Coverage for python/lsst/ctrl/mpexec/reports.py: 76%

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/>. 

21 

22from __future__ import annotations 

23 

24__all__ = ["ExecutionStatus", "Report", "QuantumReport"] 

25 

26import enum 

27import sys 

28from typing import Dict, List, Optional 

29 

30from lsst.daf.butler import DataCoordinate, DataId, DataIdValue 

31from lsst.utils.introspection import get_full_type_name 

32from pydantic import BaseModel, validator 

33 

34 

35def _serializeDataId(dataId: DataId) -> Dict[str, DataIdValue]: 

36 if isinstance(dataId, DataCoordinate): 

37 return dataId.byName() 

38 else: 

39 return dataId # type: ignore 

40 

41 

42class ExecutionStatus(enum.Enum): 

43 """Possible values for job execution status. 

44 

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

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

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

48 and usually should have non-zero exit code. 

49 """ 

50 

51 SUCCESS = "success" 

52 FAILURE = "failure" 

53 TIMEOUT = "timeout" 

54 SKIPPED = "skipped" 

55 

56 

57class ExceptionInfo(BaseModel): 

58 """Information about exception.""" 

59 

60 className: str 

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

62 

63 message: str 

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

65 quantum was executed in sub-process. 

66 """ 

67 

68 @classmethod 

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

70 """Construct instance from an exception.""" 

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

72 

73 

74class QuantumReport(BaseModel): 

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

76 

77 status: ExecutionStatus = ExecutionStatus.SUCCESS 

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

79 

80 dataId: Dict[str, DataIdValue] 

81 """Quantum DataId.""" 

82 

83 taskLabel: Optional[str] 

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

85 

86 exitCode: Optional[int] = None 

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

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

89 """ 

90 

91 exceptionInfo: Optional[ExceptionInfo] = None 

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

93 

94 def __init__( 

95 self, 

96 dataId: DataId, 

97 taskLabel: str, 

98 status: ExecutionStatus = ExecutionStatus.SUCCESS, 

99 exitCode: Optional[int] = None, 

100 exceptionInfo: Optional[ExceptionInfo] = None, 

101 ): 

102 super().__init__( 

103 status=status, 

104 dataId=_serializeDataId(dataId), 

105 taskLabel=taskLabel, 

106 exitCode=exitCode, 

107 exceptionInfo=exceptionInfo, 

108 ) 

109 

110 @classmethod 

111 def from_exception( 

112 cls, 

113 exception: Exception, 

114 dataId: DataId, 

115 taskLabel: str, 

116 ) -> QuantumReport: 

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

118 data. 

119 """ 

120 return cls( 

121 status=ExecutionStatus.FAILURE, 

122 dataId=dataId, 

123 taskLabel=taskLabel, 

124 exceptionInfo=ExceptionInfo.from_exception(exception), 

125 ) 

126 

127 @classmethod 

128 def from_exit_code( 

129 cls, 

130 exitCode: int, 

131 dataId: DataId, 

132 taskLabel: str, 

133 ) -> QuantumReport: 

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

135 data. 

136 """ 

137 return cls( 

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

139 dataId=dataId, 

140 taskLabel=taskLabel, 

141 exitCode=exitCode, 

142 ) 

143 

144 

145class Report(BaseModel): 

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

147 

148 status: ExecutionStatus = ExecutionStatus.SUCCESS 

149 """Job status.""" 

150 

151 cmdLine: Optional[List[str]] = None 

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

153 

154 exitCode: Optional[int] = None 

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

156 

157 exceptionInfo: Optional[ExceptionInfo] = None 

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

159 

160 quantaReports: List[QuantumReport] = [] 

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

162 quanta may not produce a report. 

163 """ 

164 

165 @validator("cmdLine", always=True) 

166 def _set_cmdLine(cls, v: Optional[List[str]]) -> List[str]: # noqa: N805 

167 if v is None: 

168 v = sys.argv 

169 return v 

170 

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

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

173 self.exceptionInfo = ExceptionInfo.from_exception(exception)