Skip to content

Yoda 168 add error handling for tasks that fail #79

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
SkepticRaven merged 3 commits into from
Sep 5, 2025
Merged

Yoda 168 add error handling for tasks that fail #79

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1fa9108
Adding in ignore condition for unsuccessful tasks
SkepticRaven Jul 28, 2025
7b6b9f9
Merge branch 'main' into YODA-168-add-error-handling-for-tasks-that-fail
SkepticRaven Sep 4, 2025
8b2cde9
Ignoring failures in multimouse too
SkepticRaven Sep 4, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
49 changes: 26 additions & 23 deletions nextflow/configs/profiles/sumner2.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -251,7 +251,7 @@ process {
return r_value + '.sec'
}
array = 200
errorStrategy = 'retry'
errorStrategy = { task.attempt <= 3 ? 'retry' : 'ignore' }
maxRetries = 3
}
withLabel: "r_fboli_predict" {
Expand All @@ -263,7 +263,7 @@ process {
return r_value + '.sec'
}
array = 200
errorStrategy = 'retry'
errorStrategy = { task.attempt <= 3 ? 'retry' : 'ignore' }
maxRetries = 3
}
// Frailty Resources
Expand All @@ -280,7 +280,7 @@ process {
return r_value + '.min'
}
array = 200
errorStrategy = 'retry'
errorStrategy = { task.attempt <= 3 ? 'retry' : 'ignore' }
maxRetries = 3
}
withLabel: "r_rearpaw" {
Expand All @@ -292,7 +292,7 @@ process {
}
time = { 10.min * task.attempt }
array = 200
errorStrategy = 'retry'
errorStrategy = { task.attempt <= 3 ? 'retry' : 'ignore' }
maxRetries = 3
}
// Gait Resources
Expand All @@ -305,7 +305,7 @@ process {
}
time = { 10.min * task.attempt }
array = 200
errorStrategy = 'retry'
errorStrategy = { task.attempt <= 3 ? 'retry' : 'ignore' }
maxRetries = 3
}
withLabel: "r_gait_bin" {
Expand All @@ -317,7 +317,7 @@ process {
}
time = { 5.min * task.attempt }
array = 200
errorStrategy = 'retry'
errorStrategy = { task.attempt <= 3 ? 'retry' : 'ignore' }
maxRetries = 3
}
// JABS Resources
Expand All @@ -337,7 +337,7 @@ process {
return r_value + '.sec'
}
array = 200
errorStrategy = 'retry'
errorStrategy = { task.attempt <= 3 ? 'retry' : 'ignore' }
maxRetries = 3
}
withLabel: "r_jabs_classify" {
Expand All @@ -355,15 +355,15 @@ process {
return r_value + '.sec'
}
array = 200
errorStrategy = 'retry'
errorStrategy = { task.attempt <= 3 ? 'retry' : 'ignore' }
maxRetries = 3
}
withLabel: "r_jabs_tablegen" {
cpus = 1
memory = { 1.GB * task.attempt }
time = { 5.min * task.attempt }
array = 200
errorStrategy = 'retry'
errorStrategy = { task.attempt <= 3 ? 'retry' : 'ignore' }
maxRetries = 3
}
withLabel: "r_jabs_heuristic" {
Expand All @@ -377,7 +377,7 @@ process {
return r_value + '.sec'
}
array = 200
errorStrategy = 'retry'
errorStrategy = { task.attempt <= 3 ? 'retry' : 'ignore' }
maxRetries = 3
}
withLabel: "r_jabs_table_convert" {
Expand All @@ -387,7 +387,7 @@ process {
// High value in experiments was 1-minute for a 1-hr video
time = { 20.min * task.attempt }
array = 200
errorStrategy = 'retry'
errorStrategy = { task.attempt <= 3 ? 'retry' : 'ignore' }
maxRetries = 3
}
// Single Mouse Resources
Expand All @@ -407,7 +407,7 @@ process {
return r_value + '.sec'
}
array = 200
errorStrategy = 'retry'
errorStrategy = { task.attempt <= 3 ? 'retry' : 'ignore' }
maxRetries = 3
}
withLabel: "r_single_keypoints" {
Expand All @@ -418,15 +418,15 @@ process {
memory = { 64.GB * task.attempt }
time = { 6.hours * task.attempt }
array = 200
errorStrategy = 'retry'
errorStrategy = { task.attempt <= 3 ? 'retry' : 'ignore' }
maxRetries = 3
}
withLabel: "r_single_qc" {
// This task scales with number of videos in the batch, but is still small
cpus = 1
memory = { 4.GB * task.attempt }
time = { 20.min * task.attempt }
errorStrategy = 'retry'
errorStrategy = { task.attempt <= 3 ? 'retry' : 'ignore' }
maxRetries = 3
}
withLabel: "r_clip_video" {
Expand All @@ -442,7 +442,7 @@ process {
return r_value + '.sec'
}
array = 200
errorStrategy = 'retry'
errorStrategy = { task.attempt <= 3 ? 'retry' : 'ignore' }
maxRetries = 3
}
// Multi Mouse Resources
Expand All @@ -456,7 +456,7 @@ process {
}
time = { 5.hours * task.attempt }
array = 200
errorStrategy = 'retry'
errorStrategy = { task.attempt <= 3 ? 'retry' : 'ignore' }
maxRetries = 3
}
withLabel: "r_multi_keypoints" {
Expand All @@ -472,7 +472,7 @@ process {
return r_value + '.hours'
}
array = 200
errorStrategy = 'retry'
errorStrategy = { task.attempt <= 3 ? 'retry' : 'ignore' }
maxRetries = 3
}
withLabel: "r_multi_identity" {
Expand All @@ -484,7 +484,7 @@ process {
return r_value + '.hours'
}
array = 200
errorStrategy = 'retry'
errorStrategy = { task.attempt <= 3 ? 'retry' : 'ignore' }
maxRetries = 3
}
withLabel: "r_multi_tracklets" {
Expand All @@ -493,6 +493,9 @@ process {
// First video suggested ~16GB and ~30min for 3 mice
memory = { 16.GB * task.attempt }
time = { 45.min * task.attempt }
array = 200
errorStrategy = { task.attempt <= 3 ? 'retry' : 'ignore' }
maxRetries = 3
}
// Static Object Resources
// These do not scale with clip duration
Expand All @@ -501,23 +504,23 @@ process {
memory = { 4.GB * task.attempt }
time = { 10.min * task.attempt }
array = 200
errorStrategy = 'retry'
errorStrategy = { task.attempt <= 3 ? 'retry' : 'ignore' }
maxRetries = 3
}
withLabel: "r_food_hopper" {
cpus = 2
memory = { 4.GB * task.attempt }
time = { 10.min * task.attempt }
array = 200
errorStrategy = 'retry'
errorStrategy = { task.attempt <= 3 ? 'retry' : 'ignore' }
maxRetries = 3
}
withLabel: "r_lixit" {
cpus = 2
memory = { 4.GB * task.attempt }
time = { 10.min * task.attempt }
array = 200
errorStrategy = 'retry'
errorStrategy = { task.attempt <= 3 ? 'retry' : 'ignore' }
maxRetries = 3
}
// Utility Resources
Expand All @@ -526,14 +529,14 @@ process {
memory = { 1.GB * task.attempt }
time = { 5.min * task.attempt }
array = 500
errorStrategy = 'retry'
errorStrategy = { task.attempt <= 3 ? 'retry' : 'ignore' }
maxRetries = 3
}
withLabel: "r_gen_vid" {
cpus = 1
memory = { 1.GB * task.attempt }
time = { 1.hours * task.attempt }
errorStrategy = 'retry'
errorStrategy = { task.attempt <= 3 ? 'retry' : 'ignore' }
maxRetries = 3
}
}
Expand Down