Saturday, September 19, 2026

IBM Power Systems

IBM Power Systems is a family of high-end servers made by IBM. Think of it as a very powerful computer — but instead of running just one operating system like your laptop does, it can run hundreds of separate computers simultaneously inside one physical box. Each of those "virtual computers" is called an LPAR (we will explain this shortly).

EVERYDAY ANALOGY

Imagine a large apartment building (the IBM Power server). Each apartment (LPAR) has its own door, its own electricity meter, its own tenants (applications). The building manager (HMC) controls who gets how many rooms. The building's wiring and plumbing (VIOS) supplies electricity and water to each apartment. Tenants never see the wiring behind the walls — they just plug things in.

DIAGRAM 1 — THE BIG PICTURE: ONE PHYSICAL SERVER, MANY VIRTUAL COMPUTERS
HMCBuilding Manager — controls everythingIBM Power Server (one physical machine)PowerVM Hypervisor — the invisible referee that keeps every LPAR isolated and fairVIOS 1Virtual I/O ServerShares NICs + HBAswith all LPARs(like the building wiring)LPAR 1Linux (RHEL)Your app runs here4 vCPU · 16 GB RAMLPAR 2Linux (SLES)Different team's app8 vCPU · 32 GB RAMLPAR 3Linux (RHEL)Database server16 vCPU · 128 GB RAMVIOS 2Backup I/O ServerIf VIOS 1 fails,this takes over(redundancy)
Key insight: All three LPARs share the same physical server hardware — the same CPUs, the same memory chips, the same network cables. But they are completely isolated from each other. LPAR 1 cannot see or touch LPAR 2's data, just like apartment 1A cannot walk into apartment 2B.

LPAR — Logical Partition

An LPAR is a virtual computer. It behaves exactly like a real physical server — it has its own CPU, RAM, storage, and network connection. It runs its own Linux operating system. From the perspective of Linux, it thinks it is a real server. It has no idea it's sharing the same physical box with 50 other LPARs.

EVERYDAY ANALOGY

An LPAR is like a virtual machine on your laptop (VirtualBox, VMware Workstation). You create a VM, give it 4 CPUs and 8 GB RAM, install Linux, and it runs as if it were a real computer. An LPAR is the same concept — just running on IBM's enterprise-grade hardware with far more performance, reliability, and scale.

LPAR SettingWhat it means in plain EnglishExample value
vCPUHow many virtual CPU cores this LPAR gets to use4 vCPU
MemoryHow much RAM this LPAR gets16 GB
Shared vs Dedicated CPUShared = borrows CPUs from a pool (like a shared office desk). Dedicated = has its own CPUs always reserved (like your own private desk).Shared capped
LPAR nameThe hostname of this virtual serverdb-prod-lpar01
Operating systemWhat Linux version runs inside itRHEL 9.4 ppc64le
vNICVirtual network card — how the LPAR connects to the networketh0
vFCVirtual Fibre Channel — how the LPAR connects to storage/dev/sda, /dev/sdb
Micro-partitioning: IBM Power lets you give an LPAR as little as 0.05 of a CPU (5% of one core). This lets you pack many small test or development LPARs onto one server very efficiently. Try doing that on a standard x86 server!

Hypervisor — The Invisible Referee

The hypervisor is a piece of software (actually firmware on IBM Power) that runs directly on the hardware — beneath everything else. Its job is to create and manage LPARs, share the physical CPU and memory fairly between them, and make sure they can never interfere with each other.

EVERYDAY ANALOGY

Imagine a sports referee at a football match. The referee does not play the game (it's not an operating system running apps). It just makes sure every player follows the rules — no cheating, no crossing into someone else's area. The hypervisor is that referee for LPARs.

DIAGRAM 2 — WHERE THE HYPERVISOR LIVES (BETWEEN HARDWARE AND LPARS)
Physical HardwareReal CPUs · Real RAM · Real PCIe slots · Real NICs · Real HBAsPowerVM Hypervisor (PHYP) — FirmwareRuns on bare metal. No OS below it. Creates and manages LPARs. Enforces isolation.LPAR 1Linux RHELYour app hereLPAR 2Linux SLESAnother team's appLPAR 3Linux RHELDatabaseGuest OS layerHypervisorHardwareNote: There is NO operating system between the hypervisor and the hardware.PowerVM (PHYP) sits directly on the bare metal — this is called a Type-1 hypervisor.VMware ESXi works the same way. Your laptop's VirtualBox is Type-2 (runs on top of Windows/macOS).
TypeRuns onExampleIBM Power equivalent
Type-1 HypervisorDirectly on bare metal hardware — no OS below itVMware ESXi, Microsoft Hyper-VPowerVM PHYP ✓
Type-2 HypervisorOn top of a host OS (Windows, macOS)VirtualBox, VMware WorkstationNot used on Power servers

HMC — Hardware Management Console

The HMC is the control panel for your IBM Power server. It is a separate computer (or virtual appliance) that connects to the Power server over the network. From the HMC you can create new LPARs, start and stop them, change how much CPU or memory they have, and move them to another server — all without touching the server physically.

EVERYDAY ANALOGY

Think of the HMC as the building management system in a large office tower. It controls the electricity to each floor (LPAR), allocates office space, and lets the building manager add a new floor or remove one — all from a central console. Tenants (applications) in each office never interact with it directly.

VMware equivalent: If you know VMware, the HMC is similar to vCenter Server — it manages the platform but does not run workloads itself. In IBM Power, management is split further: the HMC handles hardware-level control, and PowerVC (IBM's OpenStack-based tool) provides the API and self-service portal for teams to deploy their own LPARs.

VIOS — Virtual I/O Server

VIOS is a special LPAR whose only job is to own the physical network cards and storage cables on the server, and then share them with all the other LPARs. A normal Linux LPAR never talks to a physical network card directly — it always goes through the VIOS.

EVERYDAY ANALOGY

VIOS is like a shared printer room in an office building. No individual office (LPAR) has its own printer plugged directly into the wall. Instead, there is one printer room (VIOS) with all the printers. Each office sends print jobs to the printer room, which then uses the real printers. If you need a second printer room for backup, you install VIOS 2.

DIAGRAM 3 — VIOS: THE MIDDLEMAN BETWEEN LPARS AND PHYSICAL HARDWARE
LPAR 1 (RHEL)wants network + storageLPAR 2 (SLES)wants network + storageLPAR 3 (RHEL)wants network + storageVIOS — Virtual I/O ServerOwns the real NICs and HBAs. Shares them with every LPAR above.Normal LPARs NEVER touch physical hardware directly.Physical NIC (Network Card)Sends/receives real Ethernet packetsPhysical HBA (Storage Card)Sends/receives Fibre Channel to SAN
Why two VIOS? Every production IBM Power environment runs two VIOS instances. If VIOS 1 fails (crashes, needs maintenance), VIOS 2 takes over automatically and all LPARs continue running without interruption. Running only one VIOS means a single failure takes down ALL network and storage for ALL LPARs on that server. That is never acceptable in production.

veth, vNIC, and vFC — What Is the Difference?

When a Linux LPAR needs to talk to the network or to storage, it uses virtual adapters. These are not real hardware cards — they are software-defined connections that the hypervisor creates and hands to the LPAR. There are three types, and new joiners often confuse them.

DIAGRAM 4 — THREE TYPES OF VIRTUAL ADAPTER INSIDE A LINUX LPAR
Linux LPAR (RHEL or SLES — ppc64le)veth (ibmveth driver)Virtual Ethernet AdapterLinux sees it as: eth0, eth1For network traffic (IP packets)vNIC (SR-IOV mode)Virtual NIC — bypasses VIOSLinux sees it as: eth0High-performance, low-latency networkvFC (ibmvfc driver)Virtual Fibre ChannelLinux sees it as: /dev/sda, /dev/sdbFor storage only (SAN/disk)VIOS — SEA (Shared Ethernet)Bridges virtual NIC to real NIC + LACP bond(goes through VIOS — standard path)Physical NICSR-IOV logical port(bypasses VIOS entirely)VIOS — NPIV HBAMaps virtual FC to physical HBA port(always goes through VIOS)Network Switch (LAN)Your application talks to other serversNetwork SwitchHigh-perf pathFC Switch → SAN StorageYour disk lives here
VETH / IBMVETH
Virtual Ethernet Adapter

The standard virtual network card every Linux LPAR gets. When you run ip addr inside an LPAR you see eth0 — that is a veth. It connects to the PowerVM virtual switch inside the server, then travels through the VIOS Shared Ethernet Adapter (SEA) to reach the real network cable. Used by the vast majority of LPARs.

VNIC (SR-IOV)
Virtual Network Interface Card — Single Root I/O Virtualisation

A more advanced network adapter that bypasses the VIOS entirely and connects the LPAR almost directly to a physical NIC port via hardware partitioning. The result is much lower latency and higher throughput. Used for demanding workloads like OpenShift worker nodes or high-frequency trading. Most standard LPARs use veth — not vNIC SR-IOV.

VFC / IBMVFC
Virtual Fibre Channel Adapter

The virtual storage adapter. While veth carries network packets, vFC carries storage commands to the SAN (disk array). Every LPAR that needs persistent storage gets a vFC adapter. Linux sees it as a SCSI disk — /dev/sda/dev/sdb. The VIOS maps it to a physical HBA card via NPIV. Network and storage travel on completely separate paths.

AdapterWhat it carriesGoes through VIOS?Linux kernel driverWhat you see in Linux
vethNetwork (Ethernet / IP)Yes — via SEAibmvetheth0, eth1 (ip addr)
vNIC (SR-IOV)Network (Ethernet / IP)No — hardware bypassibmvnic or vendor NIC drivereth0 (higher throughput)
vFCStorage (Fibre Channel / SCSI)Yes — via NPIV HBAibmvfc/dev/sda, /dev/sdb (lsblk)
Simple rule to remember: If the LPAR needs to talk to other computers on the network — that is veth. If the LPAR needs to talk to its disk storage — that is vFC. They are completely separate channels, like your phone having separate slots for the SIM card (calls) and the memory card (storage).

SAN and WWPN — Where Your Disk Actually Lives

A Linux LPAR running on IBM Power usually does not have a local hard drive inside the server. Its storage lives in a SAN — Storage Area Network. Think of it as a huge, fast, dedicated network whose only job is to carry disk data. The LPAR connects to the SAN through its virtual FC adapter and the VIOS.

EVERYDAY ANALOGY

Your home internet connection carries web pages, emails, and video calls all mixed together on one cable. A SAN is different — it is a dedicated private road that only carries storage traffic at very high speed. Nothing else is allowed on it. The protocol it uses is called Fibre Channel (FC), and it is much faster and more reliable than regular Ethernet for disk access.

DIAGRAM 5 — SAN STORAGE PATH: FROM LPAR TO DISK
Linux LPARHas a vFC adaptervirtual WWPN pairsees /dev/sda, /dev/sdbvFCVIOSNPIV mappingvirtual → physicalHBA port (32 Gb/s)FC cableFC SwitchLike a network switchbut for storage trafficBrocade / Cisco MDSFC fabricSAN StorageIBM FlashSystemThousands of disksNVMe all-flashLUNLUNSlice of disk givento this LPARe.g. 500 GB volumeTwo separate paths (Path A via VIOS 1 + Path B via VIOS 2) — Linux dm-multipath handles both simultaneouslyIf one path fails, the other keeps I/O running automatically. The LPAR never sees an error.
SAN
Storage Area Network

A dedicated high-speed private network whose only purpose is carrying disk data between servers and storage arrays. It uses Fibre Channel cables and switches — separate from your regular Ethernet network. The LPAR's disk physically lives on a disk array connected to the SAN, not inside the server box.

LUN
Logical Unit Number

A LUN is a chunk of storage that the SAN array "exports" to a specific LPAR. It is like a virtual hard drive. The storage admin creates a LUN of say 500 GB on the FlashSystem and maps it to your LPAR's WWPN. Inside Linux you then see it as /dev/sda. You then format it and use it like any other disk.

WWPN
World Wide Port Name

A unique address for a storage port — like a MAC address is to a network card, but for Fibre Channel. Every vFC adapter an LPAR gets is assigned a unique WWPN pair (one for each path). The storage admin uses this WWPN to say: "this LUN is allowed to be accessed by WWPN 50:05:07:68:XX:XX:XX:XX" — this is called zoning.

ZONING
FC Switch Access Control

Zoning is the SAN's equivalent of a firewall rule. It tells the FC switch: "only let LPAR-1's WWPN talk to Storage-Port-A's WWPN — everyone else is blocked." Without zoning, any LPAR could try to access any storage — a serious security problem. Zoning is configured on the FC switch (Brocade or Cisco MDS) by the storage admin.

NPIV
N_Port ID Virtualisation

A clever trick that lets one physical HBA port in the VIOS pretend to be many separate ports — one per LPAR. Each LPAR gets its own virtual port with its own WWPN. The FC switch and the storage array see each LPAR as a separate device. NPIV is how 10 LPARs can share 2 physical HBA ports in the VIOS while each having its own isolated storage access.

HBA
Host Bus Adapter

The physical card plugged into the IBM Power server's PCIe slot that has the Fibre Channel connectors. It is to storage what a NIC is to networking. The VIOS owns the HBA and uses NPIV to give each LPAR a virtual port on it. A production server typically has 2–4 HBA ports, split across VIOS 1 and VIOS 2 for redundancy.

SEA — How Network Traffic Leaves the Server

When a Linux LPAR sends a network packet (say, connecting to a website or another server), it travels through its veth adapter → the PowerVM virtual switch → VIOS → SEA → physical NIC → network switch. The SEA (Shared Ethernet Adapter) is the bridge that VIOS builds between the internal virtual world and the external real network.

DIAGRAM 6 — NETWORK PATH: HOW A PACKET TRAVELS FROM LPAR TO YOUR NETWORK
Linux LPAReth0 (veth)sends IP packetStep 1PowerVMVirtual SwitchL2 switchinginside the serverVLAN-aware802.1Q tagsStep 2VIOS — SEAShared Ethernet AdapterBridges virtual switchto physical NIC802.3ad LACP BondNIC 1 + NIC 2 bondedactive/active → 50 Gb totalStep 3 — SEA bridges to real NICToR SwitchTop-of-Rack EthernetLACP port-channelfrom VIOS SEA25 GbE / 100 GbECisco / AristaStep 4Your NetworkLAN / WANOther servers, internetStep 5⚠ SEA is NOT the same as VMware vSwitchVMware vSwitch handles both internal switching AND external uplink in one object.
SEA
Shared Ethernet Adapter

A bridge created inside VIOS that connects the internal PowerVM virtual switch to the external physical NIC. It carries all VLAN tags from the real network through to the LPARs. It also bonds two or more physical NICs together (LACP) to give more bandwidth and automatic failover if one NIC cable is unplugged.

LACP
Link Aggregation Control Protocol (IEEE 802.3ad)

A standard that lets you bundle two or more physical network cables together so they behave as one. If you have two 25 Gb cables bonded with LACP you get 50 Gb total bandwidth and if one cable fails the other keeps traffic flowing — automatically, with no manual intervention. LACP negotiation happens between the VIOS SEA and the ToR switch.

POWERVM VSWITCH
Virtual Switch (intra-server only)

A software switch inside the IBM Power server that routes traffic between LPARs on the same physical box — without sending anything out of the server at all. It handles VLAN tagging so different LPARs can be on different networks. It does not connect to the outside world directly — that is the SEA's job.

VLAN
Virtual Local Area Network

A way to logically separate network traffic on the same physical cables. For example, LPAR 1 might be on VLAN 100 (production network) and LPAR 2 on VLAN 200 (test network) — but both share the same physical cables between server and switch. VLANs keep them isolated. The SEA passes all VLANs to the correct LPARs automatically.

Why SEA ≠ VMware vSwitch (important!): In VMware, the vSwitch does both jobs — internal switching between VMs andconnecting to the external physical network. In IBM Power these are two separate things: the PowerVM vSwitch does internal switching only, and the VIOS SEA does the external bridge. New joiners often confuse these — now you know the difference.

RTAS — The Firmware's Phone Line to Linux

RTAS stands for Run-Time Abstraction Services. It is a set of services built directly into the IBM Power server's firmware. When Linux needs to do something that requires hardware-level privilege — like adding a new CPU while the server is running, recovering from a failed PCIe card, or preparing for a live migration — it makes an RTAS call. Think of it as Linux picking up a special hotline to the firmware.

EVERYDAY ANALOGY

Imagine you rent an office (LPAR) in a building. You cannot change the building's electrical wiring yourself — you call the building management team (RTAS) on a special internal phone line. You say "I need a new power socket in room 4" (add a CPU). The building team does the work behind the scenes, and when they are done, the new socket just appears in your office — no need to move out (reboot).

DIAGRAM 7 — WHAT HAPPENS WHEN LINUX MAKES AN RTAS CALL
Linux Kernel(running inside LPAR)Wants to: add a CPUCalls: rtas_call("ibm,configure-connector")This is the RTAS call.Linux does NOT touchhardware registers directly.RTAS call(hypercall)PowerVM Firmware(RTAS service table)Receives Linux requestValidates it is allowedPerforms the action onreal hardwareNo OS code runs here —firmware only.Returns success/fail to Linux.result returnedWhat RTAS is used for① DLPAR — Add/remove CPU or RAM liveNo reboot needed. Linux hotplugs the resource.② EEH — Recover from a failed PCIe cardCard glitches → RTAS resets slot → driver restarts.③ LPM — Suspend for live migrationQuiesces all CPUs so LPAR can move to new server.④ Sensor data — Temperature, fan, voltageIBM monitoring reads hardware health via RTAS.⑤ Boot abstraction — same kernel everywhereSame ppc64le kernel boots LPAR, bare-metal, or KVM.
RTAS ServicePlain English meaningWhen it is triggered
ibm,configure-connectorAdd or remove a CPU/memory/adapter to a running LPARWhen HMC or PowerVC does a DLPAR operation
ibm,read-slot-reset-state2Check if a PCIe card has faulted; reset it if neededWhen a vFC or NIC adapter glitches (EEH recovery)
ibm,suspend-meAsk all CPUs to pause so the LPAR can be moved live to another serverDuring Live Partition Mobility (LPM)
get-sensor-stateRead hardware temperature, voltage, and fan speedMonitoring agents, IBM Electronic Service Agent
check-exceptionDeliver hardware error events to the OSWhen hardware detects a fault — for logging and alerting
Why RTAS matters for you as a Linux admin: When you run lscpu on a Power LPAR and see CPUs appearing or disappearing — that is RTAS at work. When your disk path disappears and comes back in 10 seconds without a reboot — that is RTAS EEH recovery. When a running LPAR silently moves to another server during maintenance — that is RTAS suspend/resume. You will not configure RTAS directly; the system uses it behind the scenes, but understanding it helps you diagnose unexpected resource changes.

LPM — Moving a Running LPAR With No Downtime

LPM stands for Live Partition Mobility. It lets a system administrator take a running Linux LPAR — with an active application, open network connections, and live disk I/O — and move it completely to a different physical Power server, without stopping it. Your application does not even notice.

EVERYDAY ANALOGY

Imagine you are on a phone call while riding on a bus. The bus reaches a stop and you need to get off and onto a different bus — but the phone call must not be interrupted. A crew of people pick you up and carry you, mid-conversation, from one bus to the other in under a second. That is LPM. The "phone call" is your running application. The buses are the two Power servers.

DIAGRAM 8 — LIVE PARTITION MOBILITY: LPAR MOVES BETWEEN SERVERS WITH ZERO DOWNTIME
Server A (Source)LPAR — Linux RHELApp running, users connectedCPU state + RAM contentswill be moved to Server BStep 1: HMC copies RAM pages to Server BStep 2: Brief pause (<500ms), final copy sentLPMHMC managedServer B (Destination)LPAR — Linux RHELResumed! Same IP, same appUsers see no interruptionvFC re-mapped, SEA continuesStep 3: LPAR resumes onServer B. Same hostname,same IP, same storage.Application never crashed.Shared SAN Storage — accessible from BOTH servers simultaneously
One key requirement for LPM: Both servers must be able to reach the same SAN storage. The LPAR's disk does not move — it stays on the SAN. Only the CPU state and RAM contents are transferred. This is why production LPARs are always on SAN storage, never on local disks inside the server.

IBM Power Server Models — Scale-Out vs Scale-Up

IBM sells Power servers in two broad categories. Scale-out servers (S-series) are like a fleet of delivery vans — many medium-sized units, great for consolidating lots of workloads. Scale-up servers (E-series) are like a single enormous articulated lorry — one giant machine with massive memory for mission-critical databases.

DIAGRAM 9 — IBM POWER SERVER PORTFOLIO (SCALE-OUT VS SCALE-UP)
Scale-Out Servers (S-Series)Many workloads · Good density · Moderate memoryS10128 cores512 GB RAM1U · Edge/remote40 LPARs maxS101424 cores1 TB RAM4U rack120 LPARs maxS102240 cores4 TB RAM2U 2-node200 LPARs maxS102448 cores8 TB RAM4U rack240 LPARs maxScale-Up Servers (E-Series)Mission-critical · Massive memory · Huge databasesE105060 active cores16 TB RAM4U rack · 500 LPARsLarge DB · ERP · AnalyticsE1080240 active cores64 TB RAM8U · 1,000 LPARsSAP HANA · FlagshipIBM Power server generations keep advancing (Power10, Power11, and beyond).Model numbers and naming evolve — always check ibm.com/power for the latest portfolio.
Capacity on Demand (CoD): IBM Power servers ship with extra cores and memory already installed but switched off. You can turn them on at any time — even temporarily for a weekend peak — by activating a CoD licence. No hardware engineer needs to visit the data centre. This is unique to IBM Power and not possible on standard x86 servers.

Glossary — Every Term on One Page

A cheat-sheet for everything covered in this guide. Bookmark this page.

TermFull nameOne-line plain English definition
LPARLogical PartitionA virtual computer running inside a physical IBM Power server. Has its own CPU, RAM, network, and storage.
HMCHardware Management ConsoleThe remote control panel for managing LPARs, starting/stopping them, and allocating resources on the Power server.
PowerVMPower Virtual Machine (Hypervisor)IBM's hypervisor firmware that creates and isolates LPARs on the bare metal — like a referee between hardware and virtual computers.
PHYPPower HypervisorThe technical name for the PowerVM firmware layer. Type-1 — runs directly on hardware with no OS beneath it.
VIOSVirtual I/O ServerA special service LPAR that owns the real NIC and HBA cards and shares them with all other LPARs on the server.
veth / ibmvethVirtual Ethernet AdapterThe virtual network card an LPAR uses for IP/Ethernet traffic. Seen in Linux as eth0. Travels through VIOS SEA.
vNIC (SR-IOV)Virtual Network Interface CardA high-performance virtual network card that bypasses VIOS and connects almost directly to a physical NIC port.
vFC / ibmvfcVirtual Fibre Channel AdapterThe virtual storage adapter an LPAR uses to access SAN disk. Seen in Linux as /dev/sda. Goes through VIOS NPIV.
SEAShared Ethernet AdapterA bridge created inside VIOS that connects the internal PowerVM vSwitch to the external physical NIC, with LACP bonding.
LACPLink Aggregation Control ProtocolBonds two or more physical NIC cables together for more speed and automatic failover if a cable is unplugged.
SANStorage Area NetworkA dedicated high-speed private network used only for disk storage traffic between servers and storage arrays (Fibre Channel).
LUNLogical Unit NumberA chunk of storage (like a virtual hard drive) carved out of the SAN array and given to a specific LPAR.
HBAHost Bus AdapterThe physical PCIe card in the server with Fibre Channel connectors. VIOS owns it and shares it via NPIV.
WWPNWorld Wide Port NameA unique address for a Fibre Channel port — like a MAC address but for storage. Used for zoning on the FC switch.
NPIVN_Port ID VirtualisationLets one physical HBA port pretend to be many — giving each LPAR its own virtual FC port and WWPN.
ZoningFC Switch Access ControlA firewall rule on the FC switch that allows only specific LPARs (by WWPN) to talk to specific storage ports.
dm-multipathDevice Mapper MultipathLinux software that manages two or more separate paths to the same disk — if one fails, the other takes over silently.
LVM2Logical Volume Manager 2Linux disk management software that turns raw LUNs into flexible, resizable disk partitions (PV → VG → LV → filesystem).
DLPARDynamic Logical PartitioningAdding or removing CPU, RAM, or adapters from a running LPAR without rebooting it. Uses RTAS under the hood.
RTASRun-Time Abstraction ServicesA set of firmware services Linux calls to request hardware changes (DLPAR, EEH recovery, LPM suspend) without direct hardware access.
EEHEnhanced Error HandlingRTAS-powered ability to recover from a failed PCIe card (NIC or HBA) without rebooting the LPAR or server.
LPMLive Partition MobilityMoving a running LPAR from one Power server to another with no downtime. Requires shared SAN storage.
PowerVCPower Virtualisation CentreIBM's OpenStack-based self-service portal and API for deploying and managing LPARs — like a private cloud for Power servers.
ppc64lePower PC 64-bit Little EndianThe CPU architecture of IBM Power servers. When you download RHEL or SLES for Power, you choose the ppc64le build.
CoDCapacity on DemandPre-installed but locked CPU/memory that can be activated instantly by buying a licence — no engineer visit needed.
SMTSimultaneous MultithreadingEach physical CPU core on Power can run 8 threads simultaneously (SMT8). One core = 8 "virtual CPUs" visible to Linux.

Putting It All Together — A Day in the Life of a Linux LPAR

Let us trace what happens from the moment your team's Linux LPAR is created to a user making a database query — using every term from this guide.

  • 1
    Admin opens the HMCThe admin logs into the Hardware Management Console and creates a new LPAR. They name it db-prod-01, give it 8 vCPU and 64 GB RAM from the shared processor pool, and assign two vFC adapters (one per VIOS) and two veth adapters for network.
  • 2
    PowerVM PHYP creates the partitionThe hypervisor firmware carves out the requested CPU entitlement and memory from the physical server's resources and registers a new isolated partition. The LPAR does not exist to any other LPAR — they cannot see it.
  • 3
    VIOS maps the vFC adapters via NPIVEach vFC adapter gets a unique WWPN pair. VIOS 1 maps the first vFC to a virtual port on its physical HBA (NPIV). VIOS 2 maps the second vFC to its own separate HBA. The storage admin zones both WWPNs to the LUN on the FlashSystem.
  • 4
    RHEL boots via RTAS device treeThe LPAR boots from network (PXE) or a captured image. The Linux kernel reads the RTAS device tree and discovers: 8 vCPUs, 64 GB RAM, 2 × vFC adapters (ibmvfc driver), 2 × veth adapters (ibmveth driver). It initialises them all automatically.
  • 5
    dm-multipath discovers two paths to the LUNLinux sees /dev/sda (path via VIOS 1 HBA) and /dev/sdb (path via VIOS 2 HBA) — both pointing to the same SAN LUN. dm-multipath combines them into /dev/mapper/mpatha and uses both paths simultaneously (round-robin I/O).
  • 6
    LVM2 formats the storage and mounts the filesystemThe admin runs pvcreate /dev/mapper/mpathavgcreate vg_db /dev/mapper/mpathalvcreate -L 400G -n lv_data vg_db, then formats it as XFS and mounts it at /oracle. The database is installed there.
  • 7
    Network goes live through SEAThe veth adapter eth0 is configured with an IP address on VLAN 100. Traffic flows: LPAR eth0 → PowerVM vSwitch → VIOS SEA (802.3ad LACP bond across two 25 GbE NICs) → ToR switch → enterprise network. The LPAR gets a hostname in DNS and is reachable.
  • 8
    Six months later — live migration with zero downtimeThe physical server needs a firmware update. The admin triggers LPM from the HMC. The running LPAR is moved to a spare Power server in 90 seconds. The database query that was running during the migration completes normally. Users notice nothing. Afterwards, the firmware is updated and the LPAR migrated back.
You now understand IBM Power. Every term — LPAR, HMC, VIOS, SEA, veth, vNIC, vFC, SAN, LUN, WWPN, NPIV, Zoning, RTAS, DLPAR, EEH, LPM, dm-multipath, LVM2 — has been covered. The architecture is logical once you see how the layers connect: the hypervisor creates the LPARs, the VIOS shares the physical hardware, and RTAS is the firmware API that makes live changes possible without ever stopping your workloads.

No comments:

Post a Comment