DS8000 virtualization of data

From array site to volume

Virtualization definition
The definition of virtualization is the abstraction process of transforming the
physical drives to a logical volume that is presented to hosts and other systems in
a way that they see it as local physical drive.

Virtualization on storage level

The physical drives are mounted in storage enclosures and connected in a
switched Fibre Channel (FC) topology that uses a Fibre Channel Arbitrated Loop
(FC-AL) protocol, or directly through the PCIe Fabric in the case of the High-
Performance Flash Enclosure (HPFE).
Main Abstract layers for disk virtualization are:
• Array sites
• Arrays
• Ranks
• Extent pools
• Logical volumes
• Logical storage subsystems
• Address groups
• Host attachments

VIRTUALIZATION CONCEPTS IVAYLO ATANASOV

 1. Array sites
An array site is a group of identical drives (same capacity, speed, and drive class).
Which drives form an array site is predetermined automatically by the DS8000
There is no predetermined processor node affinity for array sites. Array sites are
the building blocks that are used to define arrays.
For FC-AL topology, the drives that are selected for an array site are chosen from
two standard drive enclosures that make one storage enclosure pair (four drives
from each enclosure). This configuration ensures that half of the drives are on
different loops. This design is called array across loops
Array sites in the HPFEs can contain seven flash cards. This is a change from the
array configuration that is used in standard drive enclosures, where all array sites
have eight drives.

VIRTUALIZATION CONCEPTS IVAYLO ATANASOV

During the configuration process, arrays are created from the array sites. The
flash enclosures support only RAID 5 arrays, which are either 6+Parity+Spare or
6+Parity. This is a change from the array configuration that is used in standard
drive enclosures, where all array sites have eight drives

2. Arrays
An array is created from one array site. Forming an array means defining its
Redundant Array of Independent Disks (RAID) type. The following RAID types are
supported:
RAID 5 – Supports one failed Drive at certain moment
RAID 6 – Supports two failed Drives at certain moment
This RAID type is the preferred one for the DS storage system
RAID 10 – Mirror-stripe RAID
The flash cards and the HPFE support only RAID 5
Tip: Remember that larger drives have a longer rebuild time. Only RAID 6 can
recover from a second error during a rebuild due to the extra parity. RAID 6 is the
best choice for systems that require high availability and is therefore the default.
Using RAID 6 is highly preferred and is the default in the DS GUI for DS8880. As
with large drives, the RAID rebuild time (after one drive failing) get ever larger.
Using RAID 6 significantly reduces the danger of data loss due to a double-RAID
failure
You should already be familiar how RAID works from the DS8xxx Architecture and
Implementation guide.

VIRTUALIZATION CONCEPTS IVAYLO ATANASOV

 3. Rank
In the DS8000 virtualization hierarchy, there is another logical construct that is
called a rank. When a new rank is defined, its name is chosen by the DS
Management GUI or DSCLI; for example, R1, R2, or R3. You must add an array to a
rank. Rank will define the logical construct of the array. Here we must choose the
purpose of the rank and type of the operating system which will access it.
The process of forming a rank accomplishes the following objectives: The array is
formatted for fixed block (FB for Open System such as Windows, Linux etc.) or
count key data (CKD for z Systems data).
The available space on each rank is divided into extents. The extents are the
building blocks of the logical volumes. An extent is striped across all drives of an
array. This formatting determines the size of the set of data that is contained on
one drive within a stripe on the array. The capacity of the array is subdivided into
equal-sized partitions, called extents. The extent size depends on the extent type,
FB or CKD. An FB rank features an extent size of 1 GB (more precisely, GiB,
gibibyte, or binary gigabyte, being equal to 230 bytes

VIRTUALIZATION CONCEPTS IVAYLO ATANASOV

 4. Extent pools
An extent pool is a logical construct to aggregate the extents from a set of ranks,
which forms a domain for extent allocation to a logical volume. Originally, extent
pools were used to separate drives with different revolutions per minute (rpm)
and capacity in different pools that have homogeneous characteristics. You still
might want to use extent pools for this purpose. However, with the capabilities of
Easy Tier moving data across different storage tiering levels to optimize I/O
throughput, you can create extent pools with a mix of flash cards, flash drives,
Enterprise SAS drives, and nearline drives. Thus, you can allow Easy Tier to
optimize the placement of the data within the extent pool.

VIRTUALIZATION CONCEPTS IVAYLO ATANASOV

 5. Logical volumes
A logical volume is composed of a set of extents from one extent pool. On a
DS8000, up to 65,280 volumes can be created (either 64-K CKD, or 64-K FB
volumes, or a mixture of both types with a maximum of 64-K volumes in total).
The abbreviation 64 K is used in this section, even though it is 65,536 minus 256,
which is not quite 64 K in binary

5.1. Fixed block LUNs - A logical volume that is composed of fixed block
extents is called a logical unit number (LUN). A fixed-block LUN is
composed of one or more 1 GiB (230 bytes) extents from one FB extent
pool. A LUN cannot span multiple extent pools, but a LUN can have
extents from separate ranks within the same extent pool. You can
construct LUNs up to a size of 16 TiB (16 x 240 bytes, or 244 bytes).

VIRTUALIZATION CONCEPTS IVAYLO ATANASOV

 5.2. Count key data volumes
A z Systems count key data (CKD) volume is composed of one or more extents
from one CKD extent pool. CKD extents are of the size of 3390 Model 1, which
features 1113 cylinders. However, when you define a z Systems CKD volume, you
do not specify the number of 3390 Model 1 extents but the number of cylinders
you want for the volume.

6. Logical subsystems
An LSS is another logical construct. It can also be referred to as an LCU. The term
LSS is mostly used in association with FB volumes. The term LCU is used in
association with CKD volumes. A maximum of 255 LSSs can exist in the DS8000.
Each of them has an identifier of 00 - FE. An individual LSS must manage either FB
or CKD volumes.

VIRTUALIZATION CONCEPTS IVAYLO ATANASOV

 7. Address groups
Address groups are created automatically when the first LSS that is associated
with the address group is created. The groups are deleted automatically when the
last LSS in the address group is deleted. All devices in an LSS must be CKD or FB.
This restriction goes even further. LSSs are grouped into address groups of 16
LSSs. LSSs are numbered X’ab’, where a is the address group and b denotes an LSS
within the address group. For example, X’10’ - X’1F’ are LSSs in address group 1.
All LSSs within one address group must be of the same type (CKD or FB). The first
LSS that is defined in an address group sets the type of that address group

VIRTUALIZATION CONCEPTS IVAYLO ATANASOV

VIRTUALIZATION CONCEPTS IVAYLO ATANASOV
 8. Host attachment
HBAs are identified to the DS8000 in a host attachment construct that specifies
the worldwide port names (WWPNs) of a host’s HBAs. A set of host ports can be
associated through a port group attribute that allows a set of HBAs to be
managed collectively. This port group is referred to as a host attachment within
the configuration. Each host attachment can be associated with a volume group
to define the LUNs that host is allowed to access. Multiple host attachments can
share the volume group. The host attachment can also specify a port mask that
controls the DS8000 I/O ports that the host HBA is allowed to log in to. Whichever
ports the HBA logs in on, it sees the same volume group that is defined on the
host attachment that is associated with this HBA. The maximum number of host
attachments on a DS8000 is 8,192. This host definition is only required for open
systems hosts. Any IBM Z servers can access any CKD volume in a DS8000 if its
IOCDS is correct

9. Summary:
The DS8000 virtualization includes the following benefits:
• Flexible logical volume configuration:
• Flexible logical volume sizes
• Flexible number of logical volumes
• No strict relationship between RAID ranks and logical subsystems (LSSs)
• LSS definition allows flexible configuration of the number and size of
devices for each

There is variation between different generation of the DS storage system in terms

of the virtualization capabilities.
For detail information on each topic and advance functionalities please refer to
the DS8xxx Architecture and Implementation guides or “DS8000 Series Hardware
Architecture” learning plan.

VIRTUALIZATION CONCEPTS IVAYLO ATANASOV