diff --git a/book/_toc.yml b/book/_toc.yml index 38b218e..6710506 100644 --- a/book/_toc.yml +++ b/book/_toc.yml @@ -5,18 +5,17 @@ root: welcome # ===== Getting Started ============================= chapters: -- file: part1.md -- file: part2.md -- file: part3.md -- file: part4.md -- file: part5.md -- file: part6.md - +- file: what-is-hpc.md +- file: logging-on-and-linux-recap.md +- file: storage.md +- file: modules-software.md +- file: scheduling-submission.md +- file: best-practices-troubleshooting.md +- file: wrap-up.md # ===== Training and Support ======================== - url: https://arc.leeds.ac.uk/courses/ title: Training Courses -- file: support/start title: Contact Us - url: https://arc.leeds.ac.uk title: Research Computing Website \ No newline at end of file diff --git a/book/best-practices-troubleshooting.md b/book/best-practices-troubleshooting.md new file mode 100644 index 0000000..a48f591 --- /dev/null +++ b/book/best-practices-troubleshooting.md @@ -0,0 +1,10 @@ +# Session 6: HPC Best Practices & Troubleshooting + + +## Common issues with job submission and system usage + +## Strategies for error diagnosis and resource optimization + +## Guidance and Support +### arcdocs (and google) +### submit a ticket \ No newline at end of file diff --git a/book/part2.md b/book/logging-on-and-linux-recap.md similarity index 100% rename from book/part2.md rename to book/logging-on-and-linux-recap.md diff --git a/book/part4.md b/book/modules-software.md similarity index 100% rename from book/part4.md rename to book/modules-software.md diff --git a/book/part6.md b/book/part6.md deleted file mode 100644 index d3ee6ba..0000000 --- a/book/part6.md +++ /dev/null @@ -1,9 +0,0 @@ -# Session 6: Managing and Troubleshooting Jobs - -## Queue commands - -## checks - -## docs (and google) - -## submit a ticket \ No newline at end of file diff --git a/book/part5.md b/book/scheduling-submission.md similarity index 57% rename from book/part5.md rename to book/scheduling-submission.md index 6e09ab9..2abb4aa 100644 --- a/book/part5.md +++ b/book/scheduling-submission.md @@ -1,4 +1,15 @@ -# Session 5: Scheduler +# Session 5: Job Scheduling & Submission + +## Overview of HPC job scheduling systems +### General background +### Slurm +## Job Scripts +### Structure of job scripts +### resource requests +### submission command + + +## exercise - What is a scheduler - Fair use @@ -11,13 +22,8 @@ - https://arcdocs.leeds.ac.uk/aire/usage/job_example.html -## Practical - submit an example serial job +## Practical - write and submit a simple job script, monitor its progress, and learn to interpret feedback - Create/share example job and job script https://arctraining.github.io/rc-slides/hpc1.html#/submit-a-serial-python-job -## Practical - submitting a parallelised job - NR - Remove too advanced - -- Create/port over previous examples - -https://arctraining.github.io/rc-slides/hpc1.html#/submit-some-parallel-jobs \ No newline at end of file diff --git a/book/part3.md b/book/storage.md similarity index 100% rename from book/part3.md rename to book/storage.md diff --git a/book/part1.md b/book/what-is-hpc.md similarity index 100% rename from book/part1.md rename to book/what-is-hpc.md diff --git a/book/wrap-up.md b/book/wrap-up.md new file mode 100644 index 0000000..9a4cc5e --- /dev/null +++ b/book/wrap-up.md @@ -0,0 +1,5 @@ +# Session 7: Wrap Up + +## Recap +## Further Guidance +## Q&A/Discussion \ No newline at end of file