DS8000 Terms and Concepts
Published 18 May 2005
Authors: Alluis Olivier
The DS8000 introduces new architecture design and virtualization concepts. This technote is a glossary of the specific terms used to describe the hardware and the virtualization hierarchy in the DS8000.
A storage complex is a group of DS8000s managed by a single S-HMC (Storage Hardware Management Console). It may consist of a single DS8000 storage unit. A storage complex is sometimes referred to as a storage-plex.
Storage facility refers to a single DS8000 unit (including the base frame and the optional expansion frames). A storage facility is also referred to as a storage unit. As an example, if your organization has one DS8000, then you have a single storage complex that contains a single storage unit.
Processor complex refers to one of the Power5 servers which runs, controls, and delivers all the services of the DS8000. There are two processor complexes in one storage facility: processor complex 0 and processor complex 1. Each processor complex can support one or more LPARs concurrently.
Logical partition (LPAR)
An LPAR uses software and firmware to logically partition the resources on a system. An LPAR consists of processors, memory, and I/O slots available in one processor complex.
Storage facility image (SFI)
A storage facility image consists of two LPARs, one on each processor complex in a storage facility. A storage facility image is capable of performing all functions of a storage server from the host's perspective. More than one SFI can be configured on a storage facility. A storage facility image might also be referred to as a storage image.
Storage facility image server
One SFI consists of two LPARs; each LPAR hosts a storage facility image server running a specific AIX instance. Thus, one SFI has two storage facility image servers, often referred as Server 0 and Server 1.
An array site is a group of 8 DDMs selected by the DS8000 server algorithm in a storage facility image. An array site is managed by one storage facility image.
Each array site can be individually formatted by the user to a specific RAID format. A formatted array site is called an array. The supported RAID formats are RAID-5 and RAID-10. The process of selecting the RAID format for an array is also called defining an array.
A rank is defined by the user. The user selects an array and defines the storage format for the rank, which is either Count Key Data (CKD) or Fixed Block (FB) data. One rank will be assigned to one extent pool by the user.
The available space on each rank is divided into extents. The extents are the building blocks of the logical volumes. The characteristic of the extent is its size, which depends on the specified device type when defining a rank:
- For fixed block format, the extent size is 1 GB.
- For CKD format, the extent size is .94GB for model 1.
An extent pool refers to a logical construct to manage a set of extents. The user defines extent pools by selecting one to N ranks managed by one storage facility image. The user defines which storage facility image server (Server 0 or Server 1) will manage the extent pool. All extents in an extent pool must be of the same storage type (CKD or FB). Extents in an extent pool can come from ranks defined with arrays of different RAID formats, but the same RAID configuration within an extent pool is recommended. The minimum number of extent pools in a storage facility image is two (each storage facility image server manages a minimum of one extent pool).
Ranks are organized in two rank groups:
- Rank group 0 is controlled by server 0.
- Rank group 1 is controlled by server 1.
A logical volume is composed of a set of extents from one extent pool.
- A logical volume composed of fixed block extents is called a LUN.
- A logical volume composed of CKD extents is referred to as a CKD volume or logical device.
A logical subsystem (LSS) is a logical construct grouping logical volumes. One LSS can group up to 256 logical volumes from extent pools. The user can define up to 255 LSSs in a storage facility image with the following restriction: the logical volumes in one LSS must be of extent pools with identical extent types and from the same rank pool in one storage facility image. As a result, LSSs are either CKD or FB and have affinity with one storage facility image server. Up to 128 LSSs can be managed by Server 0 and up to 127 LSSs can be managed by Server 1 (one LSS address is reserved).
An address group refers to a group of LSSs. Up to 16 LSSs can be grouped into one address group. All LSSs in an address group must be of the same format (CKD or FB). The address groups are defined by the user. A storage facility image can manage up to 16 address groups.
One host attachment is a named group of World Wide Port Names (WWPNs) defined by the user. The definition of host attachment is necessary to manage the LUN masking. One WWPN can be defined in only one host attachment. The user assigns one host attachment to one volume group. Each WWPN in the host attachment will get access to all of the LUNs defined in the volume group.
The user gathers LUNs into volume groups. The definition of volume groups is necessary to manage the LUN masking. One LUN can be defined in several volume groups. One volume group can be assigned to several host attachments.
This material has not been submitted to any formal IBM test and is published AS IS. It has not been the subject of rigorous review. IBM assumes no responsibility for its accuracy or completeness. The use of this information or the implementation of any of these techniques is a client responsibility and depends upon the client's ability to evaluate and integrate them into the client's operational environment.
Follow IBM Redbooks
Follow IBM Redbooks