HP XP7 Storage - Manual (Page 33)

Check with your HP service provider for more information.
•
Analyze write-workload. Bottlenecks severely impact performance, but the workload data you
collect (MB/s and IOPS) help determine the following key elements that, when sized properly,
form a data path that operates free of bottlenecks under all workload levels:
◦ Amount of bandwidth.
◦ Number of data paths.
◦ Number of host-interface paths.
◦ Number of ports dedicated for Continuous Access Synchronous Z on the primary and
secondary system.
•
If you are setting up Continuous Access Synchronous Z for disaster recovery, make sure that
secondary systems are attached to a host server. This enables both the reporting of sense
information and the transfer of host failover information. If the remote site is unattended by a
host, you should attach the storage systems to a host server at the main site so that the system
administrator can monitor conditions.
The following table lists conditions that affect storage system performance and provides
recommendations for addressing them.
Recommendation Description Condition
Spread write-intensive data across several
volumes to minimize queuing. Write-intensive workloads, such as database
logging volumes, can have a significant impact
on storage system I/O response times. Write-intensive
workloads
Spread workloads with large write block sizes
across several volumes. Workloads with large write block sizes, such
as DB deferred writes, can impact performance. Large block size
Spread the workload across several storage
systems to use additional channels. The demand on the primary system host
channels can affect performance. High host channel
demand
Avoid performing restore operations to volumes
that belong to Continuous Access Synchronous Continuous Access Synchronous Z operations
can have a negative impact on workloads with Sequential write
operations
Z pairs. Instead, restore data to a scratch a high percentage of sequential write
volume, and then create the Continuous Access
Synchronous Z pair. operations, such as batch processing operations
(for example, dump/restore, sort operations).
Consider increasing the cache size of the
Continuous Access Synchronous Z storage Large cache size improves read performance,
which allows more storage system resources to Cache size
systems to improve overall performance. For be devoted to write operations. Insufficient
best results, the cache and NVS capacity of cache resources result in command retries,
the primary and secondary system should be state-change-pending (SCP) notifications, and
puncture conditions.
the same. This allows the remote site to function
adequately during disaster recovery.
Distribute Continuous Access Synchronous Z
remote copy operations among several The secondary system’s performance directly
affects the performance of the primary system. Remote system
performance
secondary systems to avoid overloading any
one system. If a secondary system becomes overloaded with
heavy update activity, host and primary system
performance can also be degraded.
Install a sufficient number of data paths to meet
all write-workload levels. This is especially An inadequate number of data paths decreases
performance. Performing copy operations over
long distances also degrades performance. Data paths
important for systems containing both P-VOLs
and S-VOLs.
System performance considerations 33