Coverage for python/lsst/ctrl/mpexec/singleQuantumExecutor.py : 13%

Hot-keys on this page
r m x p toggle line displays
j k next/prev highlighted chunk
0 (zero) top of page
1 (one) first highlighted chunk
1# This file is part of ctrl_mpexec.
2#
3# Developed for the LSST Data Management System.
4# This product includes software developed by the LSST Project
5# (http://www.lsst.org).
6# See the COPYRIGHT file at the top-level directory of this distribution
7# for details of code ownership.
8#
9# This program is free software: you can redistribute it and/or modify
10# it under the terms of the GNU General Public License as published by
11# the Free Software Foundation, either version 3 of the License, or
12# (at your option) any later version.
13#
14# This program is distributed in the hope that it will be useful,
15# but WITHOUT ANY WARRANTY; without even the implied warranty of
16# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
17# GNU General Public License for more details.
18#
19# You should have received a copy of the GNU General Public License
20# along with this program. If not, see <http://www.gnu.org/licenses/>.
22__all__ = ['SingleQuantumExecutor']
24# -------------------------------
25# Imports of standard modules --
26# -------------------------------
27import logging
28from itertools import chain
30# -----------------------------
31# Imports for other modules --
32# -----------------------------
33from .quantumGraphExecutor import QuantumExecutor
34from lsst.log import Log
35from lsst.obs.base import Instrument
36from lsst.pipe.base import ButlerQuantumContext
38# ----------------------------------
39# Local non-exported definitions --
40# ----------------------------------
42_LOG = logging.getLogger(__name__.partition(".")[2])
45class SingleQuantumExecutor(QuantumExecutor):
46 """Executor class which runs one Quantum at a time.
48 Parameters
49 ----------
50 butler : `~lsst.daf.butler.Butler`
51 Data butler.
52 taskFactory : `~lsst.pipe.base.TaskFactory`
53 Instance of a task factory.
54 skipExisting : `bool`, optional
55 If True then quanta with all existing outputs are not executed.
56 clobberPartialOutputs : `bool`, optional
57 If True then delete any partial outputs from quantum execution. If
58 complete outputs exists then exception is raise if ``skipExisting`` is
59 False.
60 enableLsstDebug : `bool`, optional
61 Enable debugging with ``lsstDebug`` facility for a task.
62 """
63 def __init__(self, taskFactory, skipExisting=False, clobberPartialOutputs=False, enableLsstDebug=False):
64 self.taskFactory = taskFactory
65 self.skipExisting = skipExisting
66 self.enableLsstDebug = enableLsstDebug
67 self.clobberPartialOutputs = clobberPartialOutputs
69 def execute(self, taskDef, quantum, butler):
70 # Docstring inherited from QuantumExecutor.execute
71 taskClass, config = taskDef.taskClass, taskDef.config
72 self.setupLogging(taskClass, config, quantum)
74 # check whether to skip or delete old outputs
75 if self.checkExistingOutputs(quantum, butler, taskDef):
76 _LOG.info("Quantum execution skipped due to existing outputs, "
77 f"task={taskClass.__name__} dataId={quantum.dataId}.")
78 return
80 self.updateQuantumInputs(quantum, butler)
82 # enable lsstDebug debugging
83 if self.enableLsstDebug:
84 try:
85 _LOG.debug("Will try to import debug.py")
86 import debug # noqa:F401
87 except ImportError:
88 _LOG.warn("No 'debug' module found.")
90 # initialize global state
91 self.initGlobals(quantum, butler)
93 task = self.makeTask(taskClass, config, butler)
94 self.runQuantum(task, quantum, taskDef, butler)
96 def setupLogging(self, taskClass, config, quantum):
97 """Configure logging system for execution of this task.
99 Ths method can setup logging to attach task- or
100 quantum-specific information to log messages. Potentially this can
101 take into accout some info from task configuration as well.
103 Parameters
104 ----------
105 taskClass : `type`
106 Sub-class of `~lsst.pipe.base.PipelineTask`.
107 config : `~lsst.pipe.base.PipelineTaskConfig`
108 Configuration object for this task
109 quantum : `~lsst.daf.butler.Quantum`
110 Single Quantum instance.
111 """
112 # include input dataIds into MDC
113 dataIds = set(ref.dataId for ref in chain.from_iterable(quantum.predictedInputs.values()))
114 if dataIds:
115 if len(dataIds) == 1:
116 Log.MDC("LABEL", str(dataIds.pop()))
117 else:
118 Log.MDC("LABEL", '[' + ', '.join([str(dataId) for dataId in dataIds]) + ']')
120 def checkExistingOutputs(self, quantum, butler, taskDef):
121 """Decide whether this quantum needs to be executed.
123 If only partial outputs exist then they are removed if
124 ``clobberPartialOutputs`` is True, otherwise an exception is raised.
126 Parameters
127 ----------
128 quantum : `~lsst.daf.butler.Quantum`
129 Quantum to check for existing outputs
130 butler : `~lsst.daf.butler.Butler`
131 Data butler.
132 taskDef : `~lsst.pipe.base.TaskDef`
133 Task definition structure.
135 Returns
136 -------
137 exist : `bool`
138 True if all quantum's outputs exist in a collection and
139 ``skipExisting`` is True, False otherwise.
141 Raises
142 ------
143 RuntimeError
144 Raised if some outputs exist and some not.
145 """
146 collection = butler.run
147 registry = butler.registry
149 existingRefs = []
150 missingRefs = []
151 for datasetRefs in quantum.outputs.values():
152 for datasetRef in datasetRefs:
153 ref = registry.findDataset(datasetRef.datasetType, datasetRef.dataId,
154 collections=butler.run)
155 if ref is None:
156 missingRefs.append(datasetRef)
157 else:
158 existingRefs.append(ref)
159 if existingRefs and missingRefs:
160 # some outputs exist and some don't, either delete existing ones or complain
161 _LOG.debug("Partial outputs exist for task %s dataId=%s collection=%s "
162 "existingRefs=%s missingRefs=%s",
163 taskDef, quantum.dataId, collection, existingRefs, missingRefs)
164 if self.clobberPartialOutputs:
165 _LOG.info("Removing partial outputs for task %s: %s", taskDef, existingRefs)
166 butler.pruneDatasets(existingRefs, disassociate=True, unstore=True, purge=True)
167 return False
168 else:
169 raise RuntimeError(f"Registry inconsistency while checking for existing outputs:"
170 f" collection={collection} existingRefs={existingRefs}"
171 f" missingRefs={missingRefs}")
172 elif existingRefs:
173 # complete outputs exist, this is fine only if skipExisting is set
174 return self.skipExisting
175 else:
176 # no outputs exist
177 return False
179 def makeTask(self, taskClass, config, butler):
180 """Make new task instance.
182 Parameters
183 ----------
184 taskClass : `type`
185 Sub-class of `~lsst.pipe.base.PipelineTask`.
186 config : `~lsst.pipe.base.PipelineTaskConfig`
187 Configuration object for this task
189 Returns
190 -------
191 task : `~lsst.pipe.base.PipelineTask`
192 Instance of ``taskClass`` type.
193 butler : `~lsst.daf.butler.Butler`
194 Data butler.
195 """
196 # call task factory for that
197 return self.taskFactory.makeTask(taskClass, config, None, butler)
199 def updateQuantumInputs(self, quantum, butler):
200 """Update quantum with extra information.
202 Some methods may require input DatasetRefs to have non-None
203 ``dataset_id``, but in case of intermediate dataset it may not be
204 filled during QuantumGraph construction. This method will retrieve
205 missing info from registry.
207 Parameters
208 ----------
209 quantum : `~lsst.daf.butler.Quantum`
210 Single Quantum instance.
211 butler : `~lsst.daf.butler.Butler`
212 Data butler.
213 """
214 for refsForDatasetType in quantum.predictedInputs.values():
215 newRefsForDatasetType = []
216 for ref in refsForDatasetType:
217 if ref.id is None:
218 resolvedRef = butler.registry.findDataset(ref.datasetType, ref.dataId,
219 collections=butler.collections)
220 if resolvedRef is None:
221 raise ValueError(
222 f"Cannot find {ref.datasetType.name} with id {ref.dataId} "
223 f"in collections {butler.collections}."
224 )
225 newRefsForDatasetType.append(resolvedRef)
226 _LOG.debug("Updating dataset ID for %s", ref)
227 else:
228 newRefsForDatasetType.append(ref)
229 refsForDatasetType[:] = newRefsForDatasetType
231 def runQuantum(self, task, quantum, taskDef, butler):
232 """Execute task on a single quantum.
234 Parameters
235 ----------
236 task : `~lsst.pipe.base.PipelineTask`
237 Task object.
238 quantum : `~lsst.daf.butler.Quantum`
239 Single Quantum instance.
240 taskDef : `~lsst.pipe.base.TaskDef`
241 Task definition structure.
242 butler : `~lsst.daf.butler.Butler`
243 Data butler.
244 """
245 # Create a butler that operates in the context of a quantum
246 butlerQC = ButlerQuantumContext(butler, quantum)
248 # Get the input and output references for the task
249 connectionInstance = task.config.connections.ConnectionsClass(config=task.config)
250 inputRefs, outputRefs = connectionInstance.buildDatasetRefs(quantum)
252 # Call task runQuantum() method. Any exception thrown by the task
253 # propagates to caller.
254 task.runQuantum(butlerQC, inputRefs, outputRefs)
256 if taskDef.metadataDatasetName is not None:
257 # DatasetRef has to be in the Quantum outputs, can lookup by name
258 try:
259 ref = quantum.outputs[taskDef.metadataDatasetName]
260 except LookupError as exc:
261 raise LookupError(
262 f"Quantum outputs is missing metadata dataset type {taskDef.metadataDatasetName},"
263 f" it could happen due to inconsistent options between Quantum generation"
264 f" and execution") from exc
265 butlerQC.put(task.getFullMetadata(), ref[0])
267 def initGlobals(self, quantum, butler):
268 """Initialize global state needed for task execution.
270 Parameters
271 ----------
272 quantum : `~lsst.daf.butler.Quantum`
273 Single Quantum instance.
274 butler : `~lsst.daf.butler.Butler`
275 Data butler.
277 Notes
278 -----
279 There is an issue with initializing filters singleton which is done
280 by instrument, to avoid requiring tasks to do it in runQuantum()
281 we do it here when any dataId has an instrument dimension. Also for
282 now we only allow single instrument, verify that all instrument
283 names in all dataIds are identical.
285 This will need revision when filter singleton disappears.
286 """
287 oneInstrument = None
288 for datasetRefs in chain(quantum.predictedInputs.values(), quantum.outputs.values()):
289 for datasetRef in datasetRefs:
290 dataId = datasetRef.dataId
291 instrument = dataId.get("instrument")
292 if instrument is not None:
293 if oneInstrument is not None:
294 assert instrument == oneInstrument, \
295 "Currently require that only one instrument is used per graph"
296 else:
297 oneInstrument = instrument
298 Instrument.fromName(instrument, butler.registry)