Configuration for site PDC at KTH

.github/workflows/main.yml

@@ -96,6 +96,7 @@ jobs:
           - "oist"
           - "pasteur"
           - "pawsey_nimbus"
+          - "pdc_kth"
           - "phoenix"
           - "prince"
           - "psmn"

README.md

@@ -152,6 +152,7 @@ Currently documentation is available for the following systems:
 - [OIST](docs/oist.md)
 - [PASTEUR](docs/pasteur.md)
 - [PAWSEY NIMBUS](docs/pawsey_nimbus.md)
+- [PDC](docs/pdc_kth.md)
 - [PHOENIX](docs/phoenix.md)
 - [PRINCE](docs/prince.md)
 - [PSMN](docs/psmn.md)

conf/pdc_kth.config

@@ -0,0 +1,72 @@
+// Nextflow config for use with PDC at KTH
+
+def cluster = "unknown"
+
+try {
+    cluster = ['/bin/bash', '-c', 'sacctmgr show cluster -n | grep -o "^\s*[^ ]*\s*"'].execute().text.trim()
+} catch (java.io.IOException e) {
+    System.err.println("WARNING: Could not run scluster, defaulting to unknown")
+}
+
+params {
+  config_profile_description = 'PDC profile.'
+  config_profile_contact = 'Pontus Freyhult (@pontus)'
+  config_profile_url = "https://www.pdc.kth.se/"
+
+  max_memory = 1790.GB
+  max_cpus = 256
+  max_time = 7.d
+
+  schema_ignore_params = "genomes,input_paths,cluster-options,clusterOptions,project,validationSchemaIgnoreParams"
+  validationSchemaIgnoreParams = "genomes,input_paths,cluster-options,clusterOptions,project,schema_ignore_params"
+}
+
+
+def containerOptionsCreator = {
+  switch(cluster) {
+    case "dardel":
+      return '-B /cfs/klemming/'
+   }
+
+   return ''
+}
+
+def clusterOptionsCreator = { mem,time ->
+  String base = "-A $params.project ${params.clusterOptions ?: ''}"
+
+  switch(cluster) {
+    case "dardel":
+      String extra = ''
+
+      if (mem <= 222.GB) {
+        if (time<24.d) {
+          extra += ' -p shared'
+        } else {
+          extra += ' -p long'
+        }
+      } else {
+        // Needs more than a thin node
+	// make an ugly hack to ignore runtime
+      	extra += ' -p main,memory -t 1-0:0'
+      }
+
+      return base+extra
+   }
+
+   return base
+}
+
+
+singularity {
+  enabled = true
+  containerOptions = containerOptionsCreator
+}
+
+process {
+  // Should we lock these to specific versions?
+  beforeScript = 'module load PDC singularity'
+
+  executor = 'slurm'
+  clusterOptions = { clusterOptionsCreator(task.memory, task.time) }
+}
+

docs/pdc_kth.md

@@ -0,0 +1,47 @@
+# nf-core/configs: PDC Configuration
+
+nf-core pipelines have been successfully configured for use on the PDC
+cluster dardel. No other clusters have yet been tested, but support can be
+added if needed.
+
+## Getting started
+
+The base java installation on dardel is Java 11. By loading the `PDC`
+and `Java` module, different versions (e.g. 17) are available.
+
+To pull new singularity images, singularity must be available
+(e.g. through the module system) to the nextflow monitoring process,
+suggested preparatory work before launching nextflow is:
+
+```shell
+
+module load PDC Java singularity
+```
+
+(for reproducibility, it may be a good idea to check what versions you
+have loaded with `module list` and using those afterwards, e.g.
+`module load PDC/22.06 singularity/3.10.4-cpeGNU-22.06 Java/17.0.4`.)
+
+No singularity images or nextflow versions are currently preloaded on
+dardel, to get started you can e.g. download nextflow through
+
+```shell
+wget https://raw.githubusercontent.com/nextflow-io/nextflow/master/nextflow && \
+  chmod a+x nextflow
+```
+
+The profile `pdc_kth` has been provided for convenience, it expects you to
+pass the project used for slurm accounting through `--project`, e.g.
+`--project=nais2023-22-1027`.
+
+Due to [how partitions are set
+up](https://www.pdc.kth.se/support/documents/run_jobs/job_scheduling.html#dardel-partitions)
+on dardel, in particular the lack of long-runtime nodes with more
+memory. Some runs may be difficult to get through.
+
+Note that node local scratch is not available and `SNIC_TMP` as well
+as `PDC_TMP` point to a cluster-scratch area that will have similar
+perfomance characteristics as your project storage. `/tmp` points to a
+local `tmpfs` which uses RAM to store contents. Given that nodes don't
+have swap space anything stored in `/tmp` will mean less memory is
+available for your job.

nfcore_custom.config

@@ -78,6 +78,7 @@ profiles {
     oist             { includeConfig "${params.custom_config_base}/conf/oist.config" }
     pasteur          { includeConfig "${params.custom_config_base}/conf/pasteur.config" }
     pawsey_nimbus    { includeConfig "${params.custom_config_base}/conf/pawsey_nimbus.config" }
+    pdc_kth          { includeConfig "${params.custom_config_base}/conf/pdc_kth.config" }
     phoenix          { includeConfig "${params.custom_config_base}/conf/phoenix.config" }
     prince           { includeConfig "${params.custom_config_base}/conf/prince.config" }
     psmn             { includeConfig "${params.custom_config_base}/conf/psmn.config" }