IBM Z Software
This portal is to open public enhancement requests against IBM Z Software products. To view all of your ideas submitted to IBM, create and manage groups of Ideas, or create an idea explicitly set to be either visible by all (public) or visible only to you and IBM (private), use the IBM Unified Ideas Portal (https://ideas.ibm.com).
Shape the future of IBM!
We invite you to shape the future of IBM, including product roadmaps, by submitting ideas that matter to you the most. Here's how it works:
Search existing ideas
Start by searching and reviewing ideas and requests to enhance a product or service. Take a look at ideas others have posted, and add a comment, vote, or subscribe to updates on them if they matter to you. If you can't find what you are looking for,
Post your ideas
Post an idea.
Get feedback from the IBM team and other customers to refine your idea.
Follow the idea through the IBM Ideas process.
Specific links you will want to bookmark for future use
Welcome to the IBM Ideas Portal (https://www.ibm.com/ideas) - Use this site to find out additional information and details about the IBM Ideas process and statuses.
IBM Unified Ideas Portal (https://ideas.ibm.com) - Use this site to view all of your ideas, create new ideas for any IBM product, or search for ideas across all of IBM.
ideasibm@us.ibm.com - Use this email to suggest enhancements to the Ideas process or request help from IBM for submitting your Ideas.
IBM does not intend to implement this RFE for the following reasons.
Regarding the request to provide prime queueing, similar behavior already exists with dupe queuing. As acknowledged in the RFE, this change is “cosmetic” compared to dupe queuing and simply changes the MFST entry in which a read I/O is queued. All modules should be considered during monitoring, data collection, debugging, etc. and the relative place in the table should have minimal consideration.
Regarding the request to provide flip-flop queuing when prime/dupe queues are unequal, the proposed solution is not consistent with z/TPF’s objectives and existing solutions should be explored first if a problem does exist.
As a high volume transaction system, the purpose of z/TPF’s architecture is to transact existing (in flight) work as quickly as possible. As a result, z/TPF should not intentionally queue requests to a long queue when there is a choice of a short queue. In addition, the caches on the prime and dupe control units are independent entities which are not meant to be kept in sync and flip-flopping will cause more things to be pushed out of cache than kept in. The only thing z/TPF can do to help manage control unit cache is to consistently queue reads to the same module, which is the purpose of dupe queuing.
If there is interest in improving cache usage in the control units, IBM recommends investigating changing from flip/flop queuing to dupe queuing. This will consistently queue reads to the same physical control unit, which may help cache hit ratios.
If there is a concern about queues becoming too large, shutdown levels (number of available ECBs, IOBs, etc.) should be set low enough to allow z/TPF to complete in flight work and recover to normal operating levels.
If there is aconcern about queues building due to bursty activity or abnormal behavior, IBM recommends investigating HyperPAV support. HyperPAV allows z/TPF to start multiple I/O’s to the same physical device at the same time and can improve throughput.
Attachment (Description)