Coverage for python/lsst/ctrl/mpexec/reports.py: 81%

63 statements  

« prev     ^ index     » next       coverage.py v7.4.3, created at 2024-03-01 12:48 +0000

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 software is dual licensed under the GNU General Public License and also 

10# under a 3-clause BSD license. Recipients may choose which of these licenses 

11# to use; please see the files gpl-3.0.txt and/or bsd_license.txt, 

12# respectively. If you choose the GPL option then the following text applies 

13# (but note that there is still no warranty even if you opt for BSD instead): 

14# 

15# This program is free software: you can redistribute it and/or modify 

16# it under the terms of the GNU General Public License as published by 

17# the Free Software Foundation, either version 3 of the License, or 

18# (at your option) any later version. 

19# 

20# This program is distributed in the hope that it will be useful, 

21# but WITHOUT ANY WARRANTY; without even the implied warranty of 

22# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 

23# GNU General Public License for more details. 

24# 

25# You should have received a copy of the GNU General Public License 

26# along with this program. If not, see <http://www.gnu.org/licenses/>. 

27 

28from __future__ import annotations 

29 

30__all__ = ["ExceptionInfo", "ExecutionStatus", "Report", "QuantumReport"] 

31 

32import enum 

33import sys 

34from typing import Any 

35 

36import pydantic 

37from lsst.daf.butler import DataCoordinate, DataId, DataIdValue 

38from lsst.utils.introspection import get_full_type_name 

39 

40 

41def _serializeDataId(dataId: DataId) -> dict[str, DataIdValue]: 

42 if isinstance(dataId, DataCoordinate): 

43 return dict(dataId.required) 

44 else: 

45 return dataId # type: ignore 

46 

47 

48class ExecutionStatus(enum.Enum): 

49 """Possible values for job execution status. 

50 

51 Status `FAILURE` is set if one or more tasks failed. Status `TIMEOUT` is 

52 set if there are no failures but one or more tasks timed out. Timeouts can 

53 only be detected in multi-process mode, child task is killed on timeout 

54 and usually should have non-zero exit code. 

55 """ 

56 

57 SUCCESS = "success" 

58 FAILURE = "failure" 

59 TIMEOUT = "timeout" 

60 SKIPPED = "skipped" 

61 

62 

63class ExceptionInfo(pydantic.BaseModel): 

64 """Information about exception.""" 

65 

66 className: str 

67 """Name of the exception class if exception was raised.""" 

68 

69 message: str 

70 """Exception message for in-process quantum execution, None if 

71 quantum was executed in sub-process. 

72 """ 

73 

74 @classmethod 

75 def from_exception(cls, exception: Exception) -> ExceptionInfo: 

76 """Construct instance from an exception. 

77 

78 Parameters 

79 ---------- 

80 exception : `Exception` 

81 Exception to wrap. 

82 

83 Returns 

84 ------- 

85 info : `ExceptionInfo` 

86 Information about the exception. 

87 """ 

88 return cls(className=get_full_type_name(exception), message=str(exception)) 

89 

90 

91class QuantumReport(pydantic.BaseModel): 

92 """Task execution report for a single Quantum. 

93 

94 Parameters 

95 ---------- 

96 dataId : `~lsst.daf.butler.DataId` 

97 Quantum data ID. 

98 taskLabel : `str` 

99 Label for task executing this Quantum. 

100 status : `ExecutionStatus` 

101 Status of this quantum execution. 

102 exitCode : `int` or `None`, optional 

103 Exit code for sub-process executing this Quantum. `None` for 

104 in-process execution. Negative if process was killed by a signal. 

105 exceptionInfo : `ExceptionInfo` or `None`, optional 

106 Exception information if an exception was raised. 

107 """ 

108 

109 status: ExecutionStatus = ExecutionStatus.SUCCESS 

110 """Execution status, one of the values in `ExecutionStatus` enum.""" 

111 

112 dataId: dict[str, DataIdValue] 

113 """Quantum DataId.""" 

114 

115 taskLabel: str | None 

116 """Label for a task executing this Quantum.""" 

117 

118 exitCode: int | None = None 

119 """Exit code for a sub-process executing Quantum, None for in-process 

120 Quantum execution. Negative if process was killed by a signal. 

121 """ 

122 

123 exceptionInfo: ExceptionInfo | None = None 

124 """Exception information if exception was raised.""" 

125 

126 def __init__( 

127 self, 

128 dataId: DataId, 

129 taskLabel: str, 

130 status: ExecutionStatus = ExecutionStatus.SUCCESS, 

131 exitCode: int | None = None, 

132 exceptionInfo: ExceptionInfo | None = None, 

133 ): 

134 super().__init__( 

135 status=status, 

136 dataId=_serializeDataId(dataId), 

137 taskLabel=taskLabel, 

138 exitCode=exitCode, 

139 exceptionInfo=exceptionInfo, 

140 ) 

141 

142 @classmethod 

143 def from_exception( 

144 cls, 

145 exception: Exception, 

146 dataId: DataId, 

147 taskLabel: str, 

148 ) -> QuantumReport: 

149 """Construct report instance from an exception and other pieces of 

150 data. 

151 

152 Parameters 

153 ---------- 

154 exception : `Exception` 

155 Exception caught from processing quantum. 

156 dataId : `~lsst.daf.butler.DataId` 

157 Data ID of quantum. 

158 taskLabel : `str` 

159 Label of task. 

160 """ 

161 return cls( 

162 status=ExecutionStatus.FAILURE, 

163 dataId=dataId, 

164 taskLabel=taskLabel, 

165 exceptionInfo=ExceptionInfo.from_exception(exception), 

166 ) 

167 

168 @classmethod 

169 def from_exit_code( 

170 cls, 

171 exitCode: int, 

172 dataId: DataId, 

173 taskLabel: str, 

174 ) -> QuantumReport: 

175 """Construct report instance from an exit code and other pieces of 

176 data. 

177 

178 Parameters 

179 ---------- 

180 exitCode : `int` 

181 The exit code of the subprocess. 

182 dataId : `~lsst.daf.butler.DataId` 

183 The quantum Data ID. 

184 taskLabel : `str` 

185 The task label. 

186 """ 

187 return cls( 

188 status=ExecutionStatus.SUCCESS if exitCode == 0 else ExecutionStatus.FAILURE, 

189 dataId=dataId, 

190 taskLabel=taskLabel, 

191 exitCode=exitCode, 

192 ) 

193 

194 

195class Report(pydantic.BaseModel): 

196 """Execution report for the whole job with one or few quanta.""" 

197 

198 status: ExecutionStatus = ExecutionStatus.SUCCESS 

199 """Job status.""" 

200 

201 cmdLine: list[str] | None = None 

202 """Command line for the whole job.""" 

203 

204 exitCode: int | None = None 

205 """Job exit code, this obviously cannot be set in pipetask.""" 

206 

207 exceptionInfo: ExceptionInfo | None = None 

208 """Exception information if exception was raised.""" 

209 

210 quantaReports: list[QuantumReport] = [] 

211 """List of per-quantum reports, ordering is not specified. Some or all 

212 quanta may not produce a report. 

213 """ 

214 

215 # Always want to validate the default value for cmdLine so 

216 # use a model_validator. 

217 @pydantic.model_validator(mode="before") 

218 @classmethod 

219 def _set_cmdLine(cls, data: Any) -> Any: 

220 if data.get("cmdLine") is None: 

221 data["cmdLine"] = sys.argv 

222 return data 

223 

224 def set_exception(self, exception: Exception) -> None: 

225 """Update exception information from an exception object. 

226 

227 Parameters 

228 ---------- 

229 exception : `Exception` 

230 Exception to use to extract information from. 

231 """ 

232 self.exceptionInfo = ExceptionInfo.from_exception(exception)