This portal is to open public enhancement requests against products and services offered by the IBM Data & AI organization. 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 updateson them if they matter to you. If you can't find what you are looking for,
Post your ideas
Post ideas and requests to enhance a product or service. Take a look at ideas others have posted and upvote them if they matter to you,
Post an idea
Upvote ideas that matter most to you
Get feedback from the IBM team to refine your idea
Specific links you will want to bookmark for future use
Provide an Option to break out of 'bsub' if a job will not submit due to a user hitting their pending job limit
This is a major problem when using a web service to control jobs, you would much rather have the binary end with an exit code than continually block in a loop saying you have reached your pending jobs limit. It's really bad design behavior IMHO.
Spectrum LSF used to provide an adapter for k8s as a container orchestration to use with LSF's job scheduling as its add-on function, which is withdrawn now. The customer would like to restore it so they could improve portability/availability and ...
Allow to set/modify the same option in multiple esubs
Currently a specific option can only be set or modified once through an esub, even if multiple esub's are run. If an option is set a second time, the error message ... Conflict parameter <PARAMETER_NAME> - Ignored. appears. There are at leas...
Allow Flagging Jobs for Reservation Through Rules and/or Through a "bsub --plan" Option
Today, reservations in LSF are handled by the Top X jobs by ordered by Dynamic Priority using the variable MAX_JOB_RESERVE. We believe that this is a shotgun approach. We have millions of jobs a day that require 1 cores and less than 1GB of memory...
The file `lsf.shared` provided with Spectrum LSF is outdated. The CPU models listed seem to be 10 years old and older and there don't seem to be any updates from IBM. I suggest that IBM regularly updates this file with up-to-date CPU models and me...
This is the current bbot/btop functionality:- Group administrators can change the position of all jobs submitted by users who are members of the user group within a queue (move the selected job before/after the first/last job with the same priorit...
In the world of Multi-core processors, the context switches per second has become a KPI. It should be a standard performance metric like mem, r1m, etc.
When we try to oversubscribe hosts, it would be very beneficial to have ctx/second available as a base metric. It's available in all OS' these days. We could set a busy threshold for that say above 40k/second. For the longest time (maybe 31 years)...
Enhance bmod to not allow modifying a jobs memory reservation to not exceed the total additional reservable memory on the host if the job is running
This is important if a users wants to either decrease of increase a memory reservation for a running job. We have some applications that reserved multiple CPU's and large amounts of memory. These jobs are long tailed, and once they reach the long ...
Do not place IBM confidential, company confidential, or personal information into any field.