User guide

Hardware architecture 2–7
Hitachi Unified Storage VM Block Module Hardware User Guide
Figure 2-3: Sample RAID 5 3D + 1P Layout (Data Plus Parity Stripe) on
page 2-7 illustrates RAID 5 data stripes mapped across four physical drives.
Data and parity are striped across each of the data drives in the array group
(hence the term “parity group”). The logical devices (LDEVs) are evenly
dispersed in the array group, so that the performance of each LDEV within
the array group is the same. This figure also shows the parity chunks that
are the Exclusive OR (EOR) of the data chunks. The parity and data chunks
rotate after each stripe. The total data in each stripe is 2304 blocks (768
blocks per chunk) for open-systems data. Each of these array groups can
be configured as either 3390-x or OPEN-x logical devices. All LDEVs in the
array group must be the same format (3390-x or OPEN-x). For open
systems, each LDEV is mapped to a SCSI address, so that it has a TID and
logical unit number (LUN).
Item Description
Description In the case of RAID5 (7D+1P), two or four parity groups (eight
drives)are concatenated, and the data is distributed and arranged in
16 drives or 32 drives.
Advantage When the parity group becomes a performance bottleneck, the
performance improvement can be attempted because it is
configuredwith twice and four times the number of drives in
comparison with RAID5 (7D+1P).
Disadvantage The influence level when two drives are blocked is large because
twiceand four times LDEVs are arranged in comparison with RAID5
(7D+1P). However, the probability that the read of the single block in
the parity group becomes impossible due to the failure is the same as
that of RAID5 (7D+1P).
Figure 2-3: Sample RAID 5 3D + 1P Layout (Data Plus Parity Stripe)