1 / 51

About the Series

Get The Hype On System z z/VM vs. Distributed Hypervisor Matchup: z/VM Holds the Title Thursday 17-SEPT. About the Series.

anoush
Download Presentation

About the Series

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Get The Hype On System zz/VM vs. Distributed Hypervisor Matchup: z/VM Holds the TitleThursday 17-SEPT

  2. About the Series “Get the Hype on System z” is an ongoing webinar series, sponsored by Red Hat and IBM, designed to keep you informed of changes and improvements in mainframe computing. In this series, you'll learn about compelling hardware improvements, Linux on System z technology, new reference architectures and recommended workloads, and hear from real customers and engineers with on-the-job experience. All presentations will be recorded and placed on: www.redhat.com/z/webinars

  3. About the Series Completed Webinars: What's all the hype about System z? (Speaker: Bill Reeder, IBM)Focusing on the hardware aspect of System z, Bill spoke about why customers are opting to virtualize on IBM System z platforms. Future Webinars z/VM vs Distributed Hypervisor Matchup (Thursday 17-SEPT) Current & Future Linux on System z Technology(Thurs 24-SEPT) TBD: Check http://www.redhat.com/z/webinars ! Performance Observations of Linux on System z Troubleshooting Linux for System z Integrating Linux on System z identities to Windows/Active Directory[Done by partner Centrify] Ideas? Email Shawn Wells (sdw@redhat.com) and Shawn Briscoe (sbriscoe@redhat.com)

  4. z/VM vs. Distributed Hypervisor Matchup: z/VM Holds the Title Understanding the Technology Advantages of Running Linux on z/VM September 2009 Reed A. Mullen mullenra@us.ibm.comIBM Systems and Technology Group

  5. Why Run Linux on z/VM? • Infrastructure Simplification • Consolidate distributed, discrete servers and their networks • IBM mainframe qualities of service • Exploit built-in z/VM systems management • Speed to Market • Deploy servers, networks, and solutions fast • React quickly to challenges and opportunities • Allocate server capacity when needed • Technology Exploitation • Linux with z/VM offers more function than Linux alone • Linux exploits unique z/VM technology features • Build innovative on demand solutions

  6. Smarter Virtualization with IBM System z • Do more with less • Consolidate more servers, more networks, more applications, and more data with Linux on z/VM • Achieve nearly 100% utilization of system resources nearly 100% of the time • Enjoy the highest levels of resource sharing, I/O bandwidth, and system availability • Reduce costs on a bigger scale • Consume less power and floor space • Save on software license fees • Minimize hardware needed for business continuance and disaster recovery • Manage growth and complexity • Exploit extensive z/VM facilities for life cycle management: provisioning, monitoring, workload mgmt, capacity planning, security, charge back, patching, backup, recovery, more... • Add hardware resources to an already-running system without disruption – the epitome of Dynamic Infrastructure • Consolidation on a scale up machine like System z means fewer cables, fewer components to impede growth

  7. IBM System z Virtualization Genetics The Key to Unlocking the Value of Consolidation on System z • System z is thoroughly architected to host applications in a virtualized environment • This is accomplished with a coordinated set of investments that permeate the technology stack of hardware, firmware, hypervisors, and operating systems • This means clients can maximize the utilization, scalability, and security of all system assets, including: • CPU • Memory • I/O • Networking • Cryptography • All with exceptional levels ofoperational ease and cost efficiencies “But there’s another key factor that could impede the growth of x86 server virtualization. With the mainframe, most system components [come] from the same vendor (IBM). With x86 server virtualization, the microprocessor, server platform, storage, hypervisor and operating systems typically come from multiple vendors. ‘These vendors may have conflicting objectives,’ Burns writes.” – Charles Burns, author of “The Many Faces of Virtualization: Understanding a New IT Reality”, quoted in NetworkWorld.com* * http://www.networkworld.com/news/2008/010708-virtualization.html

  8. z/VM Technology Exploitation for Linux • Resource sharing and scalability • CPU and memory • Advanced disk support • Virtual communications and network consolidation • Systems management, provisioning, command and control

  9. Linux-on-z/VM and Resource SharingFor Cost Savings and Operational Efficiencies • A fundamental strength of z/VM is its ability to share system resources to an extreme level • System z virtual machines can share all hardware assets with very high levels of resource utilization • Both real and virtual (z/VM) resources can be shared with very high levels of bandwidth and reliability for enhanced workload throughput • Linux can exploit z/VM-unique facilities for even higher levels of resource utilization and operational efficiencies • Increase staff productivity and reduce memory consumption by sharing Linux program executables with z/VM DCSS technology • Improve memory utilization with Virtual Disks in Storage and Cooperative Memory Management • Enhance virtual networking bandwidth and availability using Link Aggregation and the z/VM Virtual Switch

  10. Linux Linux Virtual2CPUs Linux Linux Linux Linux Linux z/VM VirtualCPUs z/VM z/VM z/OS z/OS IFL2 IFL3 IFL1 IFL4 LPAR1 LPAR2 LPAR3 LPAR4 LogicalCPUs LogicalCPUs IBM System z Virtualization LeadershipExtreme Levels of CPU Sharing IBM System z PhysicalCPUs PhysicalCPUs CP1 CP2 CP3 CP4

  11. y x IBM System z CPU High AvailabilityConcurrent Processor Reassignment • Used to concurrently change the physical backing of one or more logical processors • The state of source physical processor is captured and transplanted into the target physical processor • Operation is transparent to operating systems • Used for processor sparing andbook replacement Logical CPU PUx PUy Physical CPU

  12. Up to 336 I/O Processors No additional chargefor these processors Up to 64-way SMP Share up to 64 processorswith up to 60 LPARs Configure these processorsas CPs, IFLs, zAAPs*, zIIPs*,or ICFs* * No software license fees Up to 11 System Assist Processors Offload system processing to dedicated CPUs (no impact to software license fees) Up to 16 Crypto Express2 CPUs High scale performance for SSL transactions 2 Standard Spare PUs System Design Affects Virtualization Capabilities System z packs a lot of computepower into a single box • With TCO-friendly pricing

  13. ApplicationCode OS and SystemResource Mgmt System Design Affects Virtualization Capabilities Compare to typical UNIXsystem design... Up to 128-way SMP configuration I/O DeviceDrivers Cryptography CPUs licensed for software doa lot of other things too!

  14. PR/SM High-Performance I/O Sharing (Multi-Image Facility) Shared I/O adapter or Channel Path Shared Storage Controller Subchannel Image For LPAR 1 Physical Adapter or Channel Path Interface, e.g., FICON Device Image Channel Path Image 1 LPAR 1 Subchannel Image For LPAR 1 Device Image Shared Logical Volume e.g., Parallel Access Volume (PAV) Channel Path Image 2 Subchannel Image for LPAR 2 Device Image LPAR 2 Subchannel Image for LPAR 3 Channel Path Image 3 Device Image LPAR 3 The I/O operations for each logical partition are multiplexed within the adapter/channel path and on the associated I/O interface Device Image A “virtual” ECKD volume emulated on physical SCSI disks Channel Path Image n Subchannel Image for LPAR n LPAR n • The I/O infrastructure is shared by LPARs at native speeds, without hypervisor involvement • Up to 8 physical channels process the I/O requests to the shared devices • This reduces the possibility of I/O queuing delays at the channels or at the shared storage controller

  15. Optimize virtual servers withdedicated real resources Configure virtual machineswith z/VM-unique facilities Up to 24,576 devices pervirtual machine More than 1 TB of memory(in aggregate) Simulate assets not in LPAR Add Virtual CPUs (up to 64) z/VM V5.4 – An Exceptional Virtualization Platform z/VM can massively scale a virtual server environment with a mixof virtual and real resources for each virtual machine • With exceptional levels of performance, availability, and security • Virtual and real assets can be non-disruptively added when needed Linux Linux Linux z/VSE z/OS VirtualResources z/VM Up to 256 channel paths I/O and Network LPARResources Up to 256 GB Memory CPU Up to 32 CPUs

  16. z/VM CPU Resource ControlsHighly Granular Sharing of System Resources • Allocate system resources per guest image using SHARE command • This is a highly flexible and self-managedfunction of the z/VM Control Program • Reserve CPU capacity for peak usage • Use it when needed • Relinquish the processor cycles forother servers when not needed • "Absolute guests" receive top priority • The Virtual Machine Resource Manager canbe used to monitor and adjust remainingcapacity allocated to "Relative guests“ • Also use VMRM to prioritize I/O operationsamong guest images via “I/O PriorityQueuing” Absolute% RelativeShare AbsoluteGuests RelativeGuests 80 800 60 600 40 400 20 200 Lin1 Lin2 Lin3 Lin4 Lin5 0 0 z/VM Control Program SHARE Lin1 ABSOLUTE 40% ABSOLUTE 60% LIMITSOFTSHARE Lin2 ABSOLUTE 20% ABSOLUTE 30% LIMITHARD Notes: = limit can be exceeded if unused capacity is available (LIMITSOFT) SHARE Lin3 RELATIVE 200 RELATIVE 300 LIMITHARDSHARE Lin4 RELATIVE 100 RELATIVE 200 LIMITSOFTSHARE Lin5 RELATIVE 100 RELATIVE 200 LIMITSOFT = limit will not be exceeded (LIMITHARD)

  17. Linux-on-z/VM and Resource OvercommitmentA Key Aspect of Cost Savings When Running Linux on System z • A fundamental strength of z/VM is its ability to overcommit system resources: “Do more with less” • Users can host an environment that consumes considerably more CPU and memory, in aggregate, than what is configured in the z/VM LPAR • This can translate into cost savings for hardware and software • Consider a Linux-on-z/VM environment with a 25-to-1 overcommitment of CPU capacity: Linux Linux Linux Linux Linux Linux Linux Linux Linux Linux Virtual CPUs Linux Linux Linux Linux Linux Linux Linux Linux Linux Linux Software licensed fortwo real CPUs can run on 50 virtual CPUs in this example Virtual CPUs Linux Linux Linux Linux Linux Linux Linux Linux Linux Linux Virtual CPUs Linux Linux Linux Linux Linux Linux Linux Linux Linux Linux Virtual CPUs Linux Linux Linux Linux Linux Linux Linux Linux Linux Linux Virtual CPUs z/VM Real CPUs

  18. Single-System, Multi-LPAR, Linux-on-z/VM EnvironmentMaximizing Resource Utilization and System Availability • Run multiple copies of z/VM ona single System z for enhancedscalability, failover, operations,and energy efficiency • Share CPUs and I/O adaptersacross all z/VM LPARs, and over-commit memory in eachLPAR for added costeffectiveness

  19. CPU 0SHARE=25 CPU 0SHARE=50 CPU 1SHARE=25 CPU 1SHARE=50 CPU 2SHARE=25 CPU 2Stopped CPU 3SHARE=25 CPU 3Stopped CPU 0SHARE=50 CPU 0SHARE=25 CPU 1SHARE=25 CPU 1SHARE=50 CPU 2SHARE=25 CPU 2Stopped CPU 3SHARE=25 CPU 3Stopped Guest SHARE = 100 Guest SHARE = 100 Guest SHARE = 100 Guest SHARE = 100 Virtual CPU SHARE RedistributionDynamic Virtual Processor Management • Allows z/VM guests to expand or contract the number of virtual processors it uses without affecting the overall CPU capacity it is allowed to consume • Guests can dynamically optimize their multiprogramming capacity based on workload demand • Starting and stopping virtual CPUs does not affect the total amount of CPU capacity the guest is authorized to use • Linux CPU hotplug daemon starts and stops virtual CPUs based on Linux Load Average value • Helps enhance the overall efficiency of a Linux-on-z/VM environment Reduced Need forMultiprogramming Stop 2 CPUs Increased Need forMultiprogramming Start 2 CPUs Note: Overall CPU capacity for a guest system can be dynamically adjusted using the SHARE setting

  20. Linux Linux Dynamically addresources toz/VM LPAR Smart economics: non-disruptively scale your z/VM environment byadding hardware assets that can be shared with every virtual server Linux-on-z/VM and Flexible, Efficient Growth New z/VM V5.4 Function Enhances System Availability • Clients can start small with Linux on System z and non-disruptively grow their environment as business dictates • Users can dynamically add CPUs, memory, I/O adapters, devices, and network cards to a running z/VM LPAR • z/VM virtualizes this capability for guest machines Linux Linux Linux z/VSE z/VM z/OS z/VM I/O and Network LPARResources New with V5.4 Memory CPU

  21. Virtual MachineResource Manager Extreme Virtualization with Linux on z/VMVMRM Cooperative Memory Management (VMRM-CMM) • Problem scenario: virtual memory utilization far exceeds real memory availability • Solution: real memory constraint corrected by z/VM Virtual Machine Resource Manager • Linux images signaled to reducevirtual memory consumption • Demand on real memory andz/VM paging subsystemis reduced • Helps improve overall systemperformance and guest imagethroughput z/VM PagingSubsystem VirtualMemory Disk Space Linux Linux Linux Linux Linux RealMemory ExpandedStorage = Inactive virtual memory Learn more at:ibm.com/servers/eserver/zseries/zvm/sysman/vmrm/vmrmcmm.html = Active virtual memory

  22. 50% MoreThroughput OLTP Database Environment with VMRM-CMM and CMMAExcerpt from “z/VM Large Memory – Linux on System z” Whitepaper

  23. z/VM Minidisk Cache (memory) z/VM Virtual Disk in Storage (memory) R/W R/W R/W R/W R/W R/W SharedData z/VM Technology: Advanced Disk Support Excellent SwapDevice z/VM Virtual Disk in Storage (memory) Linux Linux Linux TDISK1 R/O R/O FullVolume A B C Parallel AccessVolume (PAV) z/VM Control Program Temp Disk: “on-the-fly” disk allocation pool Minidisk: z/VM disk partitioning technology is great for staging TDISK1 Minidisk A FullVolume UnallocatedTemp DiskSpace Minidisk B Notes: R/W = Read/Write access R/O = Read only access Minidisk C

  24. Additional DCSSAddressability 2 GB PGM“C” PGM“B” PGM“A” Extreme Linux-on-z/VM VirtualizationLinux Exploitation of z/VM DCSS Support • Discontiguous Saved Segments (DCSS) • Share a single, real memory location among multiple virtual machines • Can reduce real memory utilization • Linux exploitation: shared program executables • Program executables are stored in an execute-in-place file system, then loaded into a DCSS • DCSS memory locations can reside outside thedefined virtual machine configuration • Access to file system is at memory speeds;executables are invoked directly out of the filesystem (no data movement required) • Avoids duplication of virtual memory • Helps enhance overall system performanceand scalability • z/VM V5.4 support enhancements: • Segments can reside above 2 GB address line • Enables even greater system scalability • New addressing limit is 512 GB DCSS“B” DCSS“B” DCSS“B” DCSS“A” DCSS“A” DCSS“A” DCSS“C” VirtualMemory Linux Linux Linux Linux Linux RealMemory DCSS“B” DCSS“A” DCSS“C” Note: Maximum size of a single DCSS is 2047 MB

  25. Extreme Virtualization with Linux on z/VMLinux Exploitation of z/VM Virtual Disks in Storage (VDISK) • VDISK support is Data-in-Memory technology • Simulate a disk device using real memory • Achieve memory speeds on disk I/O operations • VDISKs can be shared among virtual machines • Linux exploitation: high-speed swap device • Use VDISKs for Linux swap devices instead of real disk volumes • Reduces demand on I/O subsystem • Helps reduce the performance penalty normally associated with swapping operations • An excellent configuration tool that helps clientsminimize the memory footprint required for virtual Linux servers • Helps improve the efficiency of sharing real resources among virtual machines VirtualMemory Linux Linux Linux Linux Linux VDISK VDISK VDISK VDISK VDISK RealMemory

  26. Linux3 Linux4 Linux1 Linux2 z/VM System z and N_Port ID Virtualization (NPIV) Without N_Port ID Virtualization With N_Port ID Virtualization Linux3 Linux4 Linux1 Linux2 z/VM No NPIV: Hosted Linux images can access all the LUNs that are accessible to the real hardware channels. With NPIV: Each Linux image is separately authorized via zoning and LUN-masking with a unique WWPN for each subchannel or virtual host-bus adapter. Linux1 Linux1 Linux1 Linux1 Linux1 Linux2 Linux3 Linux4 Linux2 Linux2 Linux2 Linux2 Linux2 Problem! Linux3 Linux3 Linux3 Linux3 Linux3 Linux4 Linux4 Linux4 Linux4 Linux4 = virtual Worldwide Port Name (WWPN)

  27. IBM System Storage SAN Volume Controller Software V4.3 • z/VM and Linux for System z support SAN Volume Controller (SVC) V4.3 • SVC allows z/VM and Linux to access SCSIstorage from multiple vendors as a singlepool of disk capacity • z/VM FBA emulation allows CMS users toaccess SVC-managed disk space • New function in SVC V4.3: • Space-Efficient Virtual Disks use disk space onlywhen data is written • Space-Efficient FlashCopy uses disk space onlyfor changes between source and target data • Virtual Disk Mirroring helps improve availabilityfor critical applications by storing two copies ofa virtual disk on different disk systems • Supported in z/VM V5.3 and V5.4 • z/VM V5.2 support available with PTF for APAR VM64128 Linux Linux CMS z/VM CP FBAEmulation Spooling Paging SAN Fabric SAN Volume Controller M u l t i - v e n d o r S C S I d i s k s Learn more at: ibm.com/storage/support/2145

  28. Linux Linux Linux Linux Linux Linux Linux Linux z/VM Virtual NetworkingUsing the z/VM Virtual Switch VLAN 1 VLAN 2 • Eliminates need for router to connect virtual servers to physical LAN segments • May reduce overhead associated with router virtual machines • Allows virtual machines to be in the same subnet with the physical LAN segment • Supports Layer 2 (MAC) and Layer 3 (IP) switching • Includes support for IEEE VLAN • Provides centralized network configuration and control • Easily grant and revoke access to the real network • Dynamic changes to VLAN topology can be made transparent to virtual servers Virtual Switch z/VM Control Program Open Systems Adapter (OSA) Physical LAN

  29. Linux Linux Linux Linux Linux Linux NIC NIC NIC NIC NIC NIC Port 3 Port 1 Port 4 Port 2 OSA OSA OSA OSA z/VM Virtual Switch Link Aggregation SupportEnhanced Networking Bandwidth and Business Continuance VMController Port 65 Port 66 Port 67 Port 68 Port 69 Port 70 Load Balancer Aggregator / Multiplexer LACP z/VM z/VM VSWITCH System z LPAR Up to 8 OSA ports per VSWITCH Non-disruptive networkingscalability and failover forGuests and z/VM TCP/IP. Port 1 Port 2 Port 3 Port 4 LACP (Link Aggregation Control Protocol) Switch

  30. z/VM Command and Control Infrastructure • Built-in z/VM facilities enable cost-effective command and control • Performance data collection and reporting for every Linux image • Log accounting records for charge-back • Automate system operations with CMS, REXX, Pipelines, virtual console interrogation using PROP (VM programmable operator) • Dynamic I/O reconfiguration (e.g., dynamically add more disks) • Run EREP on z/VM for system-level hardware error reporting • Priced z/VM features: • DirMaint – simplifies task of adding/modifying/deleting users • Performance Toolkit for VM – performance recording and reporting • RACF Security Server for z/VM – security services (including LDAP) • RSCS – provides NJE connectivity support for Linux systems • Samples, examples, downloads available • IBM Redbooks • z/VM web site (www.vm.ibm.com/download) • Extensive suite of solutions available from ISVs • Visit: ibm.com/systems/z/os/linux/apps/all.html

  31. z/VM Technology – Command and Control InfrastructureLeveraging the IBM Software Portfolio Optimize and Integrate with:- RACF Security Server for z/VM- IBM Director (z/VM Center)- IBM Tivoli OMEGAMON XE for z/VM and Linux- IBM Tivoli Provisioning Manager- IBM WebSphere solutions- IBM Tivoli Monitoring- IBM Operations Manager for z/VM- IBM SAN Volume Controller- More...

  32. z/VM Integrated Systems ManagementUsing the System z Hardware Management Console (HMC) Included in z/VM V5.4 • Allows basic z/VM functionsto be performed from HMC • Network connection not required • Uses SCLP hardware interface to access z/VM systems management APIs • Supported operations: • View z/VM guests • Activate z/VM guests • Deactivate z/VM guests • Display guest configuration and status • z/VM V5.3 also supported • Requires PTFs for APARs VM64233 and VM64234

  33. IBM Systems Director VMControl Image Managerfor Linux on System z Version 2.1 – Available July 24, 2009 • VMControl Image Manager is a plug-in to IBM Systems Director V6.1 • Effectively replaces the “z/VM Center” extension of IBM Director V5.20 • Provides support to manage and automate the deployment of virtual images from a centralized location • A virtual image consists of an operating system instance and the software stack, such as middleware and applications, running on that operating system • VMControl Image Manager provides a graphical interface to create and deploy Linux images on z/VM and AIX images on Power systems • Definition of these system images is based on the industry-standard Open Virtualization Format (OVF) specifications – facilitates importation of virtual images • Deploy an all-in-one solution instead of OS, middleware, and application piece parts • Clone already-tested system configurations • Propagate virtual image updates to all instances • IBM Systems Director and VMControl Image Manager helpsupport a Dynamic Infrastructure • Helps improve responsiveness to changing business needs • May increase operational productivity • Can help reduce service and support costs

  34. Provisioning Software in System z Virtual Linux ServersUsing IBM Tivoli Provisioning Manager Tivoli Provisioning Manager deployment scope: Operating systems like Linux, AIX, Windows Middleware like DB2 and WebSphere Application Server

  35. IBM and Tivoli Virtualization Management Portfolio for Linux on z/VM • IBM System z Virtualization Infrastructure • IBM System z hardware (including LPAR hypervisor) • IBM z/VM Version 5 • Extended Infrastructure Management (Security) • IBM z/VM RACF Security Server (z/VM priced feature) • IBM Tivoli zSecure • IBM Tivoli Access Manager for e-business • IBM Tivoli Access Manager for OS • IBM Tivoli Federated Identity Manager • IBM Tivoli Identity Manager • IBM Directory Server • IBM Directory Integrator • Extended Infrastructure Management (Storage) • IBM SAN Volume Controller (SVC) • IBM Tivoli Storage Manager • IBM TotalStorage Productivity Center • IBM Backup and Restore Manager for z/VM • IBM Tape Manager for z/VM • IBM Archive Manager for z/VM • Extended Infrastructure Management (Network) • IBM z/VM RSCS (z/VM priced feature) • IBM Tivoli Network Manager IP Edition • Monitoring for Virtualization Infrastructure • z/VM Virtual Machine Resource Manager (included with z/VM) • IBM z/VM Performance Toolkit for VM (z/VM priced feature) • IBM Director • IBM Tivoli OMEGAMON XE on z/VM and Linux • IBM Tivoli Monitoring • IBM Tivoli Composite Application Manager for SOA • IBM Tivoli Usage and Accounting Manager • Automation for Virtualization Infrastructure • IBM Operations Manager for z/VM • IBM Tivoli Netcool OMNIbus • IBM Tivoli Workload Scheduler • Provisioning Management • IBM z/VM DirMaint (z/VM priced feature) • z/VM Center task of IBM Director • IBM Tivoli Provisioning Manager • Business Services Management • IBM Tivoli Business Service Manager • IBM Tivoli Service Request Manager • IBM Change and Configuration Management Database (CCMDB) • Resiliency Management • IBM Tivoli System Automation for Multiplatforms • Application Layer Management • IBM Tivoli Application Dependency Discovery Manager • IBM Tivoli OMEGAMON XE for Messaging • IBM Tivoli Composite Application Manager for Response Time • IBM Tivoli Composite Application Manager for Web Resources • IBM Tivoli Composite Application Manager for Transactions • IBM Tivoli License Compliance Manager For specific releases, refer to Tivoli Platform Support Matrix at: ibm.com/software/sysmgmt/products/support/Tivoli_Supported_Platforms.html

  36. z/VM Systems Management Products from IBM • IBM Operations Manager for z/VM • Helps improve the monitoring and management of z/VM virtual machines by automating routine maintenance tasks • Enables users to automatically respond to predictable situations that require intervention • Assists with monitoring and problem determination by allowing authorized users to view and interact with live consoles of z/VM service machines or Linux guests • IBM Backup and Restore Manager for z/VM • Provides z/VM system administrators and operators the ability to efficiently and effectively backup and restore files and data on z/VM systems • Can also backup and restore images of non-z/VM guest systems such as Linux • IBM Tape Manager for z/VM • Manages and monitors tape resources; helps increase data availability and improve operator efficiency • Automates common daily tape operations and helps eliminate tedious, often error-prone, manual tasks • IBM Archive Manager for z/VM • Addresses storage and data management concerns by allowing users to archive historical or other infrequently used data to increase data availability • Helps companies comply with data storage requirements mandated by fiscal or legal regulations and policies

  37. VirtualServers VirtualServers VirtualServers VirtualServers z/VM z/VM z/VM z/VM Shared Everything Infrastructure(CPU, Memory, Network, Adapters, Crypto, Devices) IBM System z Virtualization SupportSaving Money and Reducing ComplexityHelping You “Do More with Less” • Consolidate more cores per CPU • Run more software at less expense • Manage more virtual servers with fewer people • Deploy new servers and applications faster • Absorb workload spikes more easily • Spend less on disaster recovery • Occupy less floor space • Save on energy

  38. The future runs on System z Questions?

  39. Backup Material

  40. Transaction Rate versus Number of Hosted ServersApache Servers with 1GB of Memory Each – z/VM with 8GB of Memory* With APARVM64439applied * z/VM running in IBM System z9 LPAR with 6GB of Central Storage and 2GB of Expanded Storage

  41. Paging Space Utilization versus Number of Hosted ServersApache Servers with 1GB of Memory Each – z/VM with 8GB of Memory* Without APARVM64439applied * z/VM running in IBM System z9 LPAR with 6GB of Central Storage and 2GB of Expanded Storage

  42. z/VM Support for N_Port ID Virtualization • FICON Express features on System z9 and z10 support FCP N_Port ID Virtualization (NPIV) • NPIV enables zoning and LUN masking on a virtual machine basis • Multiple operating system images can now concurrently access the same or different SAN-attached devices (LUNs) via a single, shared FCP channel • Can increase channel utilization • Less hardware required • Helps reduce the complexity of physical I/O connectivity • Supported by z/VM V5.4, V5.3, and V5.2

  43. z/VM Support for Parallel Access Volumes • PAVs allow: • Multiple concurrent I/Os to the same volume by one or more users or jobs • Automatic coordinated Read and Write I/O referential integrity when needed • Supported by z/VM V5.4, V5.3, and V5.2 (V5.2 requires PTF for APAR VM63952) • Supports PAVs as minidisks for guest operating systems that exploit the PAV architecture (e.g., z/OS and Linux for System z) • Provides the potential benefit of PAVs for I/O issued to minidisks owned or shared by guests that do not support native exploitation of PAVs, such as z/VSE, z/TPF, CMS, or GCS • IBM System Storage DASD volumes must be defined to z/VM as: • 3390 Model 2, 3, or 9 on a 3990 Model 3 or 6 Controller • Or…2105, 2107, or 1750 Storage Controller • Note: 3380 track-compatibility mode for the 3390 Model 2 or 3 is also supported. • Potential benefit: • Designed to improve I/O response times by reducing device queuing delays

  44. z/VM HyperPAV Support • IBM System Storage DS8000 HyperPAV is designed to: • Provide more efficient Parallel Access Volumes (PAV) function • Help customers who implement larger volumes to scale I/O rates without the need for additional PAV-alias definitions • Help reduce overhead, improve addressing efficiencies, and provide storage capacity and performance improvements • Enable a dynamic response to changing workloads • Reduce costs via simplified management of aliases • Enable customers to stave off migration to larger volume sizes • z/VM support is designed to: • Potentially reduce the number of alias-device addresses needed for parallel I/O operations • Provide support of HyperPAV volumes as linkable minidisks for guest operating systems, such as z/OS, that exploit this new PAV architecture • Provide the potential benefits of HyperPAV volumes for minidisks owned or shared by guests that do not specifically exploit HyperPAV volumes (e.g., CMS, Linux)

  45. z/VM Virtual Switch SupportLayer 3 Compared to Layer 2 Switching Layer 3 Switching Layer 2 Switching 9.47.255.45 9.47.255.46 9.47.255.47 02-00-00-00-00-01 02-00-00-00-00-02 02-00-00-00-00-03 Linux Guest Linux Guest Linux Guest Linux Guest Linux Guest Linux Guest LEGEND IP Addresses MAC Addresses z/VM Virtual Switch (L3) z/VM Virtual Switch (L2) Data (QDIO) OSA-Express or OSA-Express2 Control (R/W) OSA-Express or OSA-Express2 00-09-6B-1A-2A-F4 00-09-6B-1A-2B-71 Outboard Switch • IP environment only • One MAC address shared by all • guests using Virtual Switch • IP address used for packet forwarding • IP or non-IP environments • All guests have their own MAC address • Automatically assigned by z/VM • Or locally administered • MAC header used for packet forwarding

  46. Business Services Management Application Layer Management … Provisioning Management Resilience Management Security Storage Network Extended Infrastructure Management Automation for Virtualization Infrastructure Monitoring for Virtualization Infrastructure IBM System z Virtualization Infrastructure IBM Tivoli Virtualization Management for System z Helping Clients Manage and Control Their Virtualized IT Infrastructure

  47. Monitoring System z Virtual Linux ServersUsing IBM Tivoli OMEGAMON XE on z/VM and Linux V4.1.2 • Combined product offering that monitors z/VM and Linux for System z • Provides work spaces that display: • Overall system health • Workload metrics forlogged-in users • Individual device metrics • LPAR data • Provides compositeviews of Linux runningon z/VM • New function in V4.1.2: • Additional monitoring tohelp identify bottlenecksin the I/O subsystem • Processor spin lockwait statistics Learn more at: ibm.com/software/tivoli/products/omegamon-xe-zvm-linux

  48. IBM Tivoli Service Management Center for System z Enabling clients to use System z as an integrated, enterprise-wide hub for the efficient management of business and IT services • Unique advantages that address many of today’s operational challenges • Hub for managing services that span heterogeneous operating systems and platforms • Integrated IBM Tivoli z/OS and Linux on System z management solutions • Utilize virtualization and ability to consolidate workloads • Unified means for System z practitioners to have enhanced visibility, control and automation • Enabling a dynamic and highly efficient servicedelivery model • Manage a service landscape running on System zfrom bare metal up to the application as if it werehomogeneous • Dynamic provisioning, configuration andde-provisioning complete application landscapes • Exploits the multi-OS environment and elasticityof the platform to support the delivery of SaaSand a cloud user experience

  49. GDPS/PPRC Multiplatform Resiliency for System z

  50. Linux and z/VM on System z While Linux is Linux, Linux on System z benefits from its support of the outstanding z/VM virtualization and System z hardware features Consolidation • Servers, I/O, networks, storage, cryptography • Enhanced staff productivity • Extreme sharing of applications and utilities • Consolidate I/O-intensive workloads (e.g., database) Security • Image isolation • Privacy protection • Identity management • Cryptographic acceleration • Centralized authentication • System z qualities of service • Common Criteria Certification • Ethical hacking test validation • Internal HiperSockets network Business resiliency • Best-in-class hardware reliability • High availability and system failover • GDPS/PPRC disaster recovery • Serviceability • Storage failover (HyperSwap) • Data replication (XRC and PPRC) Linux andSystem zVirtualization Operational simplification • Extreme virtualization • Resource simulation • Single point of control • Large single-system image • z/OS similarities and synergies • Highly granular resource sharing Dynamic infrastructure • Scale up and scale out • Rapid server (de)commissioning • Dynamically add HW to Linux and z/VM • Idle servers don’t consume resources Proximity to data • Can increase transactional throughput • Shared data access • Integrated storage management • Flexible, convenient HiperSockets connectivity

More Related