Presentation power vm editions and power systems virtualization - basic

pVM14
PowerVM Editions and Power Systems Virtualization
Anandakumar Mohan
STG Lab Services, ananmoha@in.ibm.com
© 2010 IBM Corporation
IBM POWER™ Systems and System Storage™ Symposium Sept 6-9 Bangalore, India

Download this slide
http://ouo.io/rZZrV

IBM POWER™ Systems and System Storage™ Symposium
Sept 6-9 Bangalore, India
Agenda
• Power Systems Virtualization Overview
• Power Systems Virtualization Matrix
• PowerVM Editions

Networks and network storage
Unassigned
on demand
resources
Hypervisor™
i5/OS*
Service
processor
Linux
partitions
Virtual Network
AIX 5L
V5.2
Virtual processors Virtual adapters
Linux
kernels
AIX 5L
kernels
SLIC
Virtual
network
& storage
Processors
Memory
Expansion slots
Local devices & storage
Hardware
Management
Console
(HMC)
Virtualization Architecture
Workload management and provisioning
AIX 5L V5.3
partitions
Virtual
I/O
server

Simultaneous multithreading
POWER4 (Single Threaded)
FX0
FX1
LSO
LS1
FP0
FP1
BRZ
CRL
Thread0 active
No thread active
Thread1 active
• Utilizes unused execution unit cycles
• Natural fit with superscalar out-of-order execution core
• Dispatch two threads per processor: “It’s like doubling the number of processors.”
• Net result:
– Better performance
– Better processor utilization
• POWER7 processor supports 4 SMT threads
Appears as 2 CPUs
per physical CPU to
the operating
system
Systemthroughput
SMTST
POWER6 (simultaneous multithreading)

Micro-Partitions
• Micro-partition is a type of logical partition where the processor is shared among other micro-
partitions in the system. The processors are shared from a CPU pool called shared pool.
• Micro-partition is also referred to as shared partitions. 10 micro-partitions per activated processor
supported.
• Allows significantly increased overall utilization of processor resources within the system.
• The micro-partition is provided with a processor entitlement—the processor capacity guaranteed to it
by the POWER Hypervisor. A micro-partition must have a minimum of 0.1 of the capacity of a physical
processor and can be up to the capacity of the system.
• In Micro-Partitions, the processors are represented through Virtual Processors that are scheduled on
physical processor by hypervisor based on the configured capacity of the partition
• Two modes supported
– Uncapped Mode (The processing capacity can exceed the entitled capacity when resources are
available in their Shared-Processor Pool. Extra capacity is distributed on a weighted basis. You
must specify the uncapped weight of each micro-partition when it is created.
– Capped Mode (The processing capacity given can never exceed the entitled capacity of the
micro-partition)

Micro-Partitioning
Increased number of LPARs
– Micro-partitions: Up to 254
Configured via the HMC
Number of logical processors
– Minimum/maximum
Entitled capacity
– In units of 1/100 of a CPU
– Minimum 1/10 of a CPU
Variable weight
– % share (priority) of
surplus capacity
Capped or uncapped partitions
Micro-partitions
Pool of 6 CPUs
Linux
i5/OSV5R3**
AIX5LV5.3
AIX5LV5.3
Linux
Entitled
capacity
Max
Hypervisor
Min
AIX5LV5.2
AIX5LV5.3
Dynamic
LPARs
Whole
Processors

Micro-partition Technologies
• Related Micro-partition technologies
–Multiple Shared-Processor Pools (A new capability supported on
POWER6 servers. This capability allows a system administrator to
create a set of micro-partitions with the purpose of controlling the
processor capacity that can be consumed from the physical
shared-processor pool.)
DB2 cores to license: 5 instead of 8
• Max Cap for pool # 1 = 5 Procs
• Total VPs for DB2 LPARs =8
WAS cores to license: 6 instead of 14
• Max Cap for pool = 6 Procs
• Total VPs for WAS LPARs =14

Dedicated processor sharing
• POWER6 processors in a dedicated partition can donate unused capacity to the
shared pool.
• The excess (donated) dedicated capacity can be utilized by uncapped shared
partitions in addition to the shared processors.
• The dedicated logical partition has a “donation” option that can be enabled for the
HMC panel. This is done by an interrupt mechanism between the OS and the
POWER Hypervisor (same behavior as shared processor micro-partitions).
Idle CPU

• In case of processor failure
– If no unassigned processors available
• The partition can acquire a replacement processor from logical partition with a lower
availability priority
• Allow the logical partition with the higher partition-availability priority to continue running after
a processor failure
Processor recovery: Partition availability priority
Server
Configuration
Availability
Priority Update

Active Memory Sharing
• Active Memory Sharing will intelligently flow memory from one partition to another for
increased utilization and flexibility of memory usage.
• Memory virtualization enhancement for Power Systems
– Memory dynamically allocated based on partition’s workload demands
– Contents of memory written to a paging device
– Improves memory utilization
• Designed for partitions with variable memory requirements
– Low average memory requirements
– Active/inactive environments
– Workloads that peak at different times across the partitions
• Supports over-commitment of physical memory with overflow going to a paging
device.
– Users can define a partition with a logical memory size larger than the available physical
memory.
– Users can activate a set of partitions whose aggregate logical memory size exceeds the
available physical memory.

Dedicated
Processor
LPAR
Finance
70 GB
LPAR
#3
LPAR
#1
LPAR
VIOS
LPAR
#2
Dedicated
Processor
LPAR
Planning
105 GB 105 GB
350 GB Memory
105 GB 5 GB60 GB
Power Hypervisor
Micro-Partition Processor Pool
AIX AIX AIX Linux IBM i AIX
Memory Pool: 210 GB
M
Total Defined Memory
450 GB
Physical Memory
350 GB
Shared Memory Pool
210 GB
Active Memory Sharing Configuration
Shared Memory Pool
Paging Devices
Disk4
Disk1
Disk2
Disk3
M M M
M M M
M M M
M M M
M M M
M M M
M M M
M M M
M M M
M M M
M M M
M M M
M M M
M M M
M M M
M M M
M M M
M M M
M M M
M M M
M M M
M M M
M M M
M M M
M M M
M M M
M M M
M M M
M M M
M M M

Active Memory Expansion
• Active Memory Expansion increases a system’s effective memory capacity.
• Active Memory Expansion employs memory compression technology to
transparently compress in-memory data, allowing more data to be placed into
memory and thus expanding the memory capacity of POWER7 systems.
• Benefits:
– Higher Consolidation
– LPAR throughput increase
• The memory expansion factor is specified as a multiplier of a LPAR’s true memory
size:
LPAR_expanded_mem_size = LPAR_true_mem_size * LPAR_mem_exp_factor
• AME Planning tool can be used for determining the expansion factor and CPU
overhead
• Requires separate license to activate AME at the server level

• POWER7 advantage
• Expand memory beyond physical limits
• More effective server consolidation
– Run more application workload / users per partition
– Run more partitions and more workload per server
Expand
memory
True
memory
True
memory
True
memory
True
memory
True
memory
True
memory
Expand
memory
Expand
memory
Expand
memory
Effectively up
to 100% more
memory
Expand
memory
Expand
memory

• Innovative POWER7 technology
– For AIX 6.1 or later
– For POWER7 servers
• Uses compression/decompression to effectively expand the true physical memory
available for client workloads
• Often a small amount of processor resource provides a significant increase in the
effective memory maximum
– Processor resource part of AIX partition’s resource and licensing
• Actual expansion results dependent upon how “compressible” the data being used in
the application
• Tool amepat available to identify compression possible on a given workload and
approximate CPU utilization

M
G
Physical/true memory
Gained memory capacity
MMMM
MMMM
MMMM
MMMM
MMMM
MMMM
96 GB LPAR1
MMMMG
MMMMG
MMMMG
MMMMG
MMMMG
MMMMG
120 GB LPAR1
MMGG
MMGG
MMMG
MMMG
MMMG
MMMG
96 GB LPAR1
MM
MM
MG
MG
MG
MG
48 GB LPAR2
Assumes
25%
expansion
Assumes
50%
expansion
Active Memory Expansion – Basic Concept

Virtual I/O Server
• Implements I/O virtualization by allowing physical network adapters and SCSI adapters to be
shared by multiple partitions.
• Helps overcome the limitation by maximum physical I/O slots supported and improves overall
system resource utilization.
• Virtual I/O server is hosted as a separate partition, created as of type Virtual I/O server
• Virtual I/O server owns physical I/O adapters, resources that are shared with other partitions on
the system (called client partitions)
• Some components
– Virtual Ethernet – Supported by Hypervisor by means of implementing a Layer 2 Virtual switch.
It allows partitions within the system to communicate with each other without physical adapter.
– Shared Ethernet Adapter – A Layer 2 bridge created on Virtual I/O server to bridge several
virtual networks with in the system to external network
– Virtual SCSI – Supported by Virtual I/O server to share physical SCSI, FC disks with multiple
partitions. It can export logical volumes or entire disk to client partitions. Optical device such
as CD-ROM is supported as well.
– Virtual Optical devices – Supported by VIO server to create virtual optical devices which can
be shared as RAM or ROM to multiple LPARs.

Virtual I/O server architecture

Integrated Virtual Ethernet (IVE)
• IVE offers an alternative to the use of virtual Ethernet or the Shared Ethernet
Adapter service of the Virtual I/O Server. Supported only on platforms that are entry,
midrange platforms that are POWER6 or above
• IVE offers greater throughput and lower latency than PCIe or PCI-X bus connected
Ethernet adapters as it is connected to the GX+ bus of the POWER6-based System
p server.
• IVE also provides special hardware features that enables logical Ethernet adapters
which can communicate directly with logical partitions running on the system.
• IVE refers to the collective name referring to a number of technologies including
Hardware - Host Ethernet Adapter (HEA), Software components and Power
Hypervisor functions

Integrated Virtual Ethernet

Integrated Virtual Ethernet Components

Implementing IVE

Live Partition mobility
• Move running partitions from one POWER6/POWER7 system to another
– Live (active) partition mobility
– Inactive partition mobility
• Provides non-disruptive system maintenance flexibility
– Reduce planned down time by dynamically moving applications from one server to another.
• Environment and system resource optimization option
– Can balance workloads and resources
– Can also be used as a mechanism for server consolidation
– Provides greater control over the usage of resources in the data center
• Live Partition Mobility can be automated and incorporated into system management tools and
scripts

Live Partition Mobility – POWER6 & POWER7 feature

Implementing Live Partition Mobility

NPIV (N_Port ID Virtualization)
• N_Port ID Virtualization (NPIV) provides direct Fibre Channel connections from client
partitions to SAN resources , simplifying SAN management
– N_Port ID Virtualization (NPIV) is a fibre channel industry standard method for
virtualizing a physical fibre channel port.
– Fibre Channel Host Bus Adapter is owned by VIOS partition
– NPIV allows one physical port to be associated with multiple N_Port IDs (WWPNs),
so a physical fibre channel HBA can be shared across multiple guest operating
systems in a virtual environment.
– On POWER 6, NPIV allows CLIENT logical partitions(LPARs) to have dedicated
N_Port IDs (WWPNs), giving the LPAR a unique identity to the SAN, just as if it had
a dedicated physical HBA(s).
– Client LPAR WWPNs become part of the partition definition and move with the client
from server to server (LPM)
– Supported with PowerVM Express, Standard, and Enterprise Edition
– Supports AIX 5.3 and AIX 6.1 partitions with 8Gb PCIe adapter

Hypervisor
vSCSI Functional Flow
VIOS 1 AIX
LVM LVM
VSCSIVSCSI
target
SAN
multipathing
Disk Driver
LVM
VSCSI
target
VIOS 2
multipathing
Disk Driver
VSCSI
multipathing
Disk Driver
fibre channel
HBAs
fibre channel
HBAs

Hypervisor
NPIV Functional Flow
VIOS 1 AIX
LVM
multipathing
Disk Driver
HBA
module
SAN
module
VIOS 2
HBA
fibre channel
HBAs
fibre channel
HBAs

WPAR Manager for Managing WPAR
• WPAR and WPAR manager are support only with AIX 6.1 and above
• WPAR Manager is a Management Tool for managing multiple WPARs on different server
instances
• Provided as separate LPP
• Available as Plugin with IBM Systems Director
• WPAR Live Application Mobility LPP is available only with WPAR Manager
– Is available as part of AIX Enterprise Edition
– Or can be purchased separately as IBM Systems Director Plugin

PowerVM Lx86
• Lx86 - PowerVM Lx86 enables to run a wide range of x86 Linux applications on Power
Systems platforms within a Linux on Power partition. This feature is designed to support the
consolidation of x86 applications onto the Power platform

Power Systems Virtualization Matrix
Category PowerVM feature Key Benefits
Workload Isolation • LPAR
• WPAR
Isolate workload in different
logical environments
Processor Virtualization • Micro partitioning
• Shared Processor Pool
• Multiple Shared Processor pool
• Dedicated processor sharing
Improves effective processor
utilization, workload
consolidation
Memory Virtualization • AMS
• AME (Power7)
Improves effective memory
utilization, workload
consolidation
IO Virtualization • VIO Server
• NPIV
Effective I/O sharing, Workload
consolidation
Mobility Feature • Live Partition Mobility
• Live Application Mobility
Enable “Live” mobility with
minimum downtime

PowerVM - Editions
• PowerVM is available in different editions comprising of different capabilities. Customer can choose the right one based on the
need.

References
• PowerVM Information Roadmap
– http://publib.boulder.ibm.com/eserver/roadmap_powervm.html
• PowerVM Virtualization Managing and Monitoring
– http://www.redbooks.ibm.com/redpieces/abstracts/sg247590.html?Open
• PowerVM Virtualization on IBM System p: Introduction and Configuration Fourth
Edition
– http://www.redbooks.ibm.com/abstracts/sg247940.html?Open
• Integrated Virtual Ethernet Adapter Technical Overview and Introduction
– http://www.redbooks.ibm.com/abstracts/redp4340.html?Open
• PowerVM Live Partition Mobility on IBM System p
• Workload Partition Management in IBM AIX Version 6.1

41 © 2010 IBM Corporation
Trademarks
The following are trademarks of the International Business Machines Corporation in the United States, other countries, or both.
Not all common law marks used by IBM are listed on this page. Failure of a mark to appear does not mean that IBM does not use the mark nor does it mean that the product is not
actively marketed or is not significant within its relevant market.
Those trademarks followed by ® are registered trademarks of IBM in the United States; all others are trademarks or common law marks of IBM in the United States.
The following are trademarks or registered trademarks of other companies.
Adobe, the Adobe logo, PostScript, and the PostScript logo are either registered trademarks or trademarks of Adobe Systems Incorporated in the United States, and/or other countries.
Cell Broadband Engine is a trademark of Sony Computer Entertainment, Inc. in the United States, other countries, or both and is used under license therefrom.
Java and all Java-based trademarks are trademarks of Sun Microsystems, Inc. in the United States, other countries, or both.
Microsoft, Windows, Windows NT, and the Windows logo are trademarks of Microsoft Corporation in the United States, other countries, or both.
Intel, Intel logo, Intel Inside, Intel Inside logo, Intel Centrino, Intel Centrino logo, Celeron, Intel Xeon, Intel SpeedStep, Itanium, and Pentium are trademarks or registered trademarks of Intel
Corporation or its subsidiaries in the United States and other countries.
UNIX is a registered trademark of The Open Group in the United States and other countries.
Linux is a registered trademark of Linus Torvalds in the United States, other countries, or both.
ITIL is a registered trademark, and a registered community trademark of the Office of Government Commerce, and is registered in the U.S. Patent and Trademark Office.
IT Infrastructure Library is a registered trademark of the Central Computer and Telecommunications Agency, which is now part of the Office of Government Commerce.
* All other products may be trademarks or registered trademarks of their respective companies.
Notes:
Performance is in Internal Throughput Rate (ITR) ratio based on measurements and projections using standard IBM benchmarks in a controlled environment. The actual throughput that any user will
experience will vary depending upon considerations such as the amount of multiprogramming in the user's job stream, the I/O configuration, the storage configuration, and the workload processed.
Therefore, no assurance can be given that an individual user will achieve throughput improvements equivalent to the performance ratios stated here.
IBM hardware products are manufactured from new parts, or new and serviceable used parts. Regardless, our warranty terms apply.
All customer examples cited or described in this presentation are presented as illustrations of the manner in which some customers have used IBM products and the results they may have achieved. Actual
environmental costs and performance characteristics will vary depending on individual customer configurations and conditions.
This publication was produced in the United States. IBM may not offer the products, services or features discussed in this document in other countries, and the information may be subject to change without
notice. Consult your local IBM business contact for information on the product or services available in your area.
All statements regarding IBM's future direction and intent are subject to change or withdrawal without notice, and represent goals and objectives only.
Information about non-IBM products is obtained from the manufacturers of those products or their published announcements. IBM has not tested those products and cannot confirm the performance,
compatibility, or any other claims related to non-IBM products. Questions on the capabilities of non-IBM products should be addressed to the suppliers of those products.
Prices subject to change without notice. Contact your IBM representative or Business Partner for the most current pricing in your geography.
For a complete list of IBM Trademarks, see www.ibm.com/legal/copytrade.shtml:
*, AS/400®, e business(logo)®, DBE, ESCO, eServer, FICON, IBM®, IBM (logo)®, iSeries®, MVS, OS/390®, pSeries®, RS/6000®, S/30, VM/ESA®, VSE/ESA,
WebSphere®, xSeries®, z/OS®, zSeries®, z/VM®, System i, System i5, System p, System p5, System x, System z, System z9®, BladeCenter®

Presentation power vm editions and power systems virtualization - basic

Empfohlen

Empfohlen

Weitere ähnliche Inhalte

Was ist angesagt?

Was ist angesagt? (20)

Andere mochten auch

Andere mochten auch (15)

Ähnlich wie Presentation power vm editions and power systems virtualization - basic

Ähnlich wie Presentation power vm editions and power systems virtualization - basic (20)

Mehr von solarisyougood

Mehr von solarisyougood (20)

Kürzlich hochgeladen

Kürzlich hochgeladen (20)

Presentation power vm editions and power systems virtualization - basic