Performing Failovers And Failbacks Using Path Switching - Hitachi XP P9500 User Manual

Algorithm type
•
Round Robin
• Least I/Os
• Least Blocks
• Extended Round
Robin
• Extended Least I/Os
• Extended Least
Blocks
#
Some I/O operations managed by HDLM can be distributed across all,
available paths, and some cannot. Thus, you should be aware that even if
you specify the Round Robin algorithm, some of the I/O operations will
never be issued uniformly across all the given paths.
The default algorithm is the Extended Least I/Os algorithm, which is set when
HDLM is first installed. When an upgrade installation of HDLM is performed,
the algorithm that is currently being used is inherited.
Select the load balancing algorithm most suitable for the data access patterns
of your system environment. However, if there are no recognizable data
access patterns, we recommend using the default algorithm, the Extended
Least I/Os algorithm.
You can specify the load balancing function by the dlnkmgr command's set
operation. For details on the set operation, see
Environment) on page

Performing Failovers and Failbacks Using Path Switching

When the system contains multiple paths to an LU and an error occurs on the
path that is currently being used, HDLM can switch to another functional
path, so that the system can continue operating. This is called a failover.
If a path in which an error has occurred recovers from the error, HDLM can
then switch back to that path. This is called a failback.
Two types of failovers and failbacks are available:
• Automatic failovers and failbacks
• Manual failovers and failbacks
Failovers and failbacks switch which path is being used and also change the
statuses of the paths. A path status is either online or offline. An online status
means that the path can receive I/Os. On the other hand, an offline status
means that the path cannot receive I/Os. A path will go into the offline status
for the following reasons:
Table 2-4 Features of the Load Balancing Algorithms
# These types of algorithms are most effective when a lot of
discontinuous, non-sequential I/Os are issued.
If the I/O data is from something like a read request and is
generally sequential with the previous I/Os, an improvement
in reading speed can be expected due to the storage system
cache functionality. These types of algorithms are most
effective when a lot of continuous, sequential I/Os are issued.
6-16.
HDLM Functions
Hitachi Dynamic Link Manager User Guide (for Solaris(R))
Algorithm features
set (Sets Up the Operating
2-15