HP StorageWorks XP Remote Web Console Software - Manual (Page 139)

Table 47 Optimizing TrueCopy for Mainframe Operations and HP disk array Performance
Recommendation(s) Description Condition
Spread write intensive data across
several volumes to minimize queuing. Write-intensive workloads, such as
SPOOL volumes and 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 DB2 deferred writes,
can impact performance. Large block size
Spread the workload across several
storage systems to utilize additional
channels. The demand on the MCU's host
channels can affect performance. High host channel demand
Avoid performing restore operations to
volumes which belong to TrueCopy for
Mainframe pairs. Instead, restore data
to a scratch volume and then establish
the TrueCopy for Mainframe pair. TrueCopy for Mainframe operations
can have a negative impact on
workloads with a high percentage of
sequential write operations, such as
batch processing operations (for
example, dump/restore, sort
operations). Sequential write operations
Consider increasing the cache size of
the TrueCopy for Mainframe storage
systems to handle TrueCopy for
Mainframe Asynchronous, Compatible
XRC, and CC sidefile operations and
to improve overall storage system
performance. For best results, the cache
and NVS capacity of the main and
remote storage systems should be the
same (for TrueCopy for Mainframe
Asynchronous the RCU sidefile
requirements are 2x that of the MCU)
to enable the remote site to function
adequately during disaster recovery. Large cache size improves read hit
performance, which allows more
storage system resources to be
devoted to write operations. The
resulting performance improvement
can offset some or all of the
performance loss due to the TrueCopy
for Mainframe remote copy
operations.
TrueCopy for Mainframe
Asynchronous, Compatible XRC, and
Concurrent Copy (CC) require
additional cache for sidefile data.
Insufficient cache resources can result
in command retries, SCP notifications,
and puncture conditions.
Cache size
Distribute TrueCopy for Mainframe
remote copy operations among several
remote storage systems to avoid
overloading any one RCU. The performance of the RCUs directly
affects the performance of the MCUs.
If an RCU becomes overloaded with
heavy update activity, MCU and
system performance can also be
degraded. RCU capacity
Make sure to install an adequate
number of remote copy connection
paths between the main and remote
storage systems. This is especially
important for storage systems which
contain both M-VOLs and R-VOLs. An inadequate number of remote copy
connection paths may decrease
storage system performance.
Performing TrueCopy for Mainframe
Synchronous operations over long
distances can also degrade storage
system performance. TrueCopy for
Mainframe Asynchronous is
recommended for long distances. Remote copy connection paths
Changing from 3990 to 2105 or 2107 Emulation
TrueCopy for Mainframe supports 3990-6, 3990-6E, 2105, and 2107 controller emulation types
for the HP disk array MCU and RCU. The 3990-6, 3990-6E, 2105 or 2107emulation is required
for SMS I/O time-stamping of TrueCopy for Mainframe Asynchronous recordsets. The 2105 and
2107 emulation type is required for Compatible PAV operations.
Configuring and Maintaining Your TrueCopy for Mainframe Environment 139