From 7e15e676312de81245a8beba5454bcda637e0748 Mon Sep 17 00:00:00 2001 From: Alex Villa <115514619+aevilla160@users.noreply.github.com> Date: Tue, 23 Jan 2024 11:02:22 -0800 Subject: [PATCH] Minor adjustments to pages --- docs/Manage_job.md | 3 ++- docs/borgstore.md | 2 +- docs/commun.md | 11 ++++++++++- docs/news.md | 6 ++++++ 4 files changed, 19 insertions(+), 3 deletions(-) diff --git a/docs/Manage_job.md b/docs/Manage_job.md index 52ce577..de03088 100644 --- a/docs/Manage_job.md +++ b/docs/Manage_job.md @@ -18,9 +18,10 @@ Execute the script via the command: | `-M merced ` | Shows all currently submitted jobs on MERCED | | `--me ` | Shows all currently jobs submitted by user | | `--r` or `-array ` | Shows job arrays sumitted onto cluster | +| `--start` | Shows rough estimate of when jobs for specified user will begin, based off real-time state of the scheduler and jobs queued. Not always accurate estimates. | -!> Flags can be used together in the same line for example: `squeue -M merced --me` +!> Flags can be used together in the same line for example: `squeue -M merced --me --start` ## Job State Job states are the current state of the jobs that were submitted. Some important state codes that are useful are given below: diff --git a/docs/borgstore.md b/docs/borgstore.md index ffd38d6..629a62c 100644 --- a/docs/borgstore.md +++ b/docs/borgstore.md @@ -10,7 +10,7 @@ Borgstore is also made up of a metadata server with a `1U dual Xeon Skylake SP`, Borgstore is a purchasable service that can be requested [here](https://ucmerced.service-now.com/servicehub?id=public_kb_article&sys_id=3c3ee9ff1b67a0543a003112cd4bcb13&form_id=06da3f8edbfc08103c4d56f3ce9619f4). Cost for active data storage is $0.05/GB/year (startup funds) and $0.06/GB/year (non-startup funds). More information can be found [here](https://it.ucmerced.edu/Research-Computing-Services). -#### Accessing Data from Borgstore for a job +### Accessing Data from Borgstore for a job To access data that is located in Borgstore the user must be in the Borgstore folder/directory and must the submit job to the scheduler from this location. If users want to submit jobs while at the Borgstore folder, the slurm option of `#SBATCH --constraint=ib` should be added to the job script. A sample job that uses this slurm option can be found [here](running_jobs.md). diff --git a/docs/commun.md b/docs/commun.md index d09df11..393618a 100644 --- a/docs/commun.md +++ b/docs/commun.md @@ -1,5 +1,11 @@ +## 1/24/23 +### COMPLETED: HPC cluster maintenance 1/16/24 +The MERCED and Pinnacles clusters are back online. The CIRT team has completed several updates, including security advisories, bug fixes, and product enhancements. Upgrades encompassed storage server firmware, storage chassis firmware, IB and Data network expansion, and nodes' BIO and BMC firmware. Currently, the default CUDA version for GPU nodes (gnode) is 12.3. + + Please feel free to resume submitting your jobs to the cluster. + ## 11/21/23 -### Anual maintenance +### Annual maintenance Maintenance Notice: 6:30 am January 8, 2024, to 5 pm January 16, 2024 @@ -22,6 +28,8 @@ Happy Computing. + + ## 08/25/23 Dear Research Computing users - @@ -33,6 +41,7 @@ zoom: https://ucmerced.zoom.us/j/89487493900; password:895006 All students, postdocs, staff, and faculty are welcome to attend and bring research computing questions to CIRT team. + ## 07/10/2023 Dear HPC users, diff --git a/docs/news.md b/docs/news.md index 6d529d3..36b5533 100644 --- a/docs/news.md +++ b/docs/news.md @@ -1,5 +1,11 @@ +## COMPLETED: HPC cluster maintenance - 1/16/24 + +The MERCED and Pinnacles clusters are back online. The CIRT team has completed several updates, including security advisories, bug fixes, and product enhancements. Upgrades encompassed storage server firmware, storage chassis firmware, IB and Data network expansion, and nodes' BIO and BMC firmware. Currently, the default CUDA version for GPU nodes (gnode) is 12.3. + + Please feel free to resum + ## CIRT Winter Break Availbility UC Merced campus closes for winter break from December 23 - January 2. Please be aware that CIRT staff will not be available during that period for cluster support or research computing issues. Our services and support will resume as normal when the campus reopens on January 3, 2024. During the closure, you can find current information about outages and service disruptions at status.ucmerced.edu. If you have an emergency related to OIT services at UC Merced, you can call 228-HELP (4357). The CIRT staff would like to take this opportunity to wish our campus partners the happiest of holiday seasons.