
A Journey Into the Emotions of Software Developers
A Journey Into the Emotions of Software DevelopersA Journey Into the Emotions of Software Developers
A Journey Into the Emotions of Software Developers
 
Emixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native developmentEmixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native development
 
QCon London: Mastering long-running processes in modern architectures
QCon London: Mastering long-running processes in modern architecturesQCon London: Mastering long-running processes in modern architectures
QCon London: Mastering long-running processes in modern architectures
 
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
 

Beyond Tuning: Getting the most out of your Oracle Application

  • 1. Beyond Tuning: Getting the most out of your Oracle application Mike Ault, Oracle Guru, TMS Inc. Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 2. Michael R. Ault Oracle Guru - Nuclear Navy 6 years - Nuclear Chemist/Programmer 10 years - Kennedy Western University Graduate - Bachelors Degree Computer Science - Certified in all Oracle Versions Since 6 - Oracle DBA, author, since 1990 Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 3. Books by Michael R. Ault Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 4. Statspackanalyzer.com Free Statspack/AWR Analysis Sponsored by Texas Memory Systems -Looks for IO bottlenecks and other configuration issues. -Straightforward tuning advice Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 5. Introduction Ok, You’ve Tuned: • Indexes • Partitioning • Parallel Query • Memory areas • Sort and Hash areas • OS • Bandwidth But…Performance is still not satisfactory! Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 6. Introduction • What now? • Tune or replace IO subsystem? Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 7. What Now? • If you don’t have CPU or Memory Issues • If you don’t have SQL tuning issues – Or, can’t tune due to third party issues – Or, can’t use automatic Oracle tuning – Or, automatic tuning still results in IO stress • Look at supplementing or replacing IO subsystem. Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 8. Basic IO Subsystems • JBOD – Just a Bunch of Disks • Basic SAN – Stripe and Mirror or RAID5 • Advanced SAN – Basic SAN plus cache, plus hot blocking • Advanced SAN + SSD – Tiered approach with hot files on SSD or SSD as advanced caching • Pure SSD – either DDR+Flash or Pure Flash Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 9. Problems with Striping • Most JBOD or SAN will be fronted by a RAID controller or software such as ASM • Stripe widths are limited to 64k in most controllers • ASM uses 1 megabyte • Small stripe widths cause IO blocking Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 10. IO Blocking Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 11. Non-Blocking Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 12. So…. • Maximize bandwidth – More HBAs – Infiniband – Most SANs can’t utilize existing bandwidth due to disk limits • Use luns to map hot/cold disk areas (11g ASM does this) • Tune RAID set stripe depth to IO size • Tune to max expected IO size • Reduces blocking reads and writes – Oracle says it doesn’t block reads – This is internal to Oracle once block is in cache – Blocking reads are due to physical issues with disk Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 13. What causes blocking? Rotational Latency Armature Motion (positional) Latency Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 14. Other IO Issues • Redo log issues – Solve by moving or isolating redo logs • Archive issues – Improve tuning of archive location • Network or Storage Network • Faster IO in archive location • Temporary Issues – Tune sorts, GTT, Bitmap, etc. – Move temp areas to lower latency write IO Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 15. How do I tell if My System has Issues? • OEM, AWR or Statspack – Top waits are IO related (DB file, Log) – Average latencies in Tablespoace IO area are >5-10 ms – Average latencies are 2-5 ms and IO waits dominate wait profile Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 16. How do SANs Overcome These Forms of Latency? • More disks – May not help latency • Caching into Flash or DDR – Good until cache is flooded • Selective files (hot) moved to Flash • Hot blocks moved to faster portions of disk – still limited to 2-5 ms Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 17. What are the Pros and Cons? • JBOD – Pros • Easy to implement • Easy to add capacity – Cons • Difficult to manage • Requires third party or OS tools • Doesn’t handle hot blocks/files • Latency issues • Bandwidth issues Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 18. What are the Pros and Cons? • Simple SAN – Pros • Easy to manage • Easy to expand – Cons • Requires licenses for management software • Doesn’t address hot blocks/files • Still has latency issues • Bandwidth issues Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 19. What are the Pros and Cons? • Advanced SAN – Pros • Relatively easy to manage • Handles hot blocks/files – Cons • Expensive • Expensive to expand • Licensing of software and support costs • Still has latency issues • Still has bandwidth issues Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 20. What are the Pros and Cons? • Advanced SAN with Caching – Pros • Easy to manage • Handles hot blocking/files • Provides some relief from latency issues – Cons • Once cache is flooded has latency issues • Expensive to implement and expand • Licensing of software • May have bandwidth issues Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 21. What are the Pros and Cons? • Advanced San with SSD – Pros • Easy to manage • Solves most latency issues up to a point • Solves hot blocking issues – Cons • Expensive to implement and expand • License of software costs • Usually shoehorns SSDs into existing architecture • Bandwidth issues Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 22. What are the Pros and Cons? • Mixed DDR and Flash – Pros • Tier solution for hot blocks • Usually has outstanding latency • Usually has great bandwidth • Usually Automatically managed – Cons • Expensive due to DDR • DDR requires battery backup if used as a storage tier • License costs Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 23. What are the Pros and Cons? • Pure Flash – Pros • Usually doesn’t require tiering • Great Latency • Using eMLC – Lower costs than SLC or DDR • Easily managed • Easily expanded – Cons • More expensive than JBOD, less expensive than Advanced SAN • Needs management software such as ASM Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 24. How About some Numbers? IOPS Comparison for Various SANs (Source: www.storageperformance.org) Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 25. Looking Forward • You have tuned • You have tuned the existing IO subsystem • Performance is still borderline • How do you determine what system should be next? Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 26. Object Intensity •Combines both throughput and capacity requirements •IOPS/GB •At a high enough IOPS/GB SSD is the cheapest solution •At a low enough IOPS/GB Capacity oriented disk drives meet the performance requirement •In between is performance optimized drives (15K RPM) Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 27. Based on performance AND price per GB SSD Territory Fast HDD Territory Capacity Oriented HDD Territory With eMLC the ratio is now around 1 IOPS/GB or less! Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 28. The Adjusted Storage Value Index • Takes into account: – Cost (USD) – Warrantee (years) – Capacity (Terabytes) – Performance (IOPS) – Latency (ms) (not in original SVI) • The higher the number, the better the value Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 29. Calculation of ASVI Adjusted Storage Value Index = (TUC*IOPS*WY)/(cost*L) Where: TUC = Total usable capacity in Terabytes IOPS = Validated IOs per second (SPC-1 results for example) WY= Warranty years (or years of paid maintenance if added to cost) Cost = Cost of validated system L = Latency at measured IOPS level Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 30. Comparison of Storage Values Adjusted Storage Value Index 20.0000 18.0000 16.0000 14.0000 12.0000 ASVI 10.0000 8.0000 6.0000 4.0000 2.0000 0.0000 d O 0 0 0 ar re 80 0 0 2s r en 40 lla 62 60 50 XI 17 co 3p 6n 67 Pi rtr S5 X8 i2 S3 n ta fo ch 00 Sa N Da D FA ei SU In ta su 87 m aw pp Hi Ra jit ds Hu Fu tA M Ne IB Manufacturer ASVI/Manufacturer All data taken from published SPC-1 Results Texas Memory Systems, Inc. - The World's Fastest Storage®
  • 31. Summary • Once all other tuning is done, tune IO • Low latency high bandwidth architectures give the best performance • Almost all advancements in SAN technology are to overcome rotating disk limitations • Pure SSD solutions (at least at the main level) are the future Texas Memory Systems, Inc. - The World's Fastest Storage®