Shawn McCarney | 9284c30 | 2021-09-02 11:23:04 -0500 | [diff] [blame] | 1 | /** |
| 2 | * Copyright © 2021 IBM Corporation |
| 3 | * |
| 4 | * Licensed under the Apache License, Version 2.0 (the "License"); |
| 5 | * you may not use this file except in compliance with the License. |
| 6 | * You may obtain a copy of the License at |
| 7 | * |
| 8 | * http://www.apache.org/licenses/LICENSE-2.0 |
| 9 | * |
| 10 | * Unless required by applicable law or agreed to in writing, software |
| 11 | * distributed under the License is distributed on an "AS IS" BASIS, |
| 12 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| 13 | * See the License for the specific language governing permissions and |
| 14 | * limitations under the License. |
| 15 | */ |
| 16 | |
| 17 | #include "phase_fault_detection.hpp" |
| 18 | |
| 19 | #include "action_utils.hpp" |
| 20 | #include "chassis.hpp" |
| 21 | #include "device.hpp" |
| 22 | #include "error_logging.hpp" |
| 23 | #include "error_logging_utils.hpp" |
| 24 | #include "exception_utils.hpp" |
| 25 | #include "journal.hpp" |
| 26 | #include "system.hpp" |
| 27 | |
| 28 | #include <exception> |
| 29 | #include <map> |
| 30 | |
| 31 | namespace phosphor::power::regulators |
| 32 | { |
| 33 | |
| 34 | /** |
| 35 | * Maximum number of action errors to write to the journal. |
| 36 | */ |
| 37 | constexpr unsigned short maxActionErrorCount{3}; |
| 38 | |
| 39 | /** |
| 40 | * Number of consecutive phase faults required to log an error. This provides |
| 41 | * "de-glitching" to ignore transient hardware problems. |
| 42 | */ |
| 43 | constexpr unsigned short requiredConsecutiveFaults{2}; |
| 44 | |
| 45 | void PhaseFaultDetection::execute(Services& services, System& system, |
| 46 | Chassis& /*chassis*/, Device& regulator) |
| 47 | { |
| 48 | try |
| 49 | { |
| 50 | // Find the device ID to use. If the deviceID data member is empty, use |
| 51 | // the ID of the specified regulator. |
| 52 | const std::string& effectiveDeviceID = |
| 53 | deviceID.empty() ? regulator.getID() : deviceID; |
| 54 | |
| 55 | // Create ActionEnvironment |
| 56 | ActionEnvironment environment{system.getIDMap(), effectiveDeviceID, |
| 57 | services}; |
| 58 | |
| 59 | // Execute the actions to detect phase faults |
| 60 | action_utils::execute(actions, environment); |
| 61 | |
| 62 | // Check for any N or N+1 phase faults that were detected |
| 63 | checkForPhaseFault(PhaseFaultType::n, services, regulator, environment); |
| 64 | checkForPhaseFault(PhaseFaultType::n_plus_1, services, regulator, |
| 65 | environment); |
| 66 | } |
| 67 | catch (const std::exception& e) |
| 68 | { |
| 69 | // Log error messages in journal if we haven't hit the max |
| 70 | if (actionErrorCount < maxActionErrorCount) |
| 71 | { |
| 72 | ++actionErrorCount; |
| 73 | services.getJournal().logError(exception_utils::getMessages(e)); |
| 74 | services.getJournal().logError( |
| 75 | "Unable to detect phase faults in regulator " + |
| 76 | regulator.getID()); |
| 77 | } |
| 78 | |
| 79 | // Create error log entry if this type hasn't already been logged |
| 80 | error_logging_utils::logError(std::current_exception(), |
| 81 | Entry::Level::Warning, services, |
| 82 | errorHistory); |
| 83 | } |
| 84 | } |
| 85 | |
| 86 | void PhaseFaultDetection::checkForPhaseFault(PhaseFaultType faultType, |
| 87 | Services& services, |
| 88 | Device& regulator, |
| 89 | ActionEnvironment& environment) |
| 90 | { |
| 91 | // Find ErrorType that corresponds to PhaseFaultType; used by ErrorHistory |
| 92 | ErrorType errorType = toErrorType(faultType); |
| 93 | |
| 94 | // If this error has not been logged yet |
| 95 | if (!errorHistory.wasLogged(errorType)) |
| 96 | { |
| 97 | // Create reference to consecutive fault count data member |
| 98 | unsigned short& faultCount = |
| 99 | (faultType == PhaseFaultType::n) ? nFaultCount : nPlus1FaultCount; |
| 100 | |
| 101 | // Check if the phase fault was detected |
| 102 | if (environment.getPhaseFaults().count(faultType) == 0) |
| 103 | { |
| 104 | // Phase fault not detected; reset consecutive fault count |
| 105 | faultCount = 0; |
| 106 | } |
| 107 | else |
| 108 | { |
| 109 | // Phase fault detected; increment consecutive fault count |
| 110 | ++faultCount; |
| 111 | |
| 112 | // Log error message in journal |
| 113 | services.getJournal().logError( |
| 114 | toString(faultType) + " phase fault detected in regulator " + |
| 115 | regulator.getID() + ": count=" + std::to_string(faultCount)); |
| 116 | |
| 117 | // If the required number of consecutive faults have been detected |
| 118 | if (faultCount >= requiredConsecutiveFaults) |
| 119 | { |
| 120 | // Log phase fault error and update ErrorHistory |
| 121 | logPhaseFault(faultType, services, regulator, environment); |
| 122 | errorHistory.setWasLogged(errorType, true); |
| 123 | } |
| 124 | } |
| 125 | } |
| 126 | } |
| 127 | |
| 128 | void PhaseFaultDetection::logPhaseFault(PhaseFaultType faultType, |
| 129 | Services& services, Device& regulator, |
| 130 | ActionEnvironment& environment) |
| 131 | { |
| 132 | ErrorLogging& errorLogging = services.getErrorLogging(); |
| 133 | Entry::Level severity = (faultType == PhaseFaultType::n) |
| 134 | ? Entry::Level::Warning |
| 135 | : Entry::Level::Informational; |
| 136 | Journal& journal = services.getJournal(); |
| 137 | const std::string& inventoryPath = regulator.getFRU(); |
| 138 | const std::map<std::string, std::string>& additionalData = |
| 139 | environment.getAdditionalErrorData(); |
| 140 | errorLogging.logPhaseFault(severity, journal, faultType, inventoryPath, |
| 141 | additionalData); |
| 142 | } |
| 143 | |
| 144 | } // namespace phosphor::power::regulators |