fix merge conflicts

docs/developer_guidelines.md

@@ -73,11 +73,12 @@ Given a version number MAJOR.MINOR.PATCH, increment the:
 
 ## Process
 
-1. Process names should start `p`.
+Process names should start `p`. The in- and output of processes should contain a sample and/or a bin and contig id.
+Custom error strategies that do not follow the strategy defined in nextflow.config, should be documented (see Megahit example).
 
-2. The input and output of processes should contain a sample and/or bin and contig id.
+### Processes should publish process specific files
 
-3. Pocesses should publish `.command.sh`, `.command.out`, `.command.log` and `.command.err` files but never `.command.run`.
+Processes should publish `.command.sh`, `.command.out`, `.command.log` and `.command.err` files but never `.command.run`.
 In cases where processes process different data but publish it to the same folder these files would be overwritten on every run.
 For example when Prokka publishes log files of every genome to the same sample directory.
 For that reason these files need to be renamed, so that their names include a unique id (e.g. bin id). 
@@ -95,11 +96,11 @@ tuple env(FILE_ID), val("${output}"), val(params.LOG_LEVELS.INFO), file(".comman
 
 Examples can be viewed in the Checkm and Prokka process.
 
-## Logs
+#### Logs
 
 Log files should be stored in the user provided `logDir` directory.
 
-### Log Level
+##### Log Level
 
 Every configuration file must have a `logLevel` attribute that can have the following values:
 
@@ -124,7 +125,19 @@ tuple env(FILE_ID), val("${output}"), val(params.LOG_LEVELS.INFO), file(".comman
         file(".command.out"), file(".command.err"), file(".command.log"), emit: logs
 ```
 
-4. Custom error strategies that do not follow the strategy defined in nextflow.config, should be documented (see Megahit example).
+### Time Limit
+
+Every process must define a time limit which will never be reached on "normal" execution. This limit is only useful for errors in the execution environment  
+which could lead to an endless execution of the process.
+
+You can use the setTimeLimit helper method to add a user configurable time limit.
+
+Example:
+
+```
+time Utils.setTimeLimit(params.steps.qc.fastp, params.modules.qc.process.fastp.defaults, params.mediumDefault)
+```
+
 
 ## Databases
 
@@ -145,8 +158,10 @@ steps:
     parameter: 42
     processName:
       additionalParams: " --super-flag "
+      timeLimit: "AUTO"
 ```
 
+Please check the process chapter regarding possible values for the time limit attribute.
 Additional params can have a string value (like the example above) that is provided to the tool:
 
 ```JAVA

example_params/fullPipeline.yml

@@ -15,13 +15,13 @@ steps:
     fastp:
        # Example params: " --cut_front --cut_tail --detect_adapter_for_pe  "
        additionalParams: "  "
+       timeLimit: "AUTO"
     nonpareil:
        additionalParams: " -v 10 -r 1234 "
     jellyfish:
        additionalParams: 
          count: " -m 21 -s 100M "
          histo: " "
-
   assembly:
     megahit:
       additionalParams: " --min-contig-len 200 "

example_params/fullPipelineQC.yml

@@ -16,6 +16,7 @@ steps:
       download:
         s5cmdParams: " --retry-count 30 --no-verify-ssl --no-sign-request --endpoint-url https://openstack.cebitec.uni-bielefeld.de:8080 "
       additionalParams: " "
+      timeLimit: "AUTO"
 resources:
   large:
     cpus: 28

example_params/fullPipelineSRAQC.yml

@@ -17,4 +17,5 @@ steps:
       download:
         s5cmdParams: " --retry-count 30 --no-verify-ssl --no-sign-request --endpoint-url https://openstack.cebitec.uni-bielefeld.de:8080 "
       additionalParams: " "
+      timeLimit: "AUTO"
 

example_params/fullPipeline_fraction/fullPipeline_fraction_binning_metabinner.yml

@@ -15,6 +15,7 @@ steps:
     fastp:
        # Example params: " --cut_front --cut_tail --detect_adapter_for_pe  "
        additionalParams: "  "
+       timeLimit: "AUTO"
   assembly:
     megahit:
       additionalParams: " --min-contig-len 200 "

example_params/fullPipeline_fraction/fullPipeline_fraction_magAttributes.yml

@@ -15,6 +15,7 @@ steps:
     fastp:
        # Example params: " --cut_front --cut_tail --detect_adapter_for_pe  "
        additionalParams: "  "
+       timeLimit: "AUTO"
   assembly:
     megahit:
       additionalParams: " --min-contig-len 200 "

example_params/fullPipeline_fraction/fullPipeline_fraction_plasmid.yml

@@ -15,6 +15,7 @@ steps:
     fastp:
        # Example params: " --cut_front --cut_tail --detect_adapter_for_pe  "
        additionalParams: "  "
+       timeLimit: "AUTO"
   assembly:
     megahit:
       fastg: false

lib/Utils.groovy

@@ -36,4 +36,34 @@ class Utils {
           module.version.patch
   }
 
+  /*
+   * This function sets a time limit based on a user provided mode and the resource defaults
+   * that are usually consumed by the process.
+   * 
+   * Input:
+   * process: Defines the user provided timeLimit mode.
+   * processDefaults: Defines default resource values (cpus, RAM, etc.).
+   * flavor: Defines the user provided flavor for the process. 
+  */
+  static String setTimeLimit(process, processDefaults, flavor){
+    def timeUnit = "h"
+    switch(process.timeLimit){
+      case "DISABLED":
+        return "";
+      case "AUTO":
+        def defaultCPUs = processDefaults.flavor.cpus
+        if(defaultCPUs > flavor.cpus){
+          def timeLimit = defaultCPUs/flavor.cpus * processDefaults.time;
+          return timeLimit + timeUnit;
+        } else {
+          return processDefaults.time + timeUnit;
+        }
+      default:
+        if(process.timeLimit instanceof Number){
+          return process.timeLimit + timeUnit;
+        } else {
+          System.out.println("WARNING: unknown time limit parameter specified!");
+        }
+    }
+  }
 }

modules/qualityControl/module.nf

@@ -8,18 +8,21 @@ def getOutput(SAMPLE, RUNID, TOOL, filename){
            '/' + TOOL + '/' + filename
 }
 
+
 process pFastpSplit {
 
     label 'medium'
 
-    tag "$sample"
+    tag "Sample: $sample"
 
     publishDir params.output, saveAs: { filename -> getOutput("${sample}", params.runid, "fastp", filename) }
 
     when params?.steps?.qc.containsKey("fastp")
 
     container "${params.fastp_image}"
 
+    time Utils.setTimeLimit(params.steps.qc.fastp, params.modules.qc.process.fastp.defaults, params.resources.medium)
+
     input:
     tuple val(sample), path(read1, stageAs: "read1.fq.gz"), path(read2, stageAs: "read2.fq.gz")
 
@@ -97,10 +100,12 @@ process pFastpSplitDownload {
 
     label 'medium'
 
-    tag "$sample"
+    tag "Sample: $sample"
 
     publishDir params.output, saveAs: { filename -> getOutput("${sample}", params.runid, "fastp", filename) }
 
+    time Utils.setTimeLimit(params.steps.qc.fastp, params.modules.qc.process.fastpDownload.defaults, params.resources.medium)
+
     when params?.steps?.qc.containsKey("fastp")
 
     container "${params.fastp_image}"

nextflow.config

@@ -35,7 +35,6 @@ defaultResources {
 }
 
 
-
 params {
    polished {
      databases = checkParamsKey(params, "databases", { path -> path.endsWith("/") ? path : path + "/" })
@@ -73,14 +72,12 @@ params {
    PlasClass_image = "quay.io/biocontainers/plasclass:0.1.1--pyhdfd78af_0"
    rgi_image = "quay.io/biocontainers/rgi:5.2.1--pyhdfd78af_1"
    sans_image = "metagenomics/toolkit-sans:0.1.0"
-
-
-   resources = defaultResources
-
+
+   resources = defaultResources 
 
    LOG_LEVELS {
-	ALL = 0
-	INFO = 1
+       ALL = 0
+       INFO = 1
    }
 
    modules {
@@ -107,6 +104,20 @@ params {
                 minor = 3
                 patch = 0
          }
+         process {
+            fastp {
+               defaults {
+                 time = 6
+                 flavor = defaultResources.medium
+               }
+            }
+            fastpDownload {
+               defaults {
+                 time = 12
+                 flavor = defaultResources.medium
+               }
+            }
+         }
       }
       assembly {
          name = "assembly"