On October 23rd, 2014, we updated our
By continuing to use LinkedIn’s SlideShare service, you agree to the revised terms, so please take a few minutes to review them.
OpenStack on IntelBilly CoxDirector, Cloud BuildersSoftware and Services GroupIntel Corp.
By 2015… More Users More More Data Devices >1 Billion More >15 Billion >1 Zetabyte Netizen’s1 Connected Devices2 Internet Traffic3 Internet and device expansion drives new requirements for Data Centers1. IDC “Server Workloads Forecast” 2009. 2.IDC “The Internet Reaches Late Adolescence” Dec 2009, extrapolation by Intel for 2015 2.ECG “Worldwide Device Estimates Year 2020 - Intel One Smart Network Work” forecast 3. Source:http://www.cisco.com/assets/cdc_content_elements/networking_solutions/service_provider/visual_networking_ip_traffic_chart.html extrapolated to 2015
Why is IT Buying in 2011? Primary Triggers for New Server Purchases Other HW Consolidation Migrating to 6% 29% Virtualization 20% Add Capacity 10% to Existing 18% Application 17% Application New Application Upgrade Virtualization and host of application-based needs are driving the majority of server purchases3 Source: Forrester Research survey, January 2011
Common Threads for New Server Purchases 60% are likely to be VIRTUALIZED >60% will be used where POWER / SPACE is limited Physical 38% Hosts 60% Space AND Power/Cooling Virtualized Limitations Hosts No Limitations Power/Cooling 9% Limitations 34% 30% 26% Space …and EVERYONE is Limitations concerned about SECURITY IT’s needs are varied, which requires targeted server platforms4 Source: Forrester Research survey, January 2011
Today’s Key IT Challenges Security Efficiency Today’s Technology Would Require Building 45 New Coal Power Plants to Support 2015 IT Infrastructure2 70% of Respondents Saying Security is Top Concern In Moving to Public Cloud1 Lock-In Manageability August 2010 IT will spend ~$2T on “We have seen lock-in return as a top deployment & operations thru concern….routinely seeking alternatives to 2015 unless smarter infrastructure radically proprietary virtualization and cloud simplifies management of virtualized computing technology “ environments.Opportunity to save $25B in annual “excess” IT spend by 20153 1. IDC Market Analysis, January 2010. 2. Source information in speaker notes 3. Source information in speaker notes
Impact of Scale * * * Software Technologies & Data Center Management Server, Storage, Switches Tight coupling across software, hardware, data center Cost in Cost in Resource Medium DC Very Large DC Ratio Network $95 / Mbps / month $13 / Mbps / month 7.1x Storage $2.20 / GB / month $0.40 / GB / month 5.7x Administration ≈140 servers/admin >1000 servers/admin 7.1x7 Source: Hamilton 2009.03.28: Cloud Computing Economies of Scale, Keynote, Self-Managing Database Systems, Shanghai.
Server Configurations Feature Shadowed Un-Shadowed Preheat High Low Flow Impedance High Reduced Fan Power Higher Reduced TSA Support 35 >35 AIRFLOW Shadowed Layout Non-Shadowed Layout
A little math• Using the Facebook, Open Compute as a reference − 30 servers/rack (1), 24 racks/row (2) >> 720 servers/row• With Xeon 5600 servers − 12 DIMM slots (2DPC), 4GB/DIMM >> 48GB/server• Assuming 4GB/VM >> 8,640 VMs/row• Assuming 130W/server >> 93.6kw/row• For a moderate size enterprise: − 4 rows >> 34,560 VMs and 374.4kw − At $0.10/VM/hour >> ~$83k/day revenue• Notes: − This is just the active VM’s; likely 1,000’s more offline − # VM/s goes up with Moore’s Law and memory capacity9
The implications for OpenStack• VMs: ~30k now, maybe 60k (1) in 3 years in same space• Power: ~370kw, roughly $1M/year (2) in utility spend• 10% more efficient placement >> ~$8k/day more revenue• 10% more efficient power >> saves ~$100k/year• For OpenStack − Plan for large numbers of VMs (scale) − Expect a focus on efficient use of the infrastructure (effective policy and constraint scheduling) − Support for compliance and audit (trust)10
Intel® Cloud BuildersEasing Cloud Deployments via Proven, Interoperable Solutions for ITwww.intel.com/cloudbuilders
Usage Models and Reference Architectures Use a client device Use a cloud Secure Client Balanced Secure Cloud On-boarding Execution Compute Access IaaS Policy based Trusted Scale out Converged Power Mgmt Compute Storage Networks Pools Data center
Intel® Cloud Builders Program Reference ArchitecturesA Starting Point from Which to Build and Optimize Cloud Infrastructure Intel and OEM Integrated solution HW Blueprints Software Reference Architecture White Papers ISV Cloud SW Stack Webinar/ Training Test Bed http://www.intel.com/cloudbuilders
Intel® Cloud Builders: Proven SolutionsProven, open, interoperable solutions optimized for IA capabilities Build A Cloud: Enhance A Cloud: Fujitsu Primergy with Balanced Compute Model VMware vCloud with NetSuite & Gproxy Design HP ProLiant SL* & Enomaly Elastic Computing Platform Cisco* Virtualized Multi- Huawei SingleCLOUD* Tenant Data Center IBM* CloudBurst Cloud Gateway Security on Intel Platforms Joyent SmartDataCenter Cloud On-Boarding with Microsoft System Center Citrix OpenCloud* VM Manager Self-Service Portal 2.0* Dell & VMware* Policy Nimbula* Cloud Operating Based Power System & Nimbula Management Director* EMC* Atmos* Scale-out Novell* Cloud Manager Storage Usage Models Parallels* Elastic IT Enhanced Cloud Security Solution Developer Cloud with HyTrust and VMware Powerleader Power Rack Server* with Microsoft* NetApp* Unified Storage Red Hat* Cloud and Networking Foundations Parallels* Trusted Ubuntu Enterprise Cloud Compute Pools for Cloud Computing Univa UD*Solutions to make it easier to VMware VCloud* Director VMware Enhanced Server Platform Security build & optimize cloud infrastructure
OpenStack with Cloud Builders (Challenges with Bexar release)• Need an external internet connection active to • Unable to SSH into the VM instance because download and install the OpenStack packages the configuration to IPtables that the install scripts created are lost if the server is• All steps not clearly documented, used multiple rebooted blogs and sources to complete successful installation • VM Instances reported “Failed to spawn” when starting, related to install scripts using• Automated installation scripts fails to install all development packages instead of Stable the needed packages due to ports that were packages. not open on the switch • Unable to get the nodes to add their presence to the master database on the cloud controller. • First Instance freezes at “scheduling” state, services on the node did not start automatically
Intel® Cloud Builders - Reference Architectures Usage Models SWPartners HWMaturity Technology Customer Test Bed Production
Enhance Security Trusted Compute Pools • Challenge − Little visibility or control of the level of security and trust provided by cloud infrastructure, so IT reluctant to use • Solution − Allow tenants of private and public clouds to place workloads into more secure and trusted resource pools by providing Untrusted Trusted Pool trusted/secure infrastructure and administrative tools that allow reporting and provisioning • Usage Scenarios − Launch of trusted VMM and VM − Enforcement of trusted pool − Provide tenant visibility into the infrastructure Trusted Compute Pool Reference Architectures18 www.intel.com/cloudbuilders/library
Improve Efficiency Policy-Based Power Management • Challenge − Datacenters require more efficient use of Node, Group and Data Center server power consumption. • Solution Policy − Active data center power management framework that allows monitoring and control of power usage at the node, group and data center level. • Usage Scenarios − Static Scenarios − Real time server monitoring − Static Power Guard Rail − Static Power Capping Policy based Power Management Reference Architecture19 www.intel.com/cloudbuilders/library
Datacenter Simplification Unified Networking • Challenge − Multiple data center networks for LAN, management, storage, virtualization, etc, add significant cost and complexity to data center environments • Solution Management Unified − Deploy standard 10GBE data center network with IO Fabric Virtualization for performance and collapse data traffic Servers Storage of all types to that network. Arrays • Usage Scenarios − 10GBE and LAN Port Consolidation − Storage (FCOE, iSCSI, NAS) and LAN Consolidation Unified Networking Reference Architectures20 www.intel.com/cloudbuilders/library
Legal Disclaimers: Performance• Performance tests and ratings are measured using specific computer systems and/or components and reflect the approximate performance of Intel products as measured by those tests. Any difference in system hardware or software design or configuration may affect actual performance. Buyers should consult other sources of information to evaluate the performance of systems or components they are considering purchasing. For more information on performance tests and on the performance of Intel products, Go to: http://www.intel.com/performance/resources/benchmark_limitations.htm.• Intel does not control or audit the design or implementation of third party benchmarks or Web sites referenced in this document. Intel encourages all of its customers to visit the referenced Web sites or others where similar performance benchmarks are reported and confirm whether the referenced benchmarks are accurate and reflect performance of systems available for purchase.• Relative performance is calculated by assigning a baseline value of 1.0 to one benchmark result, and then dividing the actual benchmark result for the baseline platform into each of the specific benchmark results of each of the other platforms, and assigning them a relative performance number that correlates with the performance improvements reported.• SPEC, SPECint, SPECfp, SPECrate. SPECpower, SPECjAppServer, SPECjEnterprise, SPECjbb, SPECompM, SPECompL, and SPEC MPI are trademarks of the Standard Performance Evaluation Corporation. See http://www.spec.org for more information.• TPC Benchmark is a trademark of the Transaction Processing Council. See http://www.tpc.org for more information.• SAP and SAP NetWeaver are the registered trademarks of SAP AG in Germany and in several other countries. See http://www.sap.com/benchmark for more information.• INFORMATION IN THIS DOCUMENT IS PROVIDED “AS IS”. NO LICENSE, EXPRESS OR IMPLIED, BY ESTOPPEL OR OTHERWISE, TO ANY INTELLECTUAL PROPERTY RIGHTS IS GRANTED BY THIS DOCUMENT. INTEL ASSUMES NO LIABILITY WHATSOEVER AND INTEL DISCLAIMS ANY EXPRESS OR IMPLIED WARRANTY, RELATING TO THIS INFORMATION INCLUDING LIABILITY OR WARRANTIES RELATING TO FITNESS FOR A PARTICULAR PURPOSE, MERCHANTABILITY, OR INFRINGEMENT OF ANY PATENT, COPYRIGHT OR OTHER INTELLECTUAL PROPERTY RIGHT.• Performance tests and ratings are measured using specific computer systems and/or components and reflect the approximate performance of Intel products as measured by those tests. Any difference in system hardware or software design or configuration may affect actual performance. Buyers should consult other sources of information to evaluate the performance of systems or components they are considering purchasing. For more information on performance tests and on the performance of Intel products, reference www.intel.com/software/products.
Optimization NoticeIntel® compilers, associated libraries and associated development tools may include or utilize options that optimize forinstruction sets that are available in both Intel® and non-Intel microprocessors (for example SIMD instruction sets), but do notoptimize equally for non-Intel microprocessors. In addition, certain compiler options for Intel compilers, including some thatare not specific to Intel micro-architecture, are reserved for Intel microprocessors. For a detailed description of Intel compileroptions, including the instruction sets and specific microprocessors they implicate, please refer to the “Intel® Compiler Userand Reference Guides” under “Compiler Options." Many library routines that are part of Intel® compiler products are morehighly optimized for Intel microprocessors than for other microprocessors. While the compilers and libraries in Intel® compilerproducts offer optimizations for both Intel and Intel-compatible microprocessors, depending on the options you select, yourcode and other factors, you likely will get extra performance on Intel microprocessors.Intel® compilers, associated libraries and associated development tools may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include Intel®Streaming SIMD Extensions 2 (Intel® SSE2), Intel® Streaming SIMD Extensions 3 (Intel® SSE3), and Supplemental StreamingSIMD Extensions 3 (Intel® SSSE3) instruction sets and other optimizations. Intel does not guarantee the availability,functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependentoptimizations in this product are intended for use with Intel microprocessors.While Intel believes our compilers and libraries are excellent choices to assist in obtaining the best performance on Intel® andnon-Intel microprocessors, Intel recommends that you evaluate other compilers and libraries to determine which best meetyour requirements. We hope to win your business by striving to offer the best performance of any compiler or library; pleaselet us know if you find we do not.Notice revision #2010110123