NPIV and the IBM Virtual I/O Server (VIOS)

October 2008

2006 IBM Corporation

NPIV Overview
N_Port ID Virtualization (NPIV) is a fibre channel industry standard

method for virtualizing a physical fibre channel port.

NPIV allows one F_Port to be associated with multiple N_Port IDs,

so a physical fibre channel HBA can be shared across multiple guest operating systems in a virtual environment.
On POWER, NPIV allows logical partitions (LPARs) to have

dedicated N_Port IDs, giving the OS a unique identity to the SAN, just as if it had a dedicated physical HBA(s).

NPIV specifics
PowerVM VIOS 2.1 - GA Nov 14 NPIV support now has planned GA of Dec 19 Required software levels
VIOS Fix Pack 20.1 AIX 5.3 TL9 SP2 AIX 6.1 TL2 SP2 HMC 7.3.4 FW Ex340_036 Linux and IBM i planned for 2009

Required HW
POWER6 520,550,560,570 only at this time, Blade planned for 2009 5735 PCIe 8Gb Fibre Channel Adapter

unique WWPN generation (allocated in pairs)*** Each virtual FC HBA has a unique and persistent identity Compatible with LPM (live partition mobility) VIOS can support NPIV and vSCSI simultaneously Each physical NPIV capable FC HBA will support 64 virtual ports HMC-managed and IVM-managed servers

Storage Virtualisation
VIO client Generic SCSI disk Virtual SCSI Adapters SCSI SAS vSCSI VIOS Note Path code And Devices difference

VI O With NPIV S
VIO client EMC 5000 LUN Virtual FC Adapters

IBM 2105 LUN

2. 1

VIOS
FC Adapters

FC Adapters

Storage Virtualiser

Pass Through mode

VIOS Admin in charge

SAN NPIV SAN

SAN Admin Back in charge

EMC 5000 LUN

IBM 4700 LUN

EMC 5000 LUN

IBM 4700 LUN

HMC 7.3.4

NPIV What you need?

Supports SCSI-2 reserve/release SCSI-3 persistent reserve

AIX 5.3 TL09, AIX 6.1 TL02, SLES 10 SP2, RHEL 4.7, RHEL 5.2 New EL340 Firmware (disruptive) VIOS 2.1

POWER6 only
VIO client EMC 5000 LUN

VI O S
Virtual FC Adapters

IBM 2105 LUN

2. 1

VIOS
FC Adapters

New PCIe 8Gbit Fibre Channel adapters (can run 2 or 4 Gbit) Entry SAN switch must be NPIV capable Disk Sub-System does not need to be NPIV capable SAN Fabric can be 2, 4 or 8 Gbit (not 1 Gbit)
IBM 4700 LUN

EMC 5000 LUN

VI O S
NPIV What you do?

2. 1

1.

HMC 7.3.4 configure

Virtual FC Adapter Just like virtual SCSI On both Client and Server

Virtual I/O Server

VI O S
NPIV What you do?

2. 1

2.

Once Created: LPAR Config Manage Profiles Edit click FC Adapter Properties and the WWPN is available

VI O S
NPIV What you do?
$ ioslevel 2.1.0.0 $ lsdev | grep FC fcs0 Available FC Adapter fscsi0 Available FC SCSI I/O Controller Protocol Device vfchost0 Available Virtual FC Server Adapter $ vfcmap -vadapter vfchost0 -fcp fcs0 vfchost0 changed $
3.

2. 1

VIOS connect the virtual FC adapter to the physical FC adapter

With vfcmap lsmap all npiv lsnports shows physical ports supporting NPIV

4.

SAN Zoning
To allow the LPAR access to the LUN via the new WWPN Allow both WWPN and on any Partition Mobility target.

NPIV benefits
NPIV allows storage administrators to used existing tools

and techniques for storage management

solutions such as SAN managers, Copy Services, backup /

restore, should work right out of the box

storage provisioning / ease-of-use Zoning / LUN masking physical <-> virtual device compatibility tape libraries SCSI-2 Reserve/Release and SCSI3 Persistent Reserve

clustered/distributed solutions Load balancing (active/active)

solutions enablement (HA, Oracle,) Storage, multipathing, apps, monitoring..

NPIV implementation
Install the correct levels of VIOS, firmware, HMC,8G HBAs,

and NPIV capable/enabled SAN and storage

Virtual Fibre channel adapters are created via the HMC The VIOS owns the server VFC, the client LPAR owns the

client VFC
Server and Client VFCs are mapped one-to-one with the

vfcmap command in the VIOS

The POWER hypervisor generates WWPNs based on the range of names

available for use with the prefix in the vital product data on the managed system.
The hypervisor does not reuse the WWPNs that are assigned to the virtual

Fibre Channel client adapter on the client logical partition.

Things to consider
WWPN pair is generated EACH time you create a VFC. NEVER is re-created or re-used. Just like a real HBA. If you create a new VFC, you get a NEW pair of WWPNs. Save the partition profile with VFCs in it. Make a copy, dont delete a profile with a VFCin it. Make sure the partition profile is backed up for local and disaster recovery! Otherwise youll have to create new VFCs and map to them during a recovery. Target Storage SUBSYSTEM must be zoned and visible from source and destination systems for LPM to work. Active/Passive storage controllers must BOTH be in the SAN zone for LPM to work Do NOT include the VIOS physical 8G adapter WWPNs in the zone You should NOT see any NPIV LUNs in the VIOS Load multi-path code in the client LPAR, NOT in the VIOS Monitor VIOS CPU and Memory NPIV impact is unclear to me at this time No passthru tunables in VIOS

NPIV useful commands

vfcmap -vadapter vfchostN -fcp fcsX maps the virtual FC to the physical FC port vfcmap -vadapter vfchostN -fcp un-maps the virtual FC from the physical FC port lsmap all npiv shows the mapping of virtual and physical adapters and current status lsmap npiv vadapter vfchostN shows same ofr one VFC lsdev -dev vfchost* lists all available virtual Fibre Channel server adapters lsdev -dev fcs* lists all available physical Fibre Channel server adapters lsdev dev fcs* -vpd shows all physical FC adapter properties lsnports shows the Fibre Channel adapter NPIV readiness of the adapter and the SAN

switch.
lscfg -vl fcsx In A(X client lpar, shows virtual fibre channel properties

NPIV resources
Redbooks:
SG24-7590-01 PowerVM Virtualization on IBM Power Systems (Volume 2): Managing and Monitoring SG24-7460-01 IBM PowerVM Live Partition Mobility

VIOS latest info:

http://www14.software.ibm.com/webapp/set2/sas/f/vios/home.html

Questions

BACKUP VIOS SLIDES

#5735 PCIe 8Gb Fibre Channel Adapter

Supported on 520, 550, 560, 570, 575 Dual port adapter - each port provides single initiator
Automatically adjusts to SAN fabric 8 Gbps, 4 Gbps, 2 Gbps LED on card indicates link speed

Ports have LC type connectors

Cables are the responsibility of the customer. Use multimode fibre optic cables with short-wave lasers:

OM3 - multimode 50/125 micron fibre, 2000 MHz*km bandwidth 2Gb (.5 500m) 4Gb (.5 380m) 8Gb (,5 150m) OM2 - multimode 50/125 micron fibre, 500 MHz*km bandwidth 2Gb (.5 150m) 4Gb (.5 70m) 8Gb (,5 21m) OM1 - multimode 62.5/125 micron fibre, 200 MHz*km bandwidth 2Gb (.5 300m) 4Gb (.5 150m) 8Gb (,5 50m)

Virtual SCSI
client LPAR (ie virtual machine) is the SCSI initiator, VIOS is the SCSI Target server LPAR owns physical I/O resources client LPAR sees standard SCSI devices, accesses LUNs via a virtual SCSI adapter VIOS is a standard storage subsystem transport layer is the interpartition communication channel provided by PHYP (reliable msg transport) SRP(SCSI Remote DMA Protocol) LRDMA(logical redirected DMA)

Virtual SCSI (continued)

SCSI peripheral device types supported: Disk (backed by logical volume, physical volume, or file) Optical (backed by physical optical, or file) Adapter and device sharing Multiple I/O Servers per system, typically deployed in pairs VSCSI client support: AIX 5.3 or later Linux(SLES9+, RHEL3 U3+, RHEL4) or later IBM i Boot from VSCSI devices Multi-pathing for VSCSI devices

Basic vSCSI Client And Server Architecture Overview

I/O Server
virtual server adapter

I/O client

I/O client

I/O client

virtual client adapter

physical HBA and storage

PHYP

vSCSI
vio client generic scsi disk SCSI
VIOS VIOS VIOS

NPIV
vio client EMC EMC FCP
VIOS

generic scsi disk

IBM 2105

FC HBAs

FC HBAs

FC HBAs

FC HBAs

SAN

SAN

EMC

IBM 2105

EMC

IBM 2105

The vSCSI model for sharing storage resources is storage virtualizer. Heterogeneous storage is pooled by the VIOS into a homogeneous pool of block storage and then allocated to client LPARs in the form of generic SCSI LUNs. The VIOS performs SCSI emulation and acts as the SCSI Target.

With NPIV, the VIOS's role is fundamentally different. The VIOS facilitates adapter sharing only, there is no device level abstraction or emulation. Rather than a storage virtualizer, the VIOS serving NPIV is a passthru, providing an FCP connection from the client to the SAN.

vSCSI
VIOS AIX VIOS

LVM multipathing

LVM

LVM multipathing

multipathing Disk Driver Disk Driver

Disk Driver

fibre channel HBAs

PHYP

VSCSI target

VSCSI HBA

VSCSI HBA

VSCSI target

fibre channel HBAs

SAN

NPIV
VIOS AIX VIOS

LVM

multipathing
VFC HBA VFC HBA VFC HBA VFC HBA VFC HBA PHYP VFC HBA VFC HBA VFC HBA

Disk Driver

fibre channel HBAs

passthru module

VFC HBA

VFC HBA

passthru module

fibre channel HBAs

SAN

NPIV provisioning, managing, monitoring

VIOS
DS4000, DS6000, DS8000
WWPN

vio client

NPIV enabled SAN

N P I V
WWPN

vio client
WWPN

SVC tape library

N P I V

WWPN WWPN

vio client

WWPN

vio client

VIOS

HDS EMC NetApp

vFC adapter pair

Live Partition Mobility(LPM) and NPIV

VIOS vio client
WWPN

VIOS
WWPN

vio client

N P I V
WWPN

N P I V

vio client
WWPN

NPIV enabled SAN

N P I V

WWPN

vio client
WWPN

vio client

WWPN WWPN

N P I V

WWPN WWPN

vio client

vio client

WWPN

WWPN

vio client

VIOS

VIOS

WWPNs are allocated in pairs

IBM System p

Heterogeneous multipathing
VIOS#1 Passthru module

AIX
A

NPIV

NPIV

Fibre HBA

POWER Hypervisor

Storage Controller
SAN Switch SAN Switch

Fibre HBA
D C D

2006 IBM Corporation

VIOS block diagram (vSCSI and NPIV)

NPIV ports

POWER Server

passthru module

LPARs

vSCSI devices (SCSI LUNS)

block virtualization

filesystems LVM multi-pathing disk | optical physical adapters FC/NPIV | SCSI | iSCSI | SAS | USB | SATA
virtual devices back by a file virtual devices backed by a logical volume virtual devices backed by a pathing device virtual devices physical peripheral device virtual tape NPIV

physical storage

vSCSI basics VIOS

File backed disk storage pool (/var/vios/storagepools/pool_name) /var/vios/storagepools/pool1/foo1 Virtual optical media repository (/var/vios/VMLibrary) /var/vios/VMLibrary/foo2.iso) Logical Volume storage pool (/dev/VG_name) /dev/storagepool_VG/lv_client12 Physical device backed devices (/dev) /dev/hdisk10 /dev/lv_client20 /dev/powerpath0 /dev/cd0 /dev/sas0 NPIV (/dev) /dev/fscsi0 <-> WWPN p2v mapping devices S C S I E M U L A T I O N a1: ../../../foo1 a2 ../../../foo2.iso b1: ../../lv_client12 b2: /dev/hdisk10 b3: /dev/lv_client20 b4: /dev/powerpath0 b5: /dev/cd0 b6: /dev//sas0

POWER Server

LPARs (AIX, Linux, or i5/OS)

physical storage
Fibre channel, iSCSI, SAS, SCSI, USB, SATA

a1 b1
b6

b3 b2 b1
b5

b4
a2

c1: /dev/fscsi0

e1

vSCSI Target

PHYP

Data flow using LRDMA for vSCSI devices

vscsi client
data buffer
Da ta
vscsi initiator vscsi target

I/O server
physical adapter driver

(L RD M

control
A)

phyp

pci adapter

VSCSI redundancy using multipathing at the client

I/O Server

AIX client
MPIO

I/O Server

disk driver

vscsi target

vscsi initiator

vscsi initiator

vscsi target

PHYP

SAN

Direct attach fibre channel block diagram AIX

generic disk driver

data buffer

fibre channel HBA DD

Da ta

phyp
FC HBA

SCSI Initiator

NPIV block diagram

AIX
generic disk driver

VIOS

data buffer
Da ta

VFC client

passthru module

fibre channel HBA DD

phyp

FC HBA
SCSI Initiator

Testing VIOS
physical fibre chan HBA

System p/i Server

logical partitions

POWER5 Server
Linux AIX

VIOS
v S C S I

AIX

AIX

AIX

AIX

A1 A2 A3 A4 A5 A6

A7 A8

Virtual SCSI

POWER Hypervisor
physical physical fibre chan fibre chan HBA HBA

External Storage ie. DS8K

A1 A2 A3 A4 A5 A6 A7 A8
Available via optional Advanced POWER Virtualization or POWER Hypervisor and VIOS features.

#5735 PCIe 8Gb Fibre Channel Adapter

Supported on 520, 550, 560, 570, 575 Dual port adapter - each port provides single initiator
Automatically adjusts to SAN fabric 8 Gbps, 4 Gbps, 2 Gbps LED on card indicates link speed

Ports have LC type connectors

Cables are the responsibility of the customer. Use multimode fibre optic cables with short-wave lasers:

OM3 - multimode 50/125 micron fibre, 2000 MHz*km bandwidth 2Gb (.5 500m) 4Gb (.5 380m) 8Gb (,5 150m) OM2 - multimode 50/125 micron fibre, 500 MHz*km bandwidth 2Gb (.5 150m) 4Gb (.5 70m) 8Gb (,5 21m) OM1 - multimode 62.5/125 micron fibre, 200 MHz*km bandwidth 2Gb (.5 300m) 4Gb (.5 150m) 8Gb (,5 50m)

Questions

2008 IBM Corporation

Special notices
This document was developed for IBM offerings in the United States as of the date of publication. IBM may not make these offerings available in other countries, and the information is subject to change without notice. Consult your local IBM business contact for information on the IBM offerings available in your area. Information in this document concerning non-IBM products was obtained from the suppliers of these products or other public sources. Questions on the capabilities of non-IBM products should be addressed to the suppliers of those products. IBM may have patents or pending patent applications covering subject matter in this document. The furnishing of this document does not give you any license to these patents. Send license inquires, in writing, to IBM Director of Licensing, IBM Corporation, New Castle Drive, Armonk, NY 10504-1785 USA. All statements regarding IBM future direction and intent are subject to change or withdrawal without notice, and represent goals and objectives only. The information contained in this document has not been submitted to any formal IBM test and is provided "AS IS" with no warranties or guarantees either expressed or implied. All examples cited or described in this document are presented as illustrations of the manner in which some IBM products can be used and the results that may be achieved. Actual environmental costs and performance characteristics will vary depending on individual client configurations and conditions. IBM Global Financing offerings are provided through IBM Credit Corporation in the United States and other IBM subsidiaries and divisions worldwide to qualified commercial and government clients. Rates are based on a client's credit rating, financing terms, offering type, equipment type and options, and may vary by country. Other restrictions may apply. Rates and offerings are subject to change, extension or withdrawal without notice. IBM is not responsible for printing errors in this document that result in pricing or information inaccuracies. All prices shown are IBM's United States suggested list prices and are subject to change without notice; reseller prices may vary. IBM hardware products are manufactured from new parts, or new and serviceable used parts. Regardless, our warranty terms apply. Any performance data contained in this document was determined in a controlled environment. Actual results may vary significantly and are dependent on many factors including system hardware configuration and software design and configuration. Some measurements quoted in this document may have been made on development-level systems. There is no guarantee these measurements will be the same on generallyavailable systems. Some measurements quoted in this document may have been estimated through extrapolation. Users of this document should verify the applicable data for their specific environment.

Revised September 26, 2006

2008 IBM Corporation

Special notices (cont.)

IBM, the IBM logo, ibm.com AIX, AIX (logo), AIX 6 (logo), AS/400, BladeCenter, Blue Gene, ClusterProven, DB2, ESCON, i5/OS, i5/OS (logo), IBM Business Partner (logo), IntelliStation, LoadLeveler, Lotus, Lotus Notes, Notes, Operating System/400, OS/400, PartnerLink, PartnerWorld, PowerPC, pSeries, Rational, RISC System/6000, RS/6000, THINK, Tivoli, Tivoli (logo), Tivoli Management Environment, WebSphere, xSeries, z/OS, zSeries, AIX 5L, Chiphopper, Chipkill, Cloudscape, DB2 Universal Database, DS4000, DS6000, DS8000, EnergyScale, Enterprise Workload Manager, General Purpose File System, , GPFS, HACMP, HACMP/6000, HASM, IBM Systems Director Active Energy Manager, iSeries, Micro-Partitioning, POWER, PowerExecutive, PowerVM, PowerVM (logo), PowerHA, Power Architecture, Power Everywhere, Power Family, POWER Hypervisor, Power Systems, Power Systems (logo), Power Systems Software, Power Systems Software (logo), POWER2, POWER3, POWER4, POWER4+, POWER5, POWER5+, POWER6, POWER6+, System i, System p, System p5, System Storage, System z, Tivoli Enterprise, TME 10, Workload Partitions Manager and X-Architecture are trademarks or registered trademarks of International Business Machines Corporation in the United States, other countries, or both. If these and other IBM trademarked terms are marked on their first occurrence in this information with a trademark symbol ( or ), these symbols indicate U.S. registered or common law trademarks owned by IBM at the time this information was published. Such trademarks may also be registered or common law trademarks in other countries. A current list of IBM trademarks is available on the Web at "Copyright and trademark information" at www.ibm.com/legal/copytrade.shtml The Power Architecture and Power.org wordmarks and the Power and Power.org logos and related marks are trademarks and service marks licensed by Power.org. UNIX is a registered trademark of The Open Group in the United States, other countries or both. Linux is a registered trademark of Linus Torvalds in the United States, other countries or both. Microsoft, Windows and the Windows logo are registered trademarks of Microsoft Corporation in the United States, other countries or both. Intel, Itanium, Pentium are registered trademarks and Xeon is a trademark of Intel Corporation or its subsidiaries in the United States, other countries or both. AMD Opteron is a trademark of Advanced Micro Devices, Inc. Java and all Java-based trademarks and logos are trademarks of Sun Microsystems, Inc. in the United States, other countries or both. TPC-C and TPC-H are trademarks of the Transaction Performance Processing Council (TPPC). SPECint, SPECfp, SPECjbb, SPECweb, SPECjAppServer, SPEC OMP, SPECviewperf, SPECapc, SPEChpc, SPECjvm, SPECmail, SPECimap and SPECsfs are trademarks of the Standard Performance Evaluation Corp (SPEC). NetBench is a registered trademark of Ziff Davis Media in the United States, other countries or both. AltiVec is a trademark of Freescale Semiconductor, Inc. Cell Broadband Engine is a trademark of Sony Computer Entertainment Inc. InfiniBand, InfiniBand Trade Association and the InfiniBand design marks are trademarks and/or service marks of the InfiniBand Trade Association. Other company, product and service names may be trademarks or service marks of others.

Revised April 24, 2008

2008 IBM Corporation