2-8s Smp Server Blades 2s/2u Rack Mount Server

Transcript

1 your infrastructure like a visionary, not a functionary. OpenVMS 8.4 on Tukwila Quad Core 9300 – Blazing Performance Prashanth K E, Technical Architect, OpenVMS Lab 24th June 2010 [email protected] Agenda – Today‟s Mission-Critical challenges – Mission-Critical Converged Infrastructure – HP‟s Server Strategy – Introduction to Intel ® Itanium ® 9300-series processor based servers – BL8x0c i2 Configurations Supported by OpenVMS – BL8x0c i2 Performance Features and OpenVMS Test Results – OpenVMS Support for RAS features on BL8x0c i2 – OpenVMS Power Management Support –Q&A 3 Mission-Critical Customer Challenges Financial Services Every minute of downtime = a minute of lost revenue! Healthcare Patient outcomes depend on 24x7 access to data Manufacturing and Distribution Production comes to grinding halt Public Sector and CME Customer retention and fraud detection at risk No tolerance for downtime Increasing SLAs with decreasing budgets Islands of legacy apps and monolithic systems 4 The First Mission-Critical Converged Infrastructure New Integrity systems optimized for the converged infrastructure Storage Servers HP Converged Infrastructure Power & cooling Network Management software A common, modular architecture that simplifies, consolidates, and automates everything 5 A mission-critical infrastructure delivering the highest levels of reliability and flexibility Introducing the Revolutionary Blade Scale Architecture The first mission-critical Converged Infrastructure on the industry‟s #1 blade platform Unified blade architecture from x86 to Superdome Simplify by consolidating applications on a common platform 6 FlexFabric Always-on resiliency Flexibly scale resources to any workload 100+ innovations to ensure global business continuity Matrix operating environment Instantly adjust infrastructure to business demands Unified Blade Architecture from x86 to Superdome Simplify by consolidating applications on a common platform BladeSystem Matrix Integrity Systems ProLiant NEW 2s 4s NEW NEW Integrity NonStop BladeSystem Superdome 2 enclosure Superdome cell blade 8s NEW c3000 Integrity NonStop c7000 Blades Intel and AMD x86 Enclosures 2-64s Train once, certify once, deploy once 7 Up to 4,096 nodes FlexFabric Scale resources to meet any workload demand Within the system Across the network Dynamically managed Blade Link Linear scaling from 2-8 sockets Crossbar Fabric Fault-tolerant flexible scaling 8 Virtual Connect Wire-once, changeready connectivity Matrix operating environment, delivered by Insight Dynamics Always-on Resiliency 100+ new innovations to ensure global business continuity Fault Tolerant Crossbar fabric with E2E retry Redundant, hot swap I/O interconnect modules Redundant manageability Blade OLAD no MP-SPOF FBD CRC, retry and spare lane ConvergedPCIInfrastructure resiliency advanced error handling XBAR OLR 2N AC/DC Memory DDDC + 1 SBE Passive XBAR Backplane Dynamic clock fail-over QPI CRC, retry, link width reduction 2010s On-line FW upgrades Memory double chip sparing Register file and TLB parity Redundant hot swap clocks Cell OLAD PCI soft-fail N+1 VRMs Automatic Processor Recovery 3 Data Center DR ServiceGuard for RAC ServiceGuard Storage Mgt. Fabric retry and lane sparing PCI OLAR Intel Cache Safe Technology Virtualization resiliency Electrically isolated partitions Memory chip-kill ECC Poison and viral error containment Memory addr/ctl Parity Enterprise HP-UX Dynamic Processor Resiliency Dual grid capable Hot swap I/O 2000s N+1 hot swap Fans Memory single-bit ECC Page de-allocation Dual path I/O Single-system resiliency Serviceguard N+1 hot swap AC/DC Dynamic Memory Resiliency 1990s 9 Matrix Operating Environment Common management delivered by HP Insight Dynamics Provision infrastructure in minutes New for HP-UX: Automated orchestration for physical blades 10 Optimize workloads confidently Reduce data center and energy costs Only for HP-UX: Most comprehensive automated workload management HP ranked #1 Optimized energy usage without compromising performance or reliability HP‟s Server Strategy 11 Integrity value redefines the data center with… Future 2010 A future business critical infrastructure More reliability and business criticality with: More modular design More common components Cellular Mid-range & High-end System More flexible and customizable architecture Today Growing family of bladed systems More performance Enhanced robustness and fully virtualized Low-cost highly-capable entry-class systems Delivering improved data center economics 12 Integrity value redefines the data center with… Future 2010 A future business critical infrastructure “Superdome-Gen2” 2-64s SMP server Low-cost highly-capable entry-class systems Supported in C7000 & C3000 chassis 2s/2U rack mount server Delivering improved data center economics 13 New Processor: Kittson Growing family of bladed systems 2-8S SMP Server Blades New Processor: Poulson Today New Processor: 9300 series Cellular Mid-range & High-end System Introduction to Intel ® Itanium ® 9300-series processor based servers 14 BL8x0c i2 Overview Form factor Memory (per blade) • Full Height c-Class form factor  Single wide BL860c i2 – 2s  Double wide BL870c i2 – 4s  Quad wide BL890c i2 – 8s • Supported in c3000 and c7000 enclosures ~6X memory BW increase over previous generation • 24 PC3-8500 DIMM sockets • 192 GB capacity per blade with 8GB DIMMs Processors and chipset • Intel ® Itanium ® 9300-series processors • Intel ® E7500 Scalable Memory Buffer • Intel ® E7500 IOH • Intel ® ICH10 south bridge I/O subsystem (per blade) Additional IO options  5X IO BW vs. previous generation • Two hot-plug SFF SAS HDDs per blade • Integrated p410i RAID controller • 2 dual-port 10GbE Flex-10 NICs; VC • Partner blade support support • 3 PCIe G2 mezz slots Management Power Management • Enhanced Demand based switching • Turbo boost 15 • • • • Integrated Lights Out (iLO3) Integrated VGA console iLO 3 Advanced Pack firmware c-Class Onboard Administrator High availability • Enhanced processor RAS features • Memory double chip spare • Internal SAS RAID • Enhanced interconnect RAS Operating Systems Support • HP-UX 11i v3 • OpenVMS 8.4 (Aug „10) • Windows 2008 R2 (to follow) Scaleable Blade Link Linear scalability with industry‟s first 2-4-8 socket server blades Blade Link combines multiple blades into a single, scalable system CPU 2s/8c Memory 96GB LAN HDDs X2= 4s/16c 192GB 4 x 10GbE 8 x 10GbE 2 Slots 4 Slots X2= Scale Up, Out and Within Scale More Only 8-Socket blade in industry standard blade enclosure Linear System resources grow evenly across CPU, memory, I/O, and etc 8s/32c 384GB 16 x 10GbE 8 Slots Scale 8 socket system at 2x the performance in half the footprint 16 NDA – Under embargo until 4/27/10 Migration from Current Integrity Server Products rx2660 BL860c 2-socket rx3600 BL860c i2 4-socket rx6600 BL870c i2 BL870c 8-socket BL890c i2 18 rx7640 rx2800 i2 – 2p/8c RACKMOUNT Value and Key Features Coming soon !!! rx2800 i2 Processor Up to two Dual-Core or Quad-Core Intel® Itanium® processors Memory Industry standard DDR3 technology 24 PC3-8500 DIMM sockets 192GB max (with 8GB DIMMs) Internal Storage 8 Hot-Plug SFF Serial Attached SCSI HDDs 1 CD+RW or DVD+RW Networking Dual Integrated Gigabit Ethernet ports Manageability LAN I/O Slots 6 PCI-E slots (2 x8, 4 x4 slots) Management Management Processor with iLO3 (Integrated Lights Out functionality) Form Factor 2U Rack Mount Server (office tower conversion kit available) 19 Key Points: Affordable, 8-core scalable entry-level non-x86 server • High Density Compute Server (2U footprint) • Excellent memory capacity • Continued innovations in RAS • Ease to deploy into today‟s racked environments • Office Friendly pedestal option • N+N redundant power and cooling • BL8x0c i2 configurations supported by OpenVMS 20 20 Supported configurations for OpenVMS Supported Supported • BL860c i2, BL870c i2, BL890c i2 • OpenVMS guest, HPVM V4.2 PK1 • LAN, FC pass thru and switches • HP Insight Control 6.1 • c3000, c7000 enclosures • vMedia, DVD (internal, USB) • Core I/O SAS disks (RAID mode) • MDS600, P2000G3,MSA2000G2 • Network NICs – 10 GigE LOM – 10 Gbps mezz –1 Gbps quad-port (NC364m) –1 Gbps dual-port (NC360m) Not Supported in Aug „10 relase • 8GB DIMMs • 8 Gbps FC HBA from Emulex • Core I/O SAS HBA mode • Fibre Channel HBA –8 • Virtual Connect, Flex10 Gbps dual-port FC (Q-logic) • 3 Gbps external SAS – P700m • FCoE • vFlash, USB flash disk 21 Only Major Items mentioned BL8x0c i2 Performance Features 22 22 Performance Enhancing Factors on BL8x0c i2 servers Enhanced thread level parallelism • Double the number of cores • Enhanced hyper thread management Directory-Based Cache Coherency • 9100 series processors used “snooping” mechanism for cache coherence • Increase in coherency traffic with increase in number of processors • Contention for bandwidth • 9300 series uses directory based cache coherency • Home agent for each memory controller • Track owners and shares of a given cache line 23 Performance Enhancing Factors on BL8x0c i2 servers Memory • Memory controllers integrated with processor (2 per processor) • rx6600 - 1 memory controller for 4 sockets • BL870c i2 – 8 dual port memory controllers for 4 sockets • DDR3 memory • Support for larger memory configurations QuickPath Interconnect • Point-to-Point connections • Higher bandwidth between processors and IO 24 Performance Enhancing Factors on BL8x0c i2 servers IOH (Intel E7500) • Connects CPU to PCIe gen2 IO (core and mezz) • Larger number of PCIe gen2 lanes increase IO throughput Data TLB support for 8K and 16K pages • Faster translations via the TLB Resource Affinity Domains • 5 standard RAD configurations • Provides users the flexibility to define how memory layout optimize for your application 25 OpenVMS Performance Test Results 26 Price performance migration path New Blades NewIntegrity Integrity blades: Cores 8-Socket 16-core rx7640 4-Socket BL890c i2 8-core rx6600 BL870c i2 2-Socket rx3600 rx2660 BL870c 2-Socket BL860c i2 BL860c New Integrity Blades are more scalable than previous generation • Double the number of cores • More memory • More I/Os 27 2X performance improvement with HT enabled Rdb Tests Rdb Performance Load Tests – OpenVMS V8.4 Rdb Performance Rdb Performance (Less is Better) (More is Better) 300 1 250 0.8 sec/txn TPS 200 150 100 0.4 0.2 50 0 0 rx8640 (1.60GHz/12.0MB) 0.6 BL890c-i2 (1.60GHz/6.0MB) rx8640 (1.60GHz/12.0MB) • BL890c i2 performs 2x better than rx8640 • The Transaction Per Second (TPS) is 2x • The time taken per transaction is reduced to half on i2 server • Rdb takes advantage of hyper-threading on i2 servers 28 BL890c-i2 (1.60GHz/6.0MB) 2X performance improvement Apache Performance Apache Bench Tests on OpenVMS V8.4 Bandwidth (More is better) Throughput ( More is Better) 250 800 200 120 100 600 100 80 Load 150 load Load Time Taken (sec) (Less is Better) 400 200 50 0 60 40 20 0 0 BL860c (1.59GHz/9.0MB) BL860c (1.59GHz/9.0MB) BL860c (1.59GHz/9.0MB) BL860c-i2 (1.73GHz/6.0MB) BL860c-i2 (1.73GHz/6.0MB) BL860c-i2 (1.73GHz/6.0MB) • BL860c-i2 delivered 2x performance compared to BL860c 29 870c i2 scaled up much better 2X performance improvement at higher workloads Java Workload Tests Native Java Tests on OpenVMS V8.4 Java Workload 140000 140000 120000 120000 Operation Rate Operation Rate Java Workload 100000 80000 60000 40000 100000 80000 60000 40000 20000 20000 0 0 0 2 4 6 8 10 12 14 16 8 18 9 10 BL870c i2 (1.60GHz/5.0MB) rx6600 (1.59GHz/12.0MB) • Java Workloads scale up better on i2 Servers • Java Workloads are high CPU and Memory Intensive 30 12 13 14 15 Threads Threads rx6600 (1.59GHz/12.0MB) 11 BL870c i2 (1.60GHz/5.0MB) 16 Memory tests Throughput Memory Bandwidth (more is better) Single stream test shows 55% improvement in memory bandwidth between rx3600 and BL860c i2 3500 3000 2500 2000 rx3600 (1.67GHz/9.0MB) 1500 BL860c-i2 (1.73GHz/6.0MB) 1000 Single Stream Test 500 0 MB/Sec – The new BL8x0c i2 server demonstrated 55% improvement in single stream test – Memory bound applications would benefit from aggregated bandwidth 31 •1.6 GHz 9300 series cores show 4% improvement over 9100/9000 cores •1.73 GHZ 9300 series cores show 15% improvement CPU Ratings Integer Test Rating Ratings (More is better) 1000 900 800 700 9300 - BL8x0c-i2 (1.73GHz/6.0MB) 600 9300- BL8x0c-i2 (1.60GHz/6.0MB) 500 9300 - BL8x0c-i2 (1.33GHz/4.0MB) 400 9000 - BL860c (1.59GHz/9.0MB) 300 9100 - rx7640 (1.60GHz/12.0MB) 200 100 0 – These numbers are per Core (within a processor/socket) Per core numbers – As the frequency increases, we see a increase in rating – CPU Bound applications should benefit (database queries), specifically integer computational bound applications 32 CPU Ratings Whetstone is FP Computation Tests MWIPS Rating (more is better) •1.6 GHz 9300 series cores show 8% improvement over 9100/9000 cores •1.73 GHZ 9300 series cores show 17% improvement 2500 2000 9300 - BL8x0c-i2 (1.73GHz/6.0MB) 1500 9300 - BL8x0c-i2 (1.60GHz/6.0MB) 9300 - BL8x0c-i2 (1.33GHz/4.0MB) 1000 9000 - BL860c (1.59GHz/9.0MB) 9100 - rx7640 (1.60GHz/12.0MB) 500 0 Per core numbers – These numbers are per Core (within a processor/socket) – Fast response to complex operations; Scientific, Automation and robotic applications should benefit 33 Performance Tests in Progress – IO tests – Oracle tests 34 OpenVMS V8.4 Performance Improvements – Integrity RAD Support – Support for TCP/IP Packet Processing Engine (PPE) • Gains of approximately 5% – Solid State Disks • Vendor benchmarks • Internal testing with EVA – Clustering Software Enhancements • PE driver – Benefits deployments that use multiple channels – Improvement of 50% observed in some use cases • Dedicated Lock Manager – Improved Request buffer handling – Results in 2x improvement in some cases – Applications like Relational databases are benefitted • Shadow Driver – Improvement of 10-12% observed in some use cases 35 OpenVMS V8.4 Performance Improvements – General Operating System Performance enhancements • Enhanced memcmp and strcmp for Inetrgity systems • Image Activation – Performance gains of 40-50% – Application performing lots of image activations gain • VA tear down – Batch jobs, creating and stopping processes improve 36 • Global Section unmap improvements • Exception Handling (on par with Alpha now) • InnerMode semaphore upcalls for Exec and Kernel mode • System service dispatch enhancements • Pthread spinlock algorithm changes • Dynamic enabling of XFC cache for mounted volumes • PageDyn LALs OpenVMS Support for RAS features on BL8x0c i2 37 37 Intel ® Itanium ® 9300-series RAS Features Enhanced reliability, availability and serviceability (RAS) over the 9100 series Extensive capabilities to detect, recover and report errors RAS features for • Processor/Socket • Memory • Interconnect and Miscellaneous • IOH and Partitions 38 Intel ® Itanium ® 9300-series Processor RAS Features Error avoidance, detection and correction across all core structures Soft error hardened latches and registers • Designed to improve resistance to soft errors by upto 100X Error Correcting Code (ECC) or parity • Widely used algorithms implemented in hardware to monitor errors that can occur during transmission 39 Intel ® Itanium ® 9300-series Processor RAS Features Intel Cache Safe Technology • Mapout bad cache lines using heuristics • Cache Data is automatically scrubbed for single bit errors • 9300 series covers L2 cache and directory cache as well as opposed to only L3 cache in 9100 Advanced Machine Check • Many errors that were fatal in 9100 are now correctable • OpenVMS logs correctable errors in the error logs Dynamic Processor Resilience (DPR) • Support for CPU indictment with help of WEBES 40 Intel ® Itanium ® 9300-series Memory RAS Features Enhanced ECC protection • ECC mechanism to detect and fix errors in attached memory components • Support for Single and Double Device Data Correction Memory Thermal Protection • Support for Closed and Open Loop throttling mechanisms to reduce failures due to over heating of components Memory sparing • Monitor memory for errors • On reaching a threshold firmware copies data from DRAM to a spare • Transparent to the Operating System 41 Intel ® Itanium ® 9300-series Interconnect RAS Features QPI Error Detection and Correction • CRC used to detect errors • Transactions retried • Channel Physically reset • Bad lanes can be mapped out (can impact performance) • Intelligent error management • Single dropped packet can have a cascade effect causing whole lot of errors • Sort and analyze the packet to determine the source 42 OpenVMS Power Management Support 43 Power Management Enhanced Demand Based Switching • Ability to operate at reduced voltage and frequency until more power is needed • Can run different P-States • Predefined voltage and frequency combinations at which a processor can operate correctly Intel Turbo Boost • Processor can run at frequencies higher the advertised frequency • Provided processor package is below rated power, thermal and current limits • If you have an idle core the active core can use its headroom to get a boost in frequency 44 OpenVMS Power Management Highest Performance Mode • Use Turboboost to maximize performance • No power savings measures Dynamic Power Mode • Use Turboboost when process is executing • Use C-states (halt states) to save power when a CPU is idle Low Power Mode • Use p-states to reduce power usage when process is executing • Use C-states to save power when a CPU is idle OS Control Mode • Enable a system service or sysgen parameter to select among power mode 45 Q&A 46 Questions/Comments Business Manager (Vivasvan Shastri) [email protected] Office of Customer Programs [email protected] 47 References and Acknowledgements – Intel Whitepapers http://download.intel.com/products/processor/itanium/323247.pdf http://download.intel.com/products/processor/itanium/318691.pdf http://software.intel.com/sites/oss/pdfs/power_mgmt_intel_arch_servers.pdf http://www.intel.com/design/itanium/documentation.htm – WEBES Documentation http://h18023.www1.hp.com/support/svctools/webes/index.html?jumpid=reg_R10 02_USEN – HP Whitepapers OpenVMS Technical Journal 14 article on OpenVMS Power Management by Prithvi Srihari, Burns Fisher and Veena K 48 Thank You 49