SlideShare a Scribd company logo
1 of 24
Download to read offline
Lustre User LINES OF TEXT
SUBTITLE WITH TWO
                  Group 2009
IF NECESSARY
Lustre as the Core of a Data Centric
Best Practice HPC Workflow
Bob Murphy, Open Storage
Sun Microsystems
A recent conversation

 “It's not computation I'm worried about, that's been
 solved, it's storing data, accessing it, and moving it
 around.”
   - Rico Magsipoc, Chief Technology Officer for the
      Laboratory of Neuro Imaging, UCLA




                      Lustre Users Group 2009             2
Processing power doubles every 2
years, but not for HPC...
              Peak FLOPS Per Rack

        In 2005:                84 cores     500 GFLOPS

        In 2009:             768 cores        9 TFLOPS

        In 2011: 1,536 cores                 172 TFLOPS



                   Lustre Users Group 2009                3
Data Explosion




Source: IDC
                  Lustre Users Group 2009   4
Factors driving the HPC data tsunami
• Increased sensor resolution
    -Cameras, Confocal Microscopes, CT Scanners, Sequencers, etc




       Protein Database Example




                                  Lustre Users Group 2009          5
Like computers themselves, the devices
creating these datasets have proliferated
• From 1 per institution, to 1 per department, to 1 per lab, to 1 per
  investigator



         Protein Database Example




• Terabyte-sized datasets from a single experiment are now routine
• 1TB/day/investigator
• Plus more - and higher resolution - simulations per unit time

                                    Lustre Users Group 2009             6
Oh, all the previously accrued data needs to be
stored too...




     Protein Database Example




                                Lustre Users Group 2009   7
Conclusion
• You can only compute the data as fast as you can move it




• HPC workflows will become performance bound by the
  speed of the storage system
                        Lustre Users Group 2009              8
So data access time will dominate HPC
workflow

        Time to Load Data   Time to Compute           Time to Store Data


 2005

 2009

 2011

                                           t



                            Lustre Users Group 2009                        9
Sun end-to-end infrastructure optimized to
     accelerate data centric HPC workf ows
                                     l




              Network Storage                                                                          Archive Storage
Sun Storage 7000 Unified Storage System                                                           Sun StorageTek Tape Archives
High Availability, Manageability, Shared Access                                           Economic, Green, Long Term Data Retention
                                                           Parallel Storage
●
    Home Directories, Application Code                                                    ●
                                                                                              Protection of IP Assets
                                                        Sun Lustre Storage System
●   Input Data, Results Files                                                             ●   SAM Storage Archive Manager HSM
                                                  High Performance Parallel File System
                                                  ●
                                                      Ongoing Computation
                                                            Lustre Users Group 2009                                                   10
High Bandwidth, High Memory
 Petaflop-Scale HPC Blade System
• Sun Blade X6275                                    New
   New, high density, dual node blade server
   2X2 Nehalem-EP 4-core CPUs
   2X12 DDR3 DIMM Slots, up to 192GB (8GB DIMMs)
   2x1 Sun Flash Module (24GB SATA)
   2x1 Dual Port QDR IB HCA

• Sun Blade 6048 System
   768 Nehalem-EP cores, 9TF, up to 9.2TB memory
   96 X Gigabit Ethernet via NEM
   96 X PCIe 2.0 Express Module x 8 interfaces                Sun Blade X6275
• Highest Compute Density in the Industry

                                                                                Sun Blade 6048
                                                                                    System
                                    Lustre Users Group 2009                                      11
Breakaway application performance

Compute-Intensive                            Sun Blade X6275 48 Node Cluster
MCAE Applications Run                                       Radioss Single Car Crash Code

Faster, with Less Power,
Less Heat, Less Space
with Integrated QDR
Infiniband
                                         Performance                    Space               Perf/Watt
 HP BL460c
 2 x 3GHz Xeon E5456
 Processors, SUSE Linux
                                                   3.2x                 50%                   3.2x


See Legal Substantiation Slides
                                  Lustre Users Group 2009                                               12
Sun Data Center 3456 IB Switch

• World's Largest Infiniband Core Switch
• Replaces 300 discrete InfiniBand
  switches and thousands of cables
• Unparalleled scalability and dramatically
  simplifying cable management
• Most economical InfiniBand cost/port
• Prelude to “Project M9” doubling
  InfiniBand performance




                              Lustre Users Group 2009   13
Efficient Petascale Architecture
Conventional                                           Constellation
                  s                                                     s
Compute      Rack                                      Cluster
                                                                   Rack
Clusters




                                          ng
                                      bli
          Le




                                   Ca
            af




                                                                                                 g
                                                                                               in
              Sw




 Conventional
                                                                                            bl
                               Co witc




                                                       Reduced
                                                                                          Ca
                itc




 Cabling
                                S
                                 re he




                                                       Cabling
                  he




 Infrastructure
                  s




                                       s




Conventional IB Fabric                                       Sun Datacenter Switch 3456
• 300 Switches: 288 Leaf + 12 core                           • 1 Core Switch 300:1 Reduction

• 6912 Cables: 3456 HCA + 3456 trunking                      • 1152 Cables 6:1 Reduction

• 92 Racks                                                   • 74 Racks 20% Smaller footprint


                                   Lustre Users Group 2009                                           14
Sun Lustre Storage System
              •    Scales to over 100 GBs/sec and capacity to petabytes
              •    Accelerated deployment though pre-defined modules
              •    Easy to size and architect configurations
              •    Automated configuration and standard install process
              •    Compelling price/performance with Sun components
              •    Deployed by Sun Professional Services to ensure success
                   Sun Lustre Storage System
                      Performance Scaling
Performance




              1         2          3           4
                  Number of HA OSS Modules                                   15
                                                   Lustre Users Group 2009
Sun Storage 7410 Unified Storage System
Breakthrough NAS performance at low cost and power
with Hybrid Storage Pool
                                               • Delivers over 1GB/s throughput
                                               • 2GB/s from DRAM
                                               • 280K IOPS
                                               • At ¼ the price of competitive
                                                 systems
                                               • And 40% of the power consumption
    Sun Storage 7410 Unified Storage System


• ZFS determines data access patterns and stores frequently
  accessed data in DRAM and FLASH
• Bundles IO into sequential lazy writes for more efficient use of
  low cost SATA mechanical disks
                                         Lustre Users Group 2009                    16
Scratch storage for a small HPC cluster



                                                                            7410 scratch performance good for
Pre-configured Sun MCAE Compute                                             single rack MCAE clusters
             Cluster
                                                                            Reduces install/operational complexity

                                                                            Expands market for HPC clusters
                                                                            -Many organizations “stuck on the desktop”
Sun Storage 7410 Unified Storage System                                     -Don't have expertise to roll their own cluster
High Availability, Manageability, Shared Access
●
    Home Directories, Application Code
●
    Input Data, Results Files
Ongoing Computation Scratch storage
Protection of IP Assets
                                                                                    “D-NAS”

                                                  Lustre Users Group 2009                                                 17
Unprecedented Dtrace
 Storage Analytics
• Automatic real-time visualization of
  application and storage related workloads
• Supports multiple simultaneous application
  and workload analysis in real-time
• Analysis can be saved, exported and
  replayed for further analysis
• Rapidly diagnose and resolve issues
   > How many Ops/Sec?
   > What services are active?
   > Which applications/users are causing
     performance issues?

                               Lustre Users Group 2009   18
Video




        Lustre Users Group 2009   19
Sun StorageTek Tape Archive
The greenest storage on the planet
• Provides a massive on-line/near-line repository –
  up to 70PB with little power or heat
• SAM Storage Archive Manager maintains active
  data on faster disk and automatically migrates                             FC
  inactive data to secondary storage                            Data Mover
                                                                                  Near Line Archive

• All data appears locally and is equally accessible
  to multiple users and applications                                         IB


• Stores data in open formats (TAR) allowing
  technology refresh and avoiding vendor lock-in
• Tape shelf life of about 30 years
• Manage HPC data at the right cost, with the right
  performance, on the right media - and deliver it to
  applications at the right time                                   Sun Lustre
                                                                 Storage System




                                      Lustre Users Group 2009                                         20
Putting it all together, the
Sun Constellation System
• An open systems super computer designed to scale from
  Departmental Cluster to Petascale
• Optimized compute, storage, networking and software technologies -
  and service - delivered as an integrated product
• Integrated connectivity and management to reduce start-up,
  development and operational complexity
• Technical innovation resulting in fewer components and high
  efficiency systems in a tightly integrated solution

    Easiest
    Path to
    Peta-Scale


                            Lustre Users Group 2009                    21
More than any other computer
  company, Sun gets it
This week's “Nehalem” Press Releases:

                                                                                                                   s-
Press Re
        lease
                                                                                            ms      Product                 age
            Microsys
                     tems, Inc
                               .
                                                            Ne    two     rk Syste                      g   and Stor
                                          w Open                                     etworkin
Source: Sun
                                    Ne                                       e, N
 S un An       nounces                      en    ce of      Comput                         e Efficie
                                                                                                            ncy
                        Converg                                                    em
                                                                   and Extr
                                                                                                                                  dy
                                                                                                                         lash-Rea
                  ts                                         ce                                                 nt; New F
 Highligh                            Pe     rforman                                     ity, Cooli
                                                                                                   ng Mana
                                                                                                           geme

                eakaway
                                                                                  eabil
                                                                         g, Manag
  with Br                        des A rchitectu
                                                 re with N
                                                           ew N etworkin
                                                             ) Pro cessor 5
                                                                            500 Serie
                                                                                      s
                                                                                                                             king, soft
                                                                                                                                        ware
                  dvanc d
                          Bla
                                           tel(R) Xe
                                                     on(R                                          etwor
        “Slow pipeseand slow storage have limited high performance computing mputing, n for d technologies
        Unveils A                by the In                                            en co systems ts an
                                                                             nce of op
   Su n                        d
                      s Powere
        years. Bladesolution is to evolve the industry's view tofohigh performance new produc todayiency and
          s and The                                                  c nverge              computing
   Server                                                 the mark
                                                                   e             launched      y     ive effic
                                                                        said ws) to Fowler, executive mass
                                              I/O and networking,” A - NeJohn da
        to include 09, 9:10performanceWIRE)--Leading
                                  T
                                am ED                                                                    h
                      20 high
                                                                 Q: JAV                         ance, wit vice Webcast live or
      esday April 14,
    Tu president, SystemsU
                                         SS
                                     SINE Sun Microsystems.
                            lif.--(B Group, stems, Inc. (NA S DA               lication perform         e launch
                L A RA , Ca                sy                        ins in app
                                                                        e ga                  To view th
                                                                                                   s.
     SANTA C                      un Micro                  liver hug                      nd cloud
                 ge s  ystems, S              g y that de                    ata  centers a
     and stora                       ms strate                   ting for d                  /launch .
                  n Netw  ork Syste                 of compu                       w.sun.com
      in its Ope                        conomics                        http://ww
                            im ize the e           rma  tion, go to
                  y, to max              duct info
       scalabilit         d for more pro                  Lustre Users Group 2009                                                     22
Summary
• Data is taking over HPC
• Sun has a wide array of complementary IP to Lustre that
  can cope with that
• Sun is leading the industry in Data-Centric HPC by
  delivering differentiated customer value in balanced HPC
  systems, including compute, storage, and networking
• Sun can uniquely deliver a complete end-to-end solution
• You can also integrate parts of that solution into your
  existing workflow
• Don't yell at your JBODs


                         Lustre Users Group 2009             23
THANK YOU

More Related Content

What's hot

EEDC Intelligent Placement of Datacenters
EEDC Intelligent Placement of DatacentersEEDC Intelligent Placement of Datacenters
EEDC Intelligent Placement of Datacenters
Roger Rafanell Mas
 
High Performance Computing - Challenges on the Road to Exascale Computing
High Performance Computing - Challenges on the Road to Exascale ComputingHigh Performance Computing - Challenges on the Road to Exascale Computing
High Performance Computing - Challenges on the Road to Exascale Computing
Heiko Joerg Schick
 
Gfarm Fs Tatebe Tip2004
Gfarm Fs Tatebe Tip2004Gfarm Fs Tatebe Tip2004
Gfarm Fs Tatebe Tip2004
xlight
 
20150704 benchmark and user experience in sahara weiting
20150704 benchmark and user experience in sahara weiting20150704 benchmark and user experience in sahara weiting
20150704 benchmark and user experience in sahara weiting
Wei Ting Chen
 
40 Powers of 10 - Simulating the Universe with the DiRAC HPC Facility
40 Powers of 10 - Simulating the Universe with the DiRAC HPC Facility40 Powers of 10 - Simulating the Universe with the DiRAC HPC Facility
40 Powers of 10 - Simulating the Universe with the DiRAC HPC Facility
inside-BigData.com
 
An Active and Hybrid Storage System for Data-intensive Applications
An Active and Hybrid Storage System for Data-intensive ApplicationsAn Active and Hybrid Storage System for Data-intensive Applications
An Active and Hybrid Storage System for Data-intensive Applications
Xiao Qin
 

What's hot (20)

EEDC Intelligent Placement of Datacenters
EEDC Intelligent Placement of DatacentersEEDC Intelligent Placement of Datacenters
EEDC Intelligent Placement of Datacenters
 
High Performance Computing - Challenges on the Road to Exascale Computing
High Performance Computing - Challenges on the Road to Exascale ComputingHigh Performance Computing - Challenges on the Road to Exascale Computing
High Performance Computing - Challenges on the Road to Exascale Computing
 
Mcae brief
Mcae briefMcae brief
Mcae brief
 
Using Distributed In-Memory Computing for Fast Data Analysis
Using Distributed In-Memory Computing for Fast Data AnalysisUsing Distributed In-Memory Computing for Fast Data Analysis
Using Distributed In-Memory Computing for Fast Data Analysis
 
NetApp Unified Scale-Out/Clustered Storage
NetApp Unified Scale-Out/Clustered StorageNetApp Unified Scale-Out/Clustered Storage
NetApp Unified Scale-Out/Clustered Storage
 
Ac922 watson 180208 v1
Ac922 watson 180208 v1Ac922 watson 180208 v1
Ac922 watson 180208 v1
 
数据中心网络研究:机遇与挑战
数据中心网络研究:机遇与挑战数据中心网络研究:机遇与挑战
数据中心网络研究:机遇与挑战
 
Cloumon enterprise
Cloumon enterpriseCloumon enterprise
Cloumon enterprise
 
Gfarm Fs Tatebe Tip2004
Gfarm Fs Tatebe Tip2004Gfarm Fs Tatebe Tip2004
Gfarm Fs Tatebe Tip2004
 
Using multi tiered storage systems for storing both structured & unstructured...
Using multi tiered storage systems for storing both structured & unstructured...Using multi tiered storage systems for storing both structured & unstructured...
Using multi tiered storage systems for storing both structured & unstructured...
 
High Performance Cyberinfrastructure Enables Data-Driven Science in the Globa...
High Performance Cyberinfrastructure Enables Data-Driven Science in the Globa...High Performance Cyberinfrastructure Enables Data-Driven Science in the Globa...
High Performance Cyberinfrastructure Enables Data-Driven Science in the Globa...
 
20150704 benchmark and user experience in sahara weiting
20150704 benchmark and user experience in sahara weiting20150704 benchmark and user experience in sahara weiting
20150704 benchmark and user experience in sahara weiting
 
Greenplum Analytics Workbench - What Can a Private Hadoop Cloud Do For You?
Greenplum Analytics Workbench - What Can a Private Hadoop Cloud Do For You?  Greenplum Analytics Workbench - What Can a Private Hadoop Cloud Do For You?
Greenplum Analytics Workbench - What Can a Private Hadoop Cloud Do For You?
 
Hana Memory Scale out using the hecatonchire Project
Hana Memory Scale out using the hecatonchire ProjectHana Memory Scale out using the hecatonchire Project
Hana Memory Scale out using the hecatonchire Project
 
Report to the NAC
Report to the NACReport to the NAC
Report to the NAC
 
MemzNet: Memory-Mapped Zero-copy Network Channel -- Streaming exascala data o...
MemzNet: Memory-Mapped Zero-copy Network Channel -- Streaming exascala data o...MemzNet: Memory-Mapped Zero-copy Network Channel -- Streaming exascala data o...
MemzNet: Memory-Mapped Zero-copy Network Channel -- Streaming exascala data o...
 
Whitepaper SSDs And Energy Efficiency
Whitepaper  SSDs And Energy EfficiencyWhitepaper  SSDs And Energy Efficiency
Whitepaper SSDs And Energy Efficiency
 
DDN: Protecting Your Data, Protecting Your Hardware
DDN: Protecting Your Data, Protecting Your HardwareDDN: Protecting Your Data, Protecting Your Hardware
DDN: Protecting Your Data, Protecting Your Hardware
 
40 Powers of 10 - Simulating the Universe with the DiRAC HPC Facility
40 Powers of 10 - Simulating the Universe with the DiRAC HPC Facility40 Powers of 10 - Simulating the Universe with the DiRAC HPC Facility
40 Powers of 10 - Simulating the Universe with the DiRAC HPC Facility
 
An Active and Hybrid Storage System for Data-intensive Applications
An Active and Hybrid Storage System for Data-intensive ApplicationsAn Active and Hybrid Storage System for Data-intensive Applications
An Active and Hybrid Storage System for Data-intensive Applications
 

Similar to Lug best practice_hpc_workflow

AWS Customer Presentation - Cycle Computing - AWS Summit 2012 - NYC
AWS Customer  Presentation - Cycle Computing - AWS Summit 2012 - NYCAWS Customer  Presentation - Cycle Computing - AWS Summit 2012 - NYC
AWS Customer Presentation - Cycle Computing - AWS Summit 2012 - NYC
Amazon Web Services
 
M6d cassandrapresentation
M6d cassandrapresentationM6d cassandrapresentation
M6d cassandrapresentation
Edward Capriolo
 
Using Many-Core Processors to Improve the Performance of Space Computing Plat...
Using Many-Core Processors to Improve the Performance of Space Computing Plat...Using Many-Core Processors to Improve the Performance of Space Computing Plat...
Using Many-Core Processors to Improve the Performance of Space Computing Plat...
Fisnik Kraja
 

Similar to Lug best practice_hpc_workflow (20)

Expectations for optical network from the viewpoint of system software research
Expectations for optical network from the viewpoint of system software researchExpectations for optical network from the viewpoint of system software research
Expectations for optical network from the viewpoint of system software research
 
Super cluster oracleday cl 7
Super cluster oracleday cl 7Super cluster oracleday cl 7
Super cluster oracleday cl 7
 
IBM Power9 Features and Specifications
IBM Power9 Features and SpecificationsIBM Power9 Features and Specifications
IBM Power9 Features and Specifications
 
Nimble Storage Series A presentation 2007
Nimble Storage Series A presentation 2007Nimble Storage Series A presentation 2007
Nimble Storage Series A presentation 2007
 
The Impact of Hardware and Software Version Changes on Apache Kafka Performan...
The Impact of Hardware and Software Version Changes on Apache Kafka Performan...The Impact of Hardware and Software Version Changes on Apache Kafka Performan...
The Impact of Hardware and Software Version Changes on Apache Kafka Performan...
 
How to be green in the cloud
How to be green in the cloudHow to be green in the cloud
How to be green in the cloud
 
QCT Ceph Solution - Design Consideration and Reference Architecture
QCT Ceph Solution - Design Consideration and Reference ArchitectureQCT Ceph Solution - Design Consideration and Reference Architecture
QCT Ceph Solution - Design Consideration and Reference Architecture
 
QCT Ceph Solution - Design Consideration and Reference Architecture
QCT Ceph Solution - Design Consideration and Reference ArchitectureQCT Ceph Solution - Design Consideration and Reference Architecture
QCT Ceph Solution - Design Consideration and Reference Architecture
 
AWS Customer Presentation - Cycle Computing - AWS Summit 2012 - NYC
AWS Customer  Presentation - Cycle Computing - AWS Summit 2012 - NYCAWS Customer  Presentation - Cycle Computing - AWS Summit 2012 - NYC
AWS Customer Presentation - Cycle Computing - AWS Summit 2012 - NYC
 
Building a High Performance Analytics Platform
Building a High Performance Analytics PlatformBuilding a High Performance Analytics Platform
Building a High Performance Analytics Platform
 
Ceph Day New York 2014: Best Practices for Ceph-Powered Implementations of St...
Ceph Day New York 2014: Best Practices for Ceph-Powered Implementations of St...Ceph Day New York 2014: Best Practices for Ceph-Powered Implementations of St...
Ceph Day New York 2014: Best Practices for Ceph-Powered Implementations of St...
 
Modernize Your Oracle Environment with an Agile Data Infrastructure
Modernize Your Oracle Environment with an Agile Data InfrastructureModernize Your Oracle Environment with an Agile Data Infrastructure
Modernize Your Oracle Environment with an Agile Data Infrastructure
 
From Rack scale computers to Warehouse scale computers
From Rack scale computers to Warehouse scale computersFrom Rack scale computers to Warehouse scale computers
From Rack scale computers to Warehouse scale computers
 
M6d cassandrapresentation
M6d cassandrapresentationM6d cassandrapresentation
M6d cassandrapresentation
 
@IBM Power roadmap 8
@IBM Power roadmap 8 @IBM Power roadmap 8
@IBM Power roadmap 8
 
云计算核心技术架构分论坛 一石三鸟 性能 功耗及成本
云计算核心技术架构分论坛 一石三鸟 性能 功耗及成本云计算核心技术架构分论坛 一石三鸟 性能 功耗及成本
云计算核心技术架构分论坛 一石三鸟 性能 功耗及成本
 
Sn wf12 amd fabric server (satheesh nanniyur) oct 12
Sn wf12 amd fabric server (satheesh nanniyur) oct 12Sn wf12 amd fabric server (satheesh nanniyur) oct 12
Sn wf12 amd fabric server (satheesh nanniyur) oct 12
 
Using Many-Core Processors to Improve the Performance of Space Computing Plat...
Using Many-Core Processors to Improve the Performance of Space Computing Plat...Using Many-Core Processors to Improve the Performance of Space Computing Plat...
Using Many-Core Processors to Improve the Performance of Space Computing Plat...
 
Future Trends in IT Storage
Future Trends in IT StorageFuture Trends in IT Storage
Future Trends in IT Storage
 
KT ucloud storage, by Jaesuk Ahn
KT ucloud storage, by Jaesuk AhnKT ucloud storage, by Jaesuk Ahn
KT ucloud storage, by Jaesuk Ahn
 

Lug best practice_hpc_workflow

  • 1. Lustre User LINES OF TEXT SUBTITLE WITH TWO Group 2009 IF NECESSARY Lustre as the Core of a Data Centric Best Practice HPC Workflow Bob Murphy, Open Storage Sun Microsystems
  • 2. A recent conversation “It's not computation I'm worried about, that's been solved, it's storing data, accessing it, and moving it around.” - Rico Magsipoc, Chief Technology Officer for the Laboratory of Neuro Imaging, UCLA Lustre Users Group 2009 2
  • 3. Processing power doubles every 2 years, but not for HPC... Peak FLOPS Per Rack In 2005: 84 cores 500 GFLOPS In 2009: 768 cores 9 TFLOPS In 2011: 1,536 cores 172 TFLOPS Lustre Users Group 2009 3
  • 4. Data Explosion Source: IDC Lustre Users Group 2009 4
  • 5. Factors driving the HPC data tsunami • Increased sensor resolution -Cameras, Confocal Microscopes, CT Scanners, Sequencers, etc Protein Database Example Lustre Users Group 2009 5
  • 6. Like computers themselves, the devices creating these datasets have proliferated • From 1 per institution, to 1 per department, to 1 per lab, to 1 per investigator Protein Database Example • Terabyte-sized datasets from a single experiment are now routine • 1TB/day/investigator • Plus more - and higher resolution - simulations per unit time Lustre Users Group 2009 6
  • 7. Oh, all the previously accrued data needs to be stored too... Protein Database Example Lustre Users Group 2009 7
  • 8. Conclusion • You can only compute the data as fast as you can move it • HPC workflows will become performance bound by the speed of the storage system Lustre Users Group 2009 8
  • 9. So data access time will dominate HPC workflow Time to Load Data Time to Compute Time to Store Data 2005 2009 2011 t Lustre Users Group 2009 9
  • 10. Sun end-to-end infrastructure optimized to accelerate data centric HPC workf ows l Network Storage Archive Storage Sun Storage 7000 Unified Storage System Sun StorageTek Tape Archives High Availability, Manageability, Shared Access Economic, Green, Long Term Data Retention Parallel Storage ● Home Directories, Application Code ● Protection of IP Assets Sun Lustre Storage System ● Input Data, Results Files ● SAM Storage Archive Manager HSM High Performance Parallel File System ● Ongoing Computation Lustre Users Group 2009 10
  • 11. High Bandwidth, High Memory Petaflop-Scale HPC Blade System • Sun Blade X6275 New New, high density, dual node blade server 2X2 Nehalem-EP 4-core CPUs 2X12 DDR3 DIMM Slots, up to 192GB (8GB DIMMs) 2x1 Sun Flash Module (24GB SATA) 2x1 Dual Port QDR IB HCA • Sun Blade 6048 System 768 Nehalem-EP cores, 9TF, up to 9.2TB memory 96 X Gigabit Ethernet via NEM 96 X PCIe 2.0 Express Module x 8 interfaces Sun Blade X6275 • Highest Compute Density in the Industry Sun Blade 6048 System Lustre Users Group 2009 11
  • 12. Breakaway application performance Compute-Intensive Sun Blade X6275 48 Node Cluster MCAE Applications Run Radioss Single Car Crash Code Faster, with Less Power, Less Heat, Less Space with Integrated QDR Infiniband Performance Space Perf/Watt HP BL460c 2 x 3GHz Xeon E5456 Processors, SUSE Linux 3.2x 50% 3.2x See Legal Substantiation Slides Lustre Users Group 2009 12
  • 13. Sun Data Center 3456 IB Switch • World's Largest Infiniband Core Switch • Replaces 300 discrete InfiniBand switches and thousands of cables • Unparalleled scalability and dramatically simplifying cable management • Most economical InfiniBand cost/port • Prelude to “Project M9” doubling InfiniBand performance Lustre Users Group 2009 13
  • 14. Efficient Petascale Architecture Conventional Constellation s s Compute Rack Cluster Rack Clusters ng bli Le Ca af g in Sw Conventional bl Co witc Reduced Ca itc Cabling S re he Cabling he Infrastructure s s Conventional IB Fabric Sun Datacenter Switch 3456 • 300 Switches: 288 Leaf + 12 core • 1 Core Switch 300:1 Reduction • 6912 Cables: 3456 HCA + 3456 trunking • 1152 Cables 6:1 Reduction • 92 Racks • 74 Racks 20% Smaller footprint Lustre Users Group 2009 14
  • 15. Sun Lustre Storage System • Scales to over 100 GBs/sec and capacity to petabytes • Accelerated deployment though pre-defined modules • Easy to size and architect configurations • Automated configuration and standard install process • Compelling price/performance with Sun components • Deployed by Sun Professional Services to ensure success Sun Lustre Storage System Performance Scaling Performance 1 2 3 4 Number of HA OSS Modules 15 Lustre Users Group 2009
  • 16. Sun Storage 7410 Unified Storage System Breakthrough NAS performance at low cost and power with Hybrid Storage Pool • Delivers over 1GB/s throughput • 2GB/s from DRAM • 280K IOPS • At ¼ the price of competitive systems • And 40% of the power consumption Sun Storage 7410 Unified Storage System • ZFS determines data access patterns and stores frequently accessed data in DRAM and FLASH • Bundles IO into sequential lazy writes for more efficient use of low cost SATA mechanical disks Lustre Users Group 2009 16
  • 17. Scratch storage for a small HPC cluster 7410 scratch performance good for Pre-configured Sun MCAE Compute single rack MCAE clusters Cluster Reduces install/operational complexity Expands market for HPC clusters -Many organizations “stuck on the desktop” Sun Storage 7410 Unified Storage System -Don't have expertise to roll their own cluster High Availability, Manageability, Shared Access ● Home Directories, Application Code ● Input Data, Results Files Ongoing Computation Scratch storage Protection of IP Assets “D-NAS” Lustre Users Group 2009 17
  • 18. Unprecedented Dtrace Storage Analytics • Automatic real-time visualization of application and storage related workloads • Supports multiple simultaneous application and workload analysis in real-time • Analysis can be saved, exported and replayed for further analysis • Rapidly diagnose and resolve issues > How many Ops/Sec? > What services are active? > Which applications/users are causing performance issues? Lustre Users Group 2009 18
  • 19. Video Lustre Users Group 2009 19
  • 20. Sun StorageTek Tape Archive The greenest storage on the planet • Provides a massive on-line/near-line repository – up to 70PB with little power or heat • SAM Storage Archive Manager maintains active data on faster disk and automatically migrates FC inactive data to secondary storage Data Mover Near Line Archive • All data appears locally and is equally accessible to multiple users and applications IB • Stores data in open formats (TAR) allowing technology refresh and avoiding vendor lock-in • Tape shelf life of about 30 years • Manage HPC data at the right cost, with the right performance, on the right media - and deliver it to applications at the right time Sun Lustre Storage System Lustre Users Group 2009 20
  • 21. Putting it all together, the Sun Constellation System • An open systems super computer designed to scale from Departmental Cluster to Petascale • Optimized compute, storage, networking and software technologies - and service - delivered as an integrated product • Integrated connectivity and management to reduce start-up, development and operational complexity • Technical innovation resulting in fewer components and high efficiency systems in a tightly integrated solution Easiest Path to Peta-Scale Lustre Users Group 2009 21
  • 22. More than any other computer company, Sun gets it This week's “Nehalem” Press Releases: s- Press Re lease ms Product age Microsys tems, Inc . Ne two rk Syste g and Stor w Open etworkin Source: Sun Ne e, N S un An nounces en ce of Comput e Efficie ncy Converg em and Extr dy lash-Rea ts ce nt; New F Highligh Pe rforman ity, Cooli ng Mana geme eakaway eabil g, Manag with Br des A rchitectu re with N ew N etworkin ) Pro cessor 5 500 Serie s king, soft ware dvanc d Bla tel(R) Xe on(R etwor “Slow pipeseand slow storage have limited high performance computing mputing, n for d technologies Unveils A by the In en co systems ts an nce of op Su n d s Powere years. Bladesolution is to evolve the industry's view tofohigh performance new produc todayiency and s and The c nverge computing Server the mark e launched y ive effic said ws) to Fowler, executive mass I/O and networking,” A - NeJohn da to include 09, 9:10performanceWIRE)--Leading T am ED h 20 high Q: JAV ance, wit vice Webcast live or esday April 14, Tu president, SystemsU SS SINE Sun Microsystems. lif.--(B Group, stems, Inc. (NA S DA lication perform e launch L A RA , Ca sy ins in app e ga To view th s. SANTA C un Micro liver hug nd cloud ge s ystems, S g y that de ata centers a and stora ms strate ting for d /launch . n Netw ork Syste of compu w.sun.com in its Ope conomics http://ww im ize the e rma tion, go to y, to max duct info scalabilit d for more pro Lustre Users Group 2009 22
  • 23. Summary • Data is taking over HPC • Sun has a wide array of complementary IP to Lustre that can cope with that • Sun is leading the industry in Data-Centric HPC by delivering differentiated customer value in balanced HPC systems, including compute, storage, and networking • Sun can uniquely deliver a complete end-to-end solution • You can also integrate parts of that solution into your existing workflow • Don't yell at your JBODs Lustre Users Group 2009 23