Skip to content
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

Jump to bottom

DM-38307: Enable simpler yaml when no output collection. #135

Merged
merged 1 commit into from
Apr 6, 2023
Merged

DM-38307: Enable simpler yaml when no output collection. #135

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
2 changes: 2 additions & 0 deletions doc/changes/DM-38307.misc.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
Modify some default yaml values to more easily allow parts to be
modified, like leaving off the output collection.
16 changes: 10 additions & 6 deletions python/lsst/ctrl/bps/etc/bps_defaults.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,6 @@ initPreCmdOpts: "{defaultPreCmdOpts}"
# for running Quanta
runPreCmdOpts: "{defaultPreCmdOpts}"


# Values defining input dataset as well as collection names of output
payload:
#USER payloadName: pipelines_check # Used in bps report, and default output collection
Expand All @@ -32,12 +31,18 @@ payload:
output: "u/{operator}/{payloadName}"
outputRun: "{output}/{timestamp}"

# Mid-level values, rarely overridden other than by plugins or tools
pipetaskOutput: "-o {output}"
pipetaskInput: "-i {inCollection}"
pipetaskDataQuery: '-d "{dataQuery}"'
fileDistributionEndPoint: "" # Needed by PanDA plugin, must end in / if non-empty string

pipetask:
pipetaskInit:
# Notes: Declaring and chaining now happen within execution butler steps.
# This command no longer needs -o and must have --extend-run.
# Change panda-plugin's config at config/bps_idf.yaml too when changing runQuantumCommand
runQuantumCommand: "${CTRL_MPEXEC_DIR}/bin/pipetask {initPreCmdOpts} run -b {butlerConfig} -i {inCollection} -o {output} --output-run {outputRun} --qgraph {qgraphFile} --qgraph-id {qgraphId} --qgraph-node-id {qgraphNodeId} --clobber-outputs --init-only --extend-run {extraInitOptions}"
runQuantumCommand: "${CTRL_MPEXEC_DIR}/bin/pipetask {initPreCmdOpts} run -b {butlerConfig} {pipetaskInput} {pipetaskOutput} --output-run {outputRun} --qgraph {fileDistributionEndPoint}{qgraphFile} --qgraph-id {qgraphId} --qgraph-node-id {qgraphNodeId} --clobber-outputs --init-only --extend-run {extraInitOptions}"
#OPT myTask:
#OPT requestCpus:
#OPT requestMemory:
Expand All @@ -50,9 +55,8 @@ pipetask:
# Default commands and usage requests for creating QuantumGraph, running Quantum.
# Defaults to using full workflow QuantumGraph instead of per-job QuantumGraphs.
whenSaveJobQgraph: "NEVER"
createQuantumGraph: '${CTRL_MPEXEC_DIR}/bin/pipetask {qgraphPreCmdOpts} qgraph -b {butlerConfig} -i {inCollection} -o {output} --output-run {outputRun} -p {pipelineYaml} -q {qgraphFile} -d "{dataQuery}" {extraQgraphOptions}'
# Change panda-plugin's config at config/bps_idf.yaml too when changing runQuantumCommand
runQuantumCommand: "${CTRL_MPEXEC_DIR}/bin/pipetask {runPreCmdOpts} run -b {butlerConfig} -i {inCollection} -o {output} --output-run {outputRun} --qgraph {qgraphFile} --qgraph-id {qgraphId} --qgraph-node-id {qgraphNodeId} --clobber-outputs --skip-init-writes --extend-run {extraRunQuantumOptions}"
createQuantumGraph: '${CTRL_MPEXEC_DIR}/bin/pipetask {qgraphPreCmdOpts} qgraph -b {butlerConfig} {pipetaskInput} {pipetaskOutput} --output-run {outputRun} -p {pipelineYaml} -q {qgraphFile} {pipetaskDataQuery} {extraQgraphOptions}'
runQuantumCommand: "${CTRL_MPEXEC_DIR}/bin/pipetask {runPreCmdOpts} run -b {butlerConfig} {pipetaskInput} {pipetaskOutput} --output-run {outputRun} --qgraph {fileDistributionEndPoint}{qgraphFile} --qgraph-id {qgraphId} --qgraph-node-id {qgraphNodeId} --clobber-outputs --skip-init-writes --extend-run {extraRunQuantumOptions}"
preemptible: True
requestMemory: 2048
requestCpus: 1
Expand All @@ -79,7 +83,7 @@ useLazyCommands: True
executionButler:
whenCreate: "SUBMIT"
#OPT executionButlerDir: "/my/exec/butler/dir" # User-provided or defaults to executionButlerTemplate
createCommand: "${CTRL_MPEXEC_DIR}/bin/pipetask qgraph -b {butlerConfig} -i {inCollection} -o {output} --output-run {outputRun} --save-execution-butler {executionButlerDir} -g {qgraphFile}"
createCommand: "${CTRL_MPEXEC_DIR}/bin/pipetask qgraph -b {butlerConfig} {pipetaskInput} {pipetaskOutput} --output-run {outputRun} --save-execution-butler {executionButlerDir} -g {qgraphFile}"
whenMerge: "ALWAYS"
implementation: JOB # Added for future flexibility, e.g., if prefer workflow instead of shell script.
concurrencyLimit: db_limit
Expand Down