Contents | Previous | Next

Migration from Other VM Releases

The performance results provided here apply to migration from VM/ESA 2.4.0. This section discusses how to use the information in this report along with similar information from earlier reports to get an understanding of the performance of migrating from earlier VM releases.

Note: In this section, VM/ESA releases prior to VM/ESA 2.1.0 are referred to without the version number. For example, VM/ESA 2.2 refers to VM/ESA Version 1 Release 2.2.

Migration Performance Measurements Matrix

The matrix on the following page is provided as an index to all the performance measurements pertaining to VM migration that are available in the VM performance reports. The numbers that appear in the matrix indicate which report includes migration results for that case: (Ref #1.)

See Referenced Publications for more information on these reports.

Most of the comparisons listed in the matrix are for two consecutive VM releases. For migrations that skip one or more VM releases, you can get a general idea how the migration will affect performance by studying the applicable results for those two or more comparisons that, in combination, span those VM releases. For example, to get a general understanding of how migrating from VM/ESA 2.3.0 to z/VM 3.1.0 will tend to affect VSE guest performance, look at the VM/ESA 2.3.0 to VM/ESA 2.4.0 comparison measurements and the VM/ESA 2.4.0 to z/VM 3.1.0 comparison measurements. In each case, use the measurements from the system configuration that best approximates your VM system.

The comparisons listed for the CMS-intensive environment include both minidisk-only and SFS measurements. Internal throughput rate ratio (ITRR) information for the minidisk-only CMS-intensive environment has been extracted from the CMS comparisons listed in the matrix and is summarized in "Migration Summary: CMS-Intensive Environment".

Table 1. Sources of VM Migration Performance Measurement Results

Migration Summary: CMS-Intensive Environment

A large body of performance information for the CMS-intensive environment has been collected over the last several releases of VM. This section summarizes the internal throughput rate (ITR) data from those measurements to show, for CMS-intensive workloads, the approximate changes in processing capacity that may occur when migrating from one VM release to another. As such, this section can serve as one source of migration planning information.

The performance relationships shown here are limited to the minidisk-only CMS-intensive environment. Other types of VM usage may show different relationships. Furthermore, any one measure such as ITR cannot provide a complete picture of the performance differences between VM releases. The VM performance reports can serve as a good source of additional performance information.

Table 2 summarizes the approximate ITR relationships for the CMS-intensive environment for migrations to z/VM 3.1.0.

Table 2. Approximate z/VM 3.1.0 Relative Capacity: CMS-Intensive Environment

Explanation of columns:

1. The VM/SP 5 system is assumed to include APAR VM30315, the performance SPE that adds segment protection and 4KB key support. Other measurements have shown that VM/SP 5 ITR is 4% to 6% lower without this APAR.

2. This includes an increase of central storage from 16MB to 32MB to compensate for VM/ESA's larger storage requirements. The VM/ESA case also includes 16MB of expanded storage for minidisk caching.

3. The VM/SP HPO 5 to VM/ESA 1.0 (ESA Feature) portion of the derivation was done with a reduced think time to avoid a 16MB-line real storage constraint in the HPO case. In cases where the base HPO system is 16MB-line constrained, migration to VM/ESA will yield additional performance benefits by eliminating this constraint.

4. z/VM 3.1.0 supports a larger real memory size than the stated migration source and this potential benefit is not reflected in the stated ITR ratios. Migrations from memory-constrained environments may yield additional ITRR and other performance benefits when the z/VM 3.1.0 system has additional real storage.

5. There has been growth in CMS real storage requirements on a per user basis. This growth is reflected in the ITR ratios to only a limited extent and should therefore be taken into consideration separately. The most significant growth took place in VM/SP 6 and in VM/ESA 2.0. The VM/SP 6 increase can affect the performance of migrations from VM/SP 5 and VM/SP HPO 5. The VM/ESA 2.0 growth can affect the performance of migrations from VM releases prior to VM/ESA 2.0. Storage constrained environments with large numbers of CMS users will be the most affected.

6. This ITRR value depends strongly upon the fact that CMS is now shipped with most of its REXX execs and XEDIT macros compiled (see Performance Improvements). If these are already compiled on your system, divide the ITRR shown by 1.07.

The ITRR estimates in Table 2 assume use of the z/VM 3.1.0 31-bit CP. If you are using the 64-bit CP, multiply the ITRR shown by 0.99 and refer to note 4 to see if it applies.

Table 2 only shows performance in terms of ITR ratios (processor capacity). It does not provide, for example, any response time information. An improved ITR tends to result in better response times and vice versa. However, exceptions occur. An especially noteworthy exception is the migration from 370-based VM releases to VM/ESA. In such migrations, response times have frequently been observed to improve significantly, even in the face of an ITR decrease. One pair of measurements, for example, showed a 30% improvement in response time, even though ITR decreased by 5%. When this occurs, factors such as XA I/O architecture and minidisk caching outweigh the adverse effects of increased processor usage. These factors have a positive effect on response time because they reduce I/O wait time, which is often the largest component of system response time.

Keep in mind that in an actual migration to a new VM release, other factors (such as hardware, licensed product release levels, and workload) are often changed in the same time frame. It is not unusual for the performance effects from upgrading VM to be outweighed by the performance effects from these additional changes.

These VM ITRR estimates can be used in conjunction with the appropriate hardware ITRR figures to estimate the overall performance change that would result from migrating both hardware and VM. For example, suppose that the new processor's ITR is 1.30 times that of the current system and suppose that the migration also includes an upgrade from VM/ESA 2.1 to z/VM 3.1.0. From Table 2, the estimated ITRR for migrating from VM/ESA 2.1 to z/VM 3.1.0 is 1.08. Therefore, the estimated overall increase in system capacity is 1.30*1.08 = 1.40.

Table 2 represents CMS-intensive performance for the case where all files are on minidisks. The release-to-release ITR ratios for shared file system (SFS) usage are very similar to the ones shown here.

Contents | Previous | Next