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.
Conductor should capture memory details for Jobs finished less than 30 seconds
Currently IBM SC is sending max memory as 0 or no memory for jobs completed less than 30 seconds. PNC application has majority of jobs that runs less than minute in small queues. Memory information is very important for PNC application to queue the job to small, medium, large, and extra-large for execution.
In case memory information is 0 or not provided then job will go to large queue. This will overload and occupy all large queues and exceed the limit. Small queues having highest limit will be underutilized. Overall goal for PNC application team is to reduce the job execution time and consume less memory. We would need same behavior as sas lasf where we were getting real time max memory for each job getting executed in grid.
The interim solution that was provided by IBM Support requires additional 2 rest calls to be made to EGO Activity API with the driver and executor container info to get the max RSS memory which just adds more overhead / calculations and the values that were returned doesn’t look reliable.. We tried to compare this max RSS value for the runs where memory was returned from ELK and they do not match. Also we don’t get the information related to CPU cores/slots from this call. PNC would like to have permanent solution to get max memory and CPU information for each job executions.
Do not place IBM confidential, company confidential, or personal information into any field.