010 VIO Overview

Copyright IBM Corporation 2006 Course materials may not be reproduced in whole or in part without written permission.
3.3
Virtual I/O Server Overview
QPS01 IBM System p APV - 010
Copyright IBM Corporation 2006
IBM System p
QPS01 010 VIO Overview
2
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.
Many of the pSeries features described in this document are operating system dependent and may not be available on Linux. For more information, please
check: http://www.ibm.com/servers/eserver/pseries/linux/whitepapers/linux_pseries.html
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 generally-available 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.
Special Notices
Revised February 6, 2004
IBM System p
3
Special Notices (Cont.)
The following terms are registered trademarks of International Business Machines Corporation in the United States and/or other countries: AIX, AIX/L,
AIX/L(logo), alphaWorks, AS/400, Blue Gene, Blue Lightning, C Set++, CICS, CICS/6000, CT/2, DataHub, DataJoiner, DB2, DEEP BLUE, developerWorks,
DFDSM, DirectTalk, DYNIX, DYNIX/ptx, e business(logo), e(logo)business, e(logo)server, Enterprise Storage Server, ESCON, FlashCopy, GDDM, IBM,
IBM(logo), ibm.com, IBM TotalStorage Proven, IntelliStation, IQ-Link, LANStreamer, LoadLeveler, Lotus, Lotus Notes, Lotusphere, Magstar, MediaStreamer,
Micro Channel, MQSeries, Net.Data, Netfinity, NetView, Network Station, Notes, NUMA-Q, Operating System/2, Operating System/400, OS/2, OS/390, OS/400,
Parallel Sysplex, PartnerLink, PartnerWorld, POWERparallel, PowerPC, PowerPC(logo), Predictive Failure Analysis, pSeries, PTX, ptx/ADMIN, RISC
System/6000, RS/6000, S/390, Scalable POWERparallel Systems, SecureWay, Sequent, ServerProven, SP1, SP2, SpaceBall, System/390, The Engines of e-business,
THINK, ThinkPad, Tivoli, Tivoli(logo), Tivoli Management Environment, Tivoli Ready(logo), TME, TotalStorage, TURBOWAYS, VisualAge, WebSphere,
xSeries, z/OS, zSeries.
The following terms are trademarks of International Business Machines Corporation in the United States and/or other countries: Advanced Micro-Partitioning,
AIX/L(logo), AIX 5L, AIX PVMe, AS/400e, BladeCenter, Chipkill, Cloudscape, DB2 OLAP Server, DB2 Universal Database, DFDSM, DFSORT, Domino,
e-business(logo), e-business on demand, eServer, GigaProcessor, HACMP, HACMP/6000, Hypervisor, i5/OS, IBMLink, IBM Virtualization Engine, IMS,
Intelligent Miner, Micro-Partitioning, iSeries, NUMACenter, OpenPower, POWER, Power Architecture, Power Everywhere, PowerPC Architecture, PowerPC 603,
PowerPC 603e, PowerPC 604, PowerPC 750, POWER2, POWER2 Architecture, POWER3, POWER4, POWER4+, POWER5, POWER5+, POWER6, Redbooks,
Sequent (logo), SequentLINK, Server Advantage, ServeRAID, Service Director, SmoothStart, SP, S/390 Parallel Enterprise Server, ThinkVision, Tivoli Enterprise,
TME 10, TotalStorage Proven, Ultramedia, VideoCharger, Visualization Data Explorer, X-Architecture, z/Architecture.
A full list of U.S. trademarks owned by IBM may be found at: http://www.ibm.com/legal/copytrade.shtml.
UNIX is a registered trademark 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, Windows NT and the Windows logo are registered trademarks of Microsoft Corporation in the United States and/or other countries.
Intel, Itanium and Pentium are registered trademarks and Intel Xeon and MMX are trademarks of Intel Corporation in the United States and/or other countries
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 and/or other countries.
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.
Other company, product and service names may be trademarks or service marks of others.
Revised August 23, 2004
IBM System p
4
The IBM benchmarks results shown herein were derived using particular, well configured, development-level and generally-available computer systems. Buyers
should consult other sources of information to evaluate the performance of systems they are considering buying and should consider conducting application
oriented testing. For additional information about the benchmarks, values and systems tested, contact your local IBM office or IBM authorized reseller or access
the website of the benchmark consortium or benchmark vendor.
IBM benchmark results can be found in the IBM eServer p5, pSeries and IBM RS/6000 Performance Report at
http://www-1.ibm.com/servers/eserver/pseries/hardware/system_perf.html
Unless otherwise indicated for a system, the performance benchmarks were conducted using AIX V4.3 or AIX 5L. IBM C Set++ for AIX and IBM XL
FORTRAN for AIX with optimization were the compilers used in the benchmark tests. The preprocessors used in some benchmark tests include KAP 3.2 for
FORTRAN and KAP/C 1.4.2 from Kuck & Associates and VAST-2 v4.01X8 from Pacific-Sierra Research. The preprocessors were purchased separately from
these vendors. Other software packages like IBM ESSL for AIX and MASS for AIX were also used in some benchmarks.
For a definition and explanation of each benchmark and the full list of detailed results, visit the web site of the benchmark consortium or benchmark vendor.
TPC http://www.tpc.org
SPEC http://www.spec.org
Linpack http://www.netlib.org/benchmark/performance.pdf
Pro/E http://www.proe.com
GPC http://www.spec.org/gpc
NotesBench http://www.notesbench.org
VolanoMark http://www.volano.com
STREAM http://www.cs.virginia.edu/stream/
SAP http://www.sap.com/benchmark/
Oracle Applications http://www.oracle.com/apps_benchmark/
PeopleSoft - To get information on PeopleSoft benchmarks, contact PeopleSoft directly
Siebel http://www.siebel.com/crm/performance_benchmark/index.shtm
Baan http://www.ssaglobal.com
Microsoft Exchange http://www.microsoft.com/exchange/evaluation/performance/default.asp
Veritest http://www.veritest.com/clients/reports
Fluent http://www.fluent.com/software/fluent/fl5bench/fullres.htm
TOP500 Supercomputers http://www.top500.org/
Ideas International http://www.microsoft.com/exchange/evaluation/performance/default.asp
Storage Performance Council http://www.storageperformance.org/results
Notes on Benchmarks and Values
Revised August 26, 2003
IBM System p
5
rPerf
rPerf (Relative Performance) is an estimate of commercial processing performance relative to other pSeries systems. It is derived from an IBM
analytical model which uses characteristics from IBM internal workloads, TPC and SPEC benchmarks. The rPerf model is not intended to represent any
specific public benchmark results and should not be reasonably used in that way. The model simulates some of the system operations such as CPU,
cache and memory. However, the model does not simulate disk or network I/O operations.
rPerf estimates are calculated based on systems with the latest levels of AIX 5L and other pertinent software at the time of system announcement.
Actual performance will vary based on application and configuration specifics. The IBM pSeries 640 is the baseline reference system and has
a value of 1.0. Although rPerf may be used to approximate relative IBM UNIX commercial processing performance, actual system performance may
vary and is dependent upon many factors including system hardware configuration and software design and configuration.
All performance estimates are provided "AS IS" and no warranties or guarantees are expressed or implied by IBM. Buyers should consult other sources
of information, including system benchmarks, and application sizing guides to evaluate the performance of a system they are considering buying. For
additional information about rPerf, contact your local IBM office or IBM authorized reseller.
Notes on Performance Estimates
Revised June 28, 2004
IBM System p
6
What is Advanced POWER Virtualization (APV)
APV the hardware feature code for POWER5 servers that enables:
Micro-partitioning fractional CPU entitlements from a shared pool of
processors, beginning at one-tenth of a CPU
Partition Load Manager (PLM) a policy-based, dynamic CPU and memory
reallocation tool
VIO Server (virtual SCSI and Shared Ethernet Adapter)
Physical disks can be shared as virtual disks to client partitions
Shared Ethernet Adapter (SEA) A physical adapter or EtherChannel in
a VIO Server can be shared by client partitions. Clients use virtual
Ethernet adapters
Virtual Ethernet a LPAR-to-LPAR Virtual LAN within a POWER5 Server
Does not require the APV feature code
IBM System p
7
Why Virtual I/O Server?
POWER5 systems will support more partitions than physical I/O slots available
Each partition still requires a boot disk and network connection, but now
they can be virtual instead of physical
VIO Server allows partitions to share disk and network adapter resources
The Fibre Channel or SCSI controllers in the VIO Server can be accessed
using Virtual SCSI controllers in the clients
A Shared Ethernet Adapter in the VIO Server can be a layer 2 bridge for
virtual Ethernet adapters in the clients
The VIO Server further enables on demand computing and server consolidation
IBM System p
8
Why Virtual I/O Server?
Virtualizing IO saves:
Gbit Ethernet Adapters
2 Gbit Fibre Channel Adapters
PCI slots
Eventually, IO drawers
Server frames?
Floor space?
Electric, HVAC?
Ethernet switch ports
Fibre channel switch ports
Logistics, scheduling, delays of physical Ethernet, SAN attach
Some servers run 90% utilization all the time everyone knows which ones.
However,
Average utilization in the UNIX server farm is closer to 25%. They dont all
maximize their use of dedicated IO devices
VIO is departure from new project, new chassis mindset
IBM System p
9
Virtual I/O Server Characteristics
Requires AIX 5.3 and POWER5 hardware with APV feature
Installed as a special purpose, AIX-based logical partition
Uses a subset of the AIX Logical Volume Manager and attaches to
traditional storage subsystems
Inter-partition communication (client-server model) provided via the POWER
Hypervisor
Clients see virtual disks as traditional AIX SCSI hdisks, although they may be
a physical disk or logical volume on the VIO Server
One physical disk on a VIO server can provide logical volumes for several
client partitions
IBM System p
10
Creating the Virtual IO Server
IBM System p
11
Virtual I/O Server installation
VIO Server code is packaged and shipped as an AIX mksysb image on a VIO CD
Installation methods
CD install
HMC install - Open rshterm and type installios; follow the prompts
The Network Installation Manager (NIM)
VIO Server can support multiple client types
AIX 5.3
SUSE Linux Enterprise Server 9 for POWER
Red Hat Enterprise Linux AS for POWER Version 3 and 4
IBM System p
12
Virtual I/O Server Administration
The VIO server uses a command line interface running in a restricted shell no
smitty or GUI
There is no root login on the VIO Server
A special user padmin executes VIO server commands
First login after install, user padmin is prompted to change password
After that, padmin runs the command license accept
Slightly modified commands are used for managing devices, networks, code
installation and maintenance, etc.
The padmin user can start a root AIX shell for setting up third-party devices
using the command oem_setup_env
IBM System p
13
VIO Server/Client Overview
IBM System p
14
VIO Server Configuration with MPIO
MPIO in client LPAR
automatically configures
Client sees one hdisk with two
MPIO paths lspath l hdisk0
Paths are fail_over only. No
load balancing in client MPIO
hdisk1 in each VIO server
attached to vscsi server
adapter as a raw disk
Set reserve_policy attribute
on hdisk1 to no_reserve in
each VIO server. Also, with two fcs in
a VIO server, change algorithm to
round_robin for hdisk1. SDDPCM
driver installed in each VIO server
LUN appears in each VIO
server as hdisk1
Single RAID5 LUN carved in ESS,
zoned to 4 FC adapters in the two VIO
servers
SDDPCM
SDDPCM
IBM System p
15
Checking for MPIO Capability
Run oem_setup_env to get to a root prompt
Run # odmget qattribute=unique_id CuAt
In the output, look for a field unique_id followed by a value field
lsattr rl hdisk0 a algorithm (both round_robin or fail_over)
With VIOS 1.3, MPIO is available with:
- IBM Enterprise Storage Server and DS6000 with SDDPCM (but not
SDD)
- FAStT and DS4000 with RDAC
- IBM System Storage N3700 and N5200
- EMC PowerPath
- HDS with HDLM
IBM System p
16
VIO Server Configuration with LVM Mirroring
IBM System p
17
Internals AIX
Virtual I/O Server
AIX client
LVM
OEM
multipathing
disk DD
HBA DD
VSCSI
client
disk
DD
LVM
MPIO
PCM
MPIO
PCM
VSCSI
server
internal or
external storage
logical volumes
OEM device paths
physical volumes
IBM System p
18
Virtual I/O Server Resource Configuration
Add physical devices to the VIO Server
If serving LVs as hdisks, create a volume group on one or more disks with
mkvg
- mkvg [-f] [-vg VolumeGroup] PhysicalVolume
- mkvg f vg rootvg_clients hdisk2
rootvg_clients
Create logical volumes on the volume group
- mklv [-lv NewLogicalVolume | -prefix Prefix ]
VolumeGroup Size [PhysicalVolume ]
- mklv lv aix_sq07 rootvg_clients 7G hdisk2
19
IBM Systems Group
POWER5 VIO Server 2006 IBM Corporation
DLPAR add of VIO Server Virtual Adapter
List virtual adapter after added by DLPAR
lsdev virtual
name status description
ent2 Available Virtual I/O Ethernet Adapter (l-lan)
vhost0 Available Virtual SCSI Server Adapter
vsa0 Available LPAR Virtual Serial Adapter
Doesnt show up in VIO Server until after running cfgdev
cfgdev dev vio0
List virtual adapter after running cfgdev
lsdev virtual
IBM System p
20
Virtual IO Server Resource Mapping
Configuring virtual target device
mkvdev vdev aix_sq07 vadapter vhost0 dev vt_aix_sq07
mkvdev vdev hdisk7 vadapter vhost1 dev vt_hdisk7
$ lsdev -virtual
vt_aix_sq07 Available Virtual Target Device - Logical Volume
vt_hdisk7 Available Virtual Target Device - Disk
IBM System p
21
Confirm what backs up each vhost
List all vscsi server adapters with all flag
$ lsmap -all
SVSA Physloc Client Partition ID
--------------- ---------------------------------- ------------------
vhost0 U9111.520.10C1C1C-V3-C2 0x00000001
VTD vtscsi0
LUN 0x8100000000000000
Backing device aix_sq07
Physloc
SVSA Physloc Client Partition ID
--------------- ---------------------------------- ------------------
vhost1 U9111.520.10C1C1C-V3-C4 0x00000001
VTD vtscsi1
LUN 0x8100000000000000
Backing device hdisk7
Physloc U787A.001.DNZ00ZE-P1-C1-T1-L4-L0
List a single vscsi server adapter with vadapter flag
$ lsmap vadapter vhost0
slot #
Logical Volume
hdisk
IBM System p
22
More Use of lsmap
$for v in `ioscli lsdev -virtual | grep vhost | awk '{print
$1}'`
do
ioscli lsmap -vadapter $v -fmt : | awk -F: '{ print $1" "$2"
"$4" "$6 $8 $10}'
done
vhost0 U9117.570.10C0EDC-V16-C7 virt_aix_sq07 aix_sq07
vhost1 U9117.570.10C0EDC-V16-C8 virt_suse_sq07 suse_sq07
vhost8 U9117.570.10C0EDC-V16-C15 virt_rhel_sq07 rhel_sq07
IBM System p
23
Client Virtual Disk Attributes
# lsdev -Cc disk
hdisk0 Available Virtual SCSI Disk Drive
# lscfg -vl hdisk0
hdisk0 U9117.570.10C0EDC-V7-C5-T1-L810000000000
Virtual SCSI Disk Drive
# lsattr -El hdisk0
PCM PCM/friend/vscsi
Path Control Module False
algorithm fail_over
Algorithm False
max_transfer 0x20000
Maximum TRANSFER Size True
pvid 00cc0edc916c5bd80000000000000000
Physical volume identifier False
queue_depth 3
Queue DEPTH False
reserve_policy no_reserve
Reserve Policy False
# lscfg -vl vscsi1
vscsi1 U9117.570.10C0EDC-V7-C6-T1 Virtual SCSI Client
Adapter
Device Specific.(YL)........U9117.570.10C0EDC-V7-C6-T1
IBM System p
24
Virtual Ethernet
Virtual Ethernet
Enable inter-lpar communications without a physical adapter
IEEE-compliant Ethernet programming model
Implemented through inter-partition, in-memory communication
VLAN splits up groups of network users on a physical network onto
segments of logical networks
Virtual switch provides support for multiple (up to 4K) VLANs
Each partition can connect to multiple networks, through one or more
adapters
VIO server can add VLAN ID tag to the Ethernet frame as appropriate.
Ethernet switch restricts frames to ports that are authorized to receive frames
with specific VLAN ID
Virtual network can connect to physical network through routing"
partitions generally not recommended
IBM System p
25
SEA Configuration
$ lsdev | grep ent[0-9]
ent1 Available 10/100 Mbps Ethernet PCI Adapter II (1410ff01)
$ mkvdev sea ent1 vadapter ent0 default ent0 defaultid 1
ent2 Available
$ lsdev | grep ent[0-9]
ent1 Available 10/100 Mbps Ethernet PCI Adapter II (1410ff01)
ent2 Available Shared Ethernet Adapter
$ lsdev dev ent2 -attr
pvid 1 PVID to use for the SEA device
pvid_adapter ent0 Default virtual adapter to use for non-VLAN-tagged packets
real_adapter ent1 Physical adapter associated with the SEA
thread 0 Thread mode enabled (1) or disabled (0)
virt_adapters ent0 List of virtual adapters associated with the SEA
IBM System p
26
Shared Ethernet Adapter setup
VIO Server after mksysb Install
Physical
Ethernet
Virtual
Ethernet
VIO Server after sea config
mkvdev sea ent1 vadapter ent0 default ent0 defaultid 1
ent2 Available
VIO servers IP address may be
put on shared adapter interface,
or on separate, non-external
access virtual adapter. VIO IP
address is NOT configured on
physical, nor on SEA virtual adapter.
ent1 ent0
9.19.126.98
Shared Ethernet ent2
ent0 ent1
IBM System p
27
SEA with NIB in VIO client Partitions
At Power5 GA, only way to provide network redundancy
VIO servers each share adapter, each on different internal network (Port
VLAN ID)
Client builds NIB EtherChannel across the Port VLAN IDs
no support for VLAN tagging both VIOs, all clients same IP subnet
IBM System p
28
What is SEA Failover? (AIX 5.3 ML3, VIO 1.2.0.0)
Shared Ethernet Adapter Redundancy
- SEA adapters in two VIO servers can back each other up.
- Two VIO servers now allowed to put external access
virtual adapters on same internal PVID, with different
trunk priorities
- Administrator dictates which SEA will be the primary based
on an assigned Trunk Priority
- A standby mode is available to force the SEA failover to
backup server, allowing for regular updates or maintenance
- The backup server that became primary will switch to being
a backup when primary resumes operation
IBM System p
29
What is SEA Failover (AIX 5.3 ML3, VIO 1.2.0.0)
Current limitation is one backup SEA per primary SEA at
this time
The backup SEA is idle until a failure occurs on the
primary SEA
- This is transparent to client LPARs
Failure may be due to:
- Physical adapter failure
- VIOS crash/reboot
- Failure to reach a pre-defined remote address
IBM System p
30
SEA Failover
Inside P5, we now allowed more than one trunk adapter with the same
VLAN ID; These adapters get different Trunk Priority between 1-15
- A lower priority is the more favored SEA; primary
- If there is more than one virtual Ethernet on the same SEA,
each must have the same priority
The SEA failover protocol helps determine which one should behave as
primary, and when a failover should occur
IBM System p
31
IBM System p
32
Shared Ethernet Adapter Failover
CLI command to configure SEA failover with a remote
mkvdev sea ent0 vadapter ent1 default ent1 defaultid 10 \
attr ha_mode=auto ctl_chan=ent2
33
IBM Systems Group
POWER5 VIO Server Overview - QPS01 010
2006 IBM Corporation
Recap of these adapters:
ent0 physical adapter to be shared it could be an EtherChannel over several physicals
ent1 VIO Server 1 virtual, PVID 10, Access External Checkbox, Trunk Priority low
ent1 VIO Server 2 virtual, PVID 10, Access External Checkbox, Trunk Priority high
ent2 virtual, PVID 10, no Access External Checkbox, no Trunk Priority, VIO server IP addr
ent3 virtual, PVID 99, Control Channel
ent4 Shared adapter, created over ent0 and ent1
e
n
t
3
e
n
t
1
e
n
t
4
e
n
t
2

v
i
o
i
p
a
d
d
r
e
n
t
4
e
n
t
0
e
n
t
0
e
n
t
1
e
n
t
2

v
i
o
i
p
a
d
d
r
e
n
t
3
Enterprise network
Power5 internal PVID 10
VIO
Server1
VIO
Server2
Client LPAR
e
n
t
0
Lower trunk
priority
Higher trunk
priority
34
IBM Systems Group
VIO command line to configure SEA failover in each VIO LPAR
mkvdev sea ent0 vadapter ent1 default ent1 defaultid 10 attr
ha_mode=auto ctl_chan=ent3
Some examples show setting ha_mode and ctl_chan with a separate chdev
command. Dont.
e
n
t
3
e
n
t
1
e
n
t
4
e
n
t
2

v
i
o
i
p
a
d
d
r
e
n
t
4
e
n
t
0
e
n
t
0
e
n
t
1
e
n
t
2

v
i
o
i
p
a
d
d
r
e
n
t
3
Enterprise network
VIO
Server1
VIO
Server2
Client LPAR
e
n
t
0
Lower trunk
priority-favored
Higher trunk
priority
35
IBM Systems Group
You may put VIO IP addr on en4 (supported). We find stability putting it on another
virtual adapter en2. ent2 adapter is a virtual adapter on Port VLAN id 10, without
Access External Network checkbox
Remove and reconfig of SEA can be done without taking down VIO server ip, default router, etc
NIM restore of either VIO thru SEA on the other VIO is more seamless for example,
nim install VIO Server1 into its ent2 adapter, with RECOVER_DEVICES=yes, thru SEA of
VIO Server2
e
n
t
3
e
n
t
1
e
n
t
4
e
n
t
2

v
i
o
i
p
a
d
d
r
e
n
t
4
e
n
t
0
e
n
t
0
e
n
t
1
e
n
t
2

v
i
o
i
p
a
d
d
r
e
n
t
3
Enterprise network
VIO
Server1
VIO
Server2
Client LPAR
e
n
t
0
Lower trunk
priority
Higher trunk
priority
IBM System p
36
SEA Failover Pros and Cons
Unexpected outages such as systems crashes are uncommon but may occur
- A backup server detecting that the primary server is down will make itself the primary and
will begin bridging traffic.
No EtherChannel requirement at VIO Client partition
- Single virtual adapter in client partition, nim install thru it, keep the configured IP
interface after nim install and boot
- Client does not need rmtcpip ; EtherChannel config ; mktcpip after nim install
Allows use of Enterprise Network VLANs inside Power5 Server
SEA failover can support planned VIO maintenance
- Scheduled maintenance can now be performed with no loss of user connections
- Traffic is transparently sent over another SEA
padmin chdev dev <sea> -attr ha_mode=standby
Cons?
- More adapters in VIO server a bit more complex to configure
- All client partitions drive IO thru the more favored VIO SEA, until failed over to less
favored VIO no balancing of client LPARs between VIO servers. Perhaps EtherChannel
of physical adapters in VIO is important here.
37
IBM Systems Group
SEA Failover vs Network Interface Backup
Manual intervention required to force
affected (1/2) client partitions back to
primary VIO Server
Automatic fail-back to primary
VIO Server when network link
becomes available
Failback to Primary
Not Supported Supported 802.1Q VLAN Tagging
No idle connections as client partitions
can be split between the two VIO
Servers
Requires a backup idle
connection on opposite VIO
Server
Physical network connections
(historically limited to 1500)
> 1500 requires AIX V5.3 TL4*
>= 1500 MTU Size
Configuration required on all of the
client partitions
Configuration required only on the
VIO Servers
Configuration
VIO Server V1.1 VIO Server V1.2
GA6 Firmware/HMC
Software Pre-requisites
Network Interface Backup SEA Failover
Note: IY79375 (AIX V5.3 TL4) provides Jumbo Frame Support for EtherChannel with virtual adapters
38
IBM Systems Group
Integrated Virtualization Manager (IVM) provides
HMC functionality in a partitionat a much lower price point
AIX 5L
V5.3
Linux
SLES 9
Linux
RHEL 4
Virtual LAN
VIOS
IVM
Provides LPAR/virtualization support
without a physical HMC no HMC
hardware translates to lower entry point
Web-based, intuitive/user-friendly interface
Shipped with the Virtual I/O Server (VIOS)
provides tight integration of LPAR
management and virtual storage
configuration
Supports creating/management of I/O and
LPARs within a single physical server
All I/O is virtualized Virtual Console,
Storage, Ethernet, and Optical
Subset of HMC Service functionality
To be available for entry servers up to
p5-550Q (both System p5 and p5
families)
HMC within a partition
POWER Hypervisor
Integrated Virtualization Manager
Integrated Virtualization Mgr
IBM System p
39
Reference
InfoCenter
http://publib.boulder.ibm.com/infocenter/eserver/v1r2s/en_US/index.htm
Virtualizing your compute environment
http://publib.boulder.ibm.com/infocenter/eserver/v1r2s/en_US/info/iphb1/iphb2.pdf
VIO Server and PLM command line reference
http://publib.boulder.ibm.com/infocenter/eserver/v1r2s/en_US/info/iphb1/commands/commands.pdf
Redbook
Advanced POWER Virtualization on IBM System p5
http://www.redbooks.ibm.com search on SG24-7940
http://www.redbooks.ibm.com/redpieces/pdfs/sg247940.pdf
VIO Server Page from Fix Central Overview, Download, Documentation
http://www14.software.ibm.com/webapp/set2/sas/f/vios/home.html
IBM System p
40
More references
http://techsupport.services.ibm.com/server/vios/documentation/configuring_mpio_for_the_vir
tual_client.pdf
http://www14.software.ibm.com/webapp/set2/sas/f/vios/documentation/faq.html
http://www14.software.ibm.com/webapp/set2/sas/f/vios/home.html
http://www-128.ibm.com/developerworks/eserver/library/es-pwr5-virtualvlan/?ca=dnp-439
http://www14.software.ibm.com/webapp/set2/sas/f/vios/documentation/home.html

010 VIO Overview

Enviado por

Dados do documento

Descrição original:

Direitos autorais

Formatos disponíveis

Compartilhar este documento

Compartilhar ou incorporar documento

Opções de compartilhamento

Você considera este documento útil?

Este conteúdo é inapropriado?

Direitos autorais:

Formatos disponíveis

010 VIO Overview

Enviado por

Direitos autorais:

Formatos disponíveis

Copyright IBM Corporation 2006 Course materials may not be reproduced in whole or in part without written permission.

Você também pode gostar