Bioinformatics Center

User Tools

Site Tools

You are here: home » guides » slurm
guides:slurm

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision 		Previous revision
guides:slurm [17.04.2020 12:14]
Juha Kekäläinen 		guides:slurm [18.10.2024 14:08] (current)
Administrator
Line 3: Line 3:
 [Slurm Workload Manager](https://slurm.schedmd.com/overview.html) is an open source [Job scheduler](https://en.wikipedia.org/wiki/Job_scheduler) that is intended to control background executed programs. These background executed programs are called **Jobs**. The user specifies the Job with various parameters that include run time, number of tasks, number or required CPU cores, amount of required memory (RAM) and specify which program(s) to execute. These jobs are called batch jobs. (Batch) Jobs are submitted to a common job queue (partition) that is shared by the other users and Slurm will execute the submitted jobs automatically in turn. After the job is completed (or an error occurs) Slurm can optionally notify the user with an email notification. Additionally to the batch jobs the user can reserve a compute node for interactive jobs where you wait for your turn in a queue and on your turn you are put on your reserved node where you can execute commands. After the reserved time is over your sessions is terminated. [Slurm Workload Manager](https://slurm.schedmd.com/overview.html) is an open source [Job scheduler](https://en.wikipedia.org/wiki/Job_scheduler) that is intended to control background executed programs. These background executed programs are called **Jobs**. The user specifies the Job with various parameters that include run time, number of tasks, number or required CPU cores, amount of required memory (RAM) and specify which program(s) to execute. These jobs are called batch jobs. (Batch) Jobs are submitted to a common job queue (partition) that is shared by the other users and Slurm will execute the submitted jobs automatically in turn. After the job is completed (or an error occurs) Slurm can optionally notify the user with an email notification. Additionally to the batch jobs the user can reserve a compute node for interactive jobs where you wait for your turn in a queue and on your turn you are put on your reserved node where you can execute commands. After the reserved time is over your sessions is terminated.
  
-## Slurm Partitions on sampo.uef.fi+{{:guides:slurm:slurm.png}}
  
-- **serial**. 4 out of 4 nodes. Maximum run time 3 days +## Slurm Partitions on kudos.uef.fi 
-- **longrun**. 2 out of 4 nodes. Maximum run time 14 days + 
-- **parallel**. 2 of 4 nodes. Maximum run time 3 days. +- **small**. 8 out of 10 nodes. Maximum run time 3 days 
-- **gpu**. 1 node. Maximum run time 3 days.+- **longrun**. 3 out of 10 nodes. Maximum run time 14 days 
 +- **gpu**. 2 nodes. Maximum run time 3 days.
  
 ## Explanation of the partitions ## Explanation of the partitions
Line 14: Line 15:
 Compute nodes are grouped into multiple partitions and each partition can be considered as a job queue. Partitions can have multiple constraints and restrictions. For example access to certain partitions can be limited by the user/group or the maximum running time can restricted. Compute nodes are grouped into multiple partitions and each partition can be considered as a job queue. Partitions can have multiple constraints and restrictions. For example access to certain partitions can be limited by the user/group or the maximum running time can restricted.
  
-**Serial** partition is the default partition for all jobs that the user submits. The user can reserve maximum of 1 nodes for his/her job. Default run time is 5 minutes and maximum 3 days. +**small** partition is the default partition for all jobs that the user submits. The user can reserve maximum of 1 nodes for his/her job. Default run time is 5 minutes and maximum 3 days.
- +
-**Longrun** partition is for long running jobs and only one node is for this usage. Default run time 5 minutes and maximum 14 days.+
  
-**Parallel** partition is for parallel jobs that can span over multiple nodes (MPI jobs for example). The user can reserve 2 nodes (minimum and maximum). Default run time is 5 minutes and maximum 3 days.+**longrun** partition is for long running jobs and only one node is for this usage. Default run time 5 minutes and maximum 14 days.
  
-**GPU** partition is for gpu jobs (CUDA jobs). The user can reserve 1 node with NVIDIA P100/16 GB. Default run time is 5 minutes and maximum 3 days.+**gpu** partition is for gpu jobs (CUDA jobs). The user can reserve 2 nodes with 8xNVIDIA A100/40 GB. Default run time is 5 minutes and maximum 3 days.
  
  
guides/slurm.1587114868.txt.gz · Last modified: 17.04.2020 12:14 by Juha Kekäläinen

Page Tools