Merge pull request #553 from yandthj/kestrel_updates

Kestrel Updates
NREL · Nov 28, 2023 · 0590bd7 · 0590bd7
2 parents 62403aa + ef52c5a
commit 0590bd7
Show file tree

Hide file tree

Showing 3 changed files with 22 additions and 9 deletions.
diff --git a/docs/Documentation/Systems/Kestrel/filesystems.md b/docs/Documentation/Systems/Kestrel/filesystems.md
@@ -54,7 +54,7 @@ Directories in /projects have a quota assigned based on the project resource all
     # An asterisk(*) by the used value indicates the project has exceeded its quota of storage, and writes to the directory are not allowed.
     ```
 
-**/shared-projects**
+**/kfs2/shared-projects**
 
 Projects may request a shared project directory to host data, configuration, and applications shared by multiple projects/allocations. 
 
@@ -67,8 +67,25 @@ To request a /shared-projects directory, please contact [hpc-help@nrel.gov](mail
 5. What you would like to call the directory. For example, "/shared-projects/myproject-shared" or other similar descriptive name, ideally between about 4-15 characters in length. 
 6. A group name for the UNIX group ownership of the directory, the same or similar to the directory name provided in Step 5. 
 ```
-!!! info
-    If you currently have a shared project directory on Eagle that you need copied over to Kestrel, please contact [hpc-help@nrel.gov](mailto:HPC-Help@nrel.gov). 
+
+!!! info 
+    Shared project directories are not automatically synced between Eagle and Kestrel. 
+
+**/kfs2/pdatasets**
+
+The /kfs2/pdatasets directory on Kestrel hosts widely used data sets.
+
+There are multiple big data sets that are commonly used across various projects for computation and analysis on NREL's HPC Systems. We provide a common location on Kestrel's filesystem at /kfs2/pdatasets, where these data sets are available for global reading by all compute nodes. Each data set contains a readme file that covers background, references, explanation of the data structure, and Python examples.
+
+These datasets include: 
+
+**/kfs2/pdatasets/NSRDB**
+
+The National Solar Radiation Database (NSRDB) is a serially complete collection of meteorological and solar irradiance data sets for the United States and a growing list of international locations for 1998-2017. The NSRDB provides foundational information to support U.S. Department of Energy programs, research, and the general public.
+
+**/kfs2/pdatasets/WIND**
+
+The Wind Integration National Data Set (WIND) Toolkit consists of wind resource data for North America and was produced using the Weather Research and Forecasting Model (WRF).
 
 ### ScratchFS
 
@@ -81,11 +98,6 @@ Each user has their own directory in /scratch.
 !!! warning 
     Data in /scratch is subject to deletion after 28 days of inactivity. It is recommended to store your important data, libraries, and programs on ProjectFS. 
 
-### Datasets
-
-We plan to have the datasets hosted on Eagle available on Kestrel in the near future. Please contact [hpc-help@nrel.gov](mailto:HPC-Help@nrel.gov) for current information about availability. 
-
-
 ## Node File System
 
 Some Kestrel compute nodes have an NVMe local solid-state drive (SSD) for use by compute jobs. They vary in size; 1.7TB on 256 of the standard compute nodes and 5.8TB on the bigmem nodes. There are several possible scenarios in which a local disk may make your job run faster. For instance, you may have a job accessing or creating many small (temporary) files, you may have many parallel tasks accessing the same file, or your job may do many random reads/writes or memory mapping.

diff --git a/docs/Documentation/Systems/Kestrel/running.md b/docs/Documentation/Systems/Kestrel/running.md
@@ -11,7 +11,7 @@ Kestrel nodes are associated with one or more partitions.  Each partition is ass
 
 Excluding the shared and debug partitions, jobs will be automatically routed to the appropriate partitions by Slurm based on node quantity, walltime, hardware features, and other aspects specified in the submission. Jobs will have access to the largest number of nodes, thus shortest wait, **if the partition is not specified during job submission.**.
 
-The [Kestrel system configuration page](https://www.nrel.gov/hpc/kestrel-system-configuration.html) lists the four categories that Kestrel nodes exhibit based on their hardware features. 
+The [Kestrel system configuration page](https://www.nrel.gov/hpc/kestrel-system-configuration.html) lists the four categories that Kestrel nodes exhibit based on their hardware features. In summary, standard compute nodes on Kestrel have 104 cores and 256 GB of RAM. 256 of those nodes have a 1.7 TB NVMe local disk. There are also 10 bigmem nodes with 2 TB of RAM and 5.8 TB NVMe local disk. 
 
 The following table summarizes the partitions on Kestrel:
 

diff --git a/docs/Documentation/Systems/index.md b/docs/Documentation/Systems/index.md
@@ -15,6 +15,7 @@ NREL operates three on-premises systems for computational work.
 | OS          | RedHat Enterprise Linux | CentOS    | Rocky Linux    | RedHat       |
 | Login       | kestrel.hpc.nrel.gov | eagle.hpc.nrel.gov | swift.hpc.nrel.gov | vs.hpc.nrel.gov |
 | CPU         | Dual socket Intel Xeon Sapphire Rapids | Dual Intel Xeon Gold Skylake 6154 | Dual AMD EPYC 7532 Rome CPU | Dual AMD EPYC 7532 Rome CPU |
+| Cores per CPU Node | 104 cores | 36 cores | 128 cores | Varies by partition | 
 | Interconnect | HPE Slingshot 11 | InfiniBand EDR | InfiniBand HDR| 25GbE |
 | HPC scheduler | Slurm | Slurm | Slurm | Slurm |
 | Network Storage | 95PB Lustre | 17PB Lustre FS | 3PB NFS | 440 TB