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:
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
Help IBM prioritize your ideas and requests
The IBM team may need your help to refine the ideas so they may ask for more information or feedback. The product management team will then decide if they can begin working on your idea. If they can start during the next development cycle, they will put the idea on the priority list. Each team at IBM works on a different schedule, where some ideas can be implemented right away, others may be placed on a different schedule.
Receive notification on the decision
Some ideas can be implemented at IBM, while others may not fit within the development plans for the product. In either case, the team will let you know as soon as possible. In some cases, we may be able to find alternatives for ideas which cannot be implemented in a reasonable time.
Because "Preemption scheduling" is actually for the jobs in different queues.LSF today has no such feature or concept of in-queue preemption. the new feature maybe work like this:define a INQUEUE_PREEMPT=[[userA,80%] [userB,20%]] ...For example, ...
Add support to Kerberos ticket with new "renew-until" date for already submitted jobs
While using Kerberos ticket forwarding on a LSF cluster: Currently TGT found on the submission host is copied to LSF cache and forwarded to the execution host at job submission; These tickets can be renewed automatically by LSF until the TGT "rene...
We are troubled by the slow dispatch time of jobs, when the license scheduler is involved. Even after lengthy optimization, the dispatch time remains at 10-25 seconds, which is not good. (note that LMSTAT time and interval is just 3 seconds).If th...
License token distribution without share based calculation by LSF License Scheduler
In License Scheduler it is mandatory to configure Project mode or Cluster mode and specify the shares for all the defined Features.However, some license tokens are not tied to any project or cluster and should be distributed freely, without any fa...
The docker LSF integration would be more useful if the user inside the container was not forced to be LSB_SUB_USER. It's not clear where this -u flag is being added to the docker command by LSF. The construction of this flag does not appear to be ...
almost 3 years ago
in Spectrum LSF
Not under consideration
LSF Explorer support for multiple clusters with the same name
Customer has multiple clusters with the same cluster name.Changing LSF cluster names to be unique is not an option.Their environment is large.Other products in the LSF family support this.LSF_LIC_SCHED_CLUSTER_ALIAS addresses the concern for Licen...
Job slot of suspended jobs should be used in pending jobs
Hi Team,I would like pending jobs to be executed on the slots, where jobs are suspended using bstop command.Currently its not happening and those suspended job slots are remains unused. I request you to have a look and fix this issues in future r...
Increase MAX_JOBID in PE environment - 4194303 too low
When using PE in LSF the maximum job ID is 4194303.We have already cycled through the range in 12 months and we'll likely do it twice this year.Having jobs with duplicate IDs causes a lot of problems with things like job accounting.
Do not place IBM confidential, company confidential, or personal information into any field.