From 238d6e5e96b81f5b644257424660ea30b4ecd254 Mon Sep 17 00:00:00 2001 From: ameynert Date: Fri, 23 Jul 2021 09:33:02 +0100 Subject: [PATCH 1/9] Added cacheDir to singularity in eddie profile --- conf/eddie.config | 1 + 1 file changed, 1 insertion(+) diff --git a/conf/eddie.config b/conf/eddie.config index 7f7e2e2..0785858 100644 --- a/conf/eddie.config +++ b/conf/eddie.config @@ -46,5 +46,6 @@ singularity { runOptions = '-p -B "$TMPDIR"' enabled = true autoMounts = true + cacheDir = "/exports/igmm/eddie/BioinformaticsResources/nf-core/singularity-images" } From 26183d988339b03d224af7037e1d58aeea3a355b Mon Sep 17 00:00:00 2001 From: ameynert Date: Fri, 23 Jul 2021 09:35:15 +0100 Subject: [PATCH 2/9] Updated eddie documentation for singularity cache directory --- docs/eddie.md | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/docs/eddie.md b/docs/eddie.md index 485e20a..e35f65a 100644 --- a/docs/eddie.md +++ b/docs/eddie.md @@ -35,16 +35,17 @@ This config enables Nextflow to manage the pipeline jobs via the SGE job schedul ## Singularity set-up -Load Singularity from the module system and, if you have access to `/exports/igmm/eddie/BioinformaticsResources`, set the Singularity cache directory to the BioinformaticsResources path below. If some containers for your pipeline run are not present, please contact the [IGC Data Manager](data.manager@igc.ed.ac.uk) to have them added. You can add these lines to the file `$HOME/.bashrc`, or you can run these commands before you run an nf-core pipeline. - -If you do not have access to `/exports/igmm/eddie/BioinformaticsResources`, set the Singularity cache directory to somewhere sensible that is not in your `$HOME` area (which has limited space). It will take time to download all the Singularity containers, but you can use this again. +Load Singularity from the module system. ```bash module load singularity -export NXF_SINGULARITY_CACHEDIR="/exports/igmm/eddie/BioinformaticsResources/nf-core/singularity-images" ``` -Singularity will create a directory `.singularity` in your `$HOME` directory on eddie. Space on `$HOME` is very limited, so it is a good idea to create a directory somewhere else with more room and link the locations. +The eddie profile is set to use `/exports/igmm/eddie/BioinformaticsResources/nf-core/singularity-images` as the Singularity cache directory. If some containers for your pipeline run are not present, please contact the [IGC Data Manager](data.manager@igc.ed.ac.uk) to have them added. You can add these lines to the file `$HOME/.bashrc`, or you can run these commands before you run an nf-core pipeline. + +If you do not have access to `/exports/igmm/eddie/BioinformaticsResources`, set the Singularity cache directory to somewhere sensible that is not in your `$HOME` area (which has limited space). It will take time to download all the Singularity containers, but you can use this again. + +Singularity will by default create a directory `.singularity` in your `$HOME` directory on eddie. Space on `$HOME` is very limited, so it is a good idea to create a directory somewhere else with more room and link the locations. ```bash cd $HOME From 3bfaf65450d3e564d880d817ce129390f72255bb Mon Sep 17 00:00:00 2001 From: ameynert Date: Fri, 23 Jul 2021 09:39:32 +0100 Subject: [PATCH 3/9] Fixed trailing space --- docs/eddie.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/eddie.md b/docs/eddie.md index e35f65a..15ed728 100644 --- a/docs/eddie.md +++ b/docs/eddie.md @@ -35,7 +35,7 @@ This config enables Nextflow to manage the pipeline jobs via the SGE job schedul ## Singularity set-up -Load Singularity from the module system. +Load Singularity from the module system. ```bash module load singularity From 5c56e13747fa938ffa647a50ab66546561ed25f6 Mon Sep 17 00:00:00 2001 From: ameynert Date: Fri, 23 Jul 2021 10:18:02 +0100 Subject: [PATCH 4/9] Fix typo --- docs/eddie.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/eddie.md b/docs/eddie.md index 15ed728..3ee21cc 100644 --- a/docs/eddie.md +++ b/docs/eddie.md @@ -41,7 +41,7 @@ Load Singularity from the module system. module load singularity ``` -The eddie profile is set to use `/exports/igmm/eddie/BioinformaticsResources/nf-core/singularity-images` as the Singularity cache directory. If some containers for your pipeline run are not present, please contact the [IGC Data Manager](data.manager@igc.ed.ac.uk) to have them added. You can add these lines to the file `$HOME/.bashrc`, or you can run these commands before you run an nf-core pipeline. +The eddie profile is set to use `/exports/igmm/eddie/BioinformaticsResources/nfcore/singularity-images` as the Singularity cache directory. If some containers for your pipeline run are not present, please contact the [IGC Data Manager](data.manager@igc.ed.ac.uk) to have them added. You can add these lines to the file `$HOME/.bashrc`, or you can run these commands before you run an nf-core pipeline. If you do not have access to `/exports/igmm/eddie/BioinformaticsResources`, set the Singularity cache directory to somewhere sensible that is not in your `$HOME` area (which has limited space). It will take time to download all the Singularity containers, but you can use this again. From 937538d160827365a113ed3c9d16e670a33f1e3d Mon Sep 17 00:00:00 2001 From: ameynert Date: Fri, 23 Jul 2021 10:18:24 +0100 Subject: [PATCH 5/9] Fix typo in file path --- conf/eddie.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/conf/eddie.config b/conf/eddie.config index 0785858..ccef445 100644 --- a/conf/eddie.config +++ b/conf/eddie.config @@ -46,6 +46,6 @@ singularity { runOptions = '-p -B "$TMPDIR"' enabled = true autoMounts = true - cacheDir = "/exports/igmm/eddie/BioinformaticsResources/nf-core/singularity-images" + cacheDir = "/exports/igmm/eddie/BioinformaticsResources/nfcore/singularity-images" } From 29a0b30d85b65181a3fa330da7c7755755c34993 Mon Sep 17 00:00:00 2001 From: ameynert Date: Wed, 7 Sep 2022 16:00:52 +0100 Subject: [PATCH 6/9] Updated process names to Sarek 3 --- conf/pipeline/sarek/eddie.config | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/conf/pipeline/sarek/eddie.config b/conf/pipeline/sarek/eddie.config index 1928a9a..01887da 100644 --- a/conf/pipeline/sarek/eddie.config +++ b/conf/pipeline/sarek/eddie.config @@ -1,53 +1,53 @@ process { - withName:MapReads { + withName:BWAMEM_MEM { cpus = 16 memory = 128.GB clusterOptions = {"-l h_vmem=${(task.memory + 8.GB).bytes/task.cpus}"} } - withName:BuildDict { + withName:GATK4_CREATESEQUENCEDICTIONARY { cpus = 1 clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:BamQC { + withName:QUALIMAP_BAMQC { cpus = 8 memory = 128.GB clusterOptions = {"-l h_vmem=${(task.memory + 8.GB).bytes/task.cpus}"} } - withName:MarkDuplicates { + withName:GATK4_MARKDUPLICATES { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:BaseRecalibrator { + withName:BASERECALIBRATOR { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:ApplyBQSR { + withName:APPLYBQSR { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:GatherBQSRReports { + withName:GATHERBQSRREPORTS { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:HaplotypeCaller { + withName:GATK4_HAPLOTYPECALLER { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:GenotypeGVCFs { + withName:GATK4_GENOTYPEGVCFS { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:Mutect2 { + withName:MUTECT2 { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:MergeMutect2Stats { + withName:MERGEMUTECTSTATS { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:PileupSummariesForMutect2 { + withName:GETPILEUPSUMMARIES { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:MergePileupSummaries { + withName:GATHERPILEUPSUMMARIES { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:CalculateContamination { + withName:CALCULATECONTAMINATION { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:FilterMutect2Calls { + withName:FILTERMUTECTCALLS { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } } From a808933da81f29bd7d4df0998987af1a341c5fbd Mon Sep 17 00:00:00 2001 From: ameynert Date: Fri, 9 Sep 2022 08:37:21 +0100 Subject: [PATCH 7/9] Added another Java process that needs memory overhead --- conf/pipeline/sarek/eddie.config | 3 +++ 1 file changed, 3 insertions(+) diff --git a/conf/pipeline/sarek/eddie.config b/conf/pipeline/sarek/eddie.config index 01887da..3fe02b9 100644 --- a/conf/pipeline/sarek/eddie.config +++ b/conf/pipeline/sarek/eddie.config @@ -9,6 +9,9 @@ process { cpus = 1 clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } + withName:LEARNREADORIENTATIONMODEL { + clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} + } withName:QUALIMAP_BAMQC { cpus = 8 memory = 128.GB From 91ef9a32414d6f1a6d0540197cd391f90b073d07 Mon Sep 17 00:00:00 2001 From: ameynert Date: Tue, 13 Sep 2022 09:27:13 +0100 Subject: [PATCH 8/9] Added another Java process with overhead --- conf/pipeline/sarek/eddie.config | 3 +++ 1 file changed, 3 insertions(+) diff --git a/conf/pipeline/sarek/eddie.config b/conf/pipeline/sarek/eddie.config index 3fe02b9..32c0ec0 100644 --- a/conf/pipeline/sarek/eddie.config +++ b/conf/pipeline/sarek/eddie.config @@ -38,6 +38,9 @@ process { withName:MUTECT2 { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } + withName:MERGE_MUTECT2 { + clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} + } withName:MERGEMUTECTSTATS { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } From 9167e8121476784f4f4cf5a8a4804ea63ceacb9e Mon Sep 17 00:00:00 2001 From: ameynert Date: Wed, 14 Sep 2022 09:07:09 +0100 Subject: [PATCH 9/9] Added other Java processes with memory overhead, sorted alphabetically --- conf/pipeline/sarek/eddie.config | 66 ++++++++++++++++++++------------ 1 file changed, 42 insertions(+), 24 deletions(-) diff --git a/conf/pipeline/sarek/eddie.config b/conf/pipeline/sarek/eddie.config index 32c0ec0..a1f94a7 100644 --- a/conf/pipeline/sarek/eddie.config +++ b/conf/pipeline/sarek/eddie.config @@ -1,59 +1,77 @@ process { - - withName:BWAMEM_MEM { - cpus = 16 - memory = 128.GB - clusterOptions = {"-l h_vmem=${(task.memory + 8.GB).bytes/task.cpus}"} + withName:APPLYBQSR { + clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} + } + withName:APPLYBQSR_SPARK { + clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} + } + withName:GATK4_APPLYVQSR { + clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} + } + withName:GATK4_BASERECALIBRATOR { + clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} + } + withName:GATK4_BASERECALIBRATOR_SPARK { + clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} + } + withName:GATK4_CALCULATECONTAMINATION { + clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} + } + withName:GATK4_CNNSCOREVARIANTS { + clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } withName:GATK4_CREATESEQUENCEDICTIONARY { - cpus = 1 clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:LEARNREADORIENTATIONMODEL { + withName:GATK4_ESTIMATELIBRARYCOMPLEXITY { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:QUALIMAP_BAMQC { - cpus = 8 - memory = 128.GB - clusterOptions = {"-l h_vmem=${(task.memory + 8.GB).bytes/task.cpus}"} + withName:GATK4_FILTERMUTECTCALLS { + clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:GATK4_MARKDUPLICATES { + withName:GATK4_FILTERVARIANTTRANCHES { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:BASERECALIBRATOR { + withName:GATK4_GATHERBQSRREPORTS { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:APPLYBQSR { + withName:GATK4_GATHERPILEUPSUMMARIES { + clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} + } + withName:GATK4_GENOMICSDBIMPORT { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:GATHERBQSRREPORTS { + withName:GATK4_GENOTYPEGVCFS { + clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} + } + withName:GATK4_GETPILEUPSUMMARIES { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } withName:GATK4_HAPLOTYPECALLER { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:GATK4_GENOTYPEGVCFS { + withName:GATK4_INTERVALLISTTOBED { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:MUTECT2 { + withName:GATK4_LEARNREADORIENTATIONMODEL { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:MERGE_MUTECT2 { + withName:GATK4_MARKDUPLICATES { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:MERGEMUTECTSTATS { + withName:GATK4_MARKDUPLICATES_SPARK { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:GETPILEUPSUMMARIES { + withName:GATK4_MERGEMUTECTSTATS { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:GATHERPILEUPSUMMARIES { + withName:GATK4_MERGEVCFS { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:CALCULATECONTAMINATION { + withName:GATK4_MUTECT2 { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} } - withName:FILTERMUTECTCALLS { + withName:GATK4_VARIANTRECALIBRATOR { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} - } + } }