Skip to content

Promoting operational errors to critical severity #13930

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

Merged
ehellbar merged 2 commits into from
Mar 17, 2025
Merged

Promoting operational errors to critical severity #13930

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0a11a79
Promoting critical Error logs to ILG Ops level
ehellbar Feb 3, 2025
d656f3f
Promoting DPL errors relevant to the ECS shifter to critical, leaving…
ehellbar Feb 12, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions Detectors/TPC/workflow/src/IDCToVectorSpec.cxx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -405,7 +405,7 @@ class IDCToVectorDevice : public o2::framework::Task

for (const auto& inf : infVec) {
if (!inf.hasBothEPs()) {
LOGP(error, "IDC CRU {:3}: data missing at ({:8}, {:4}) for one or both end points {:02b} in TF {}", cru, inf.heartbeatOrbit, inf.heartbeatBC, inf.epSeen, tfCounter);
LOGP(critical, "IDC CRU {:3}: data missing at ({:8}, {:4}) for one or both end points {:02b} in TF {}", cru, inf.heartbeatOrbit, inf.heartbeatBC, inf.epSeen, tfCounter);
hasErrors = true;
}
}
Expand All @@ -417,12 +417,12 @@ class IDCToVectorDevice : public o2::framework::Task
}

if (packetsInTF != infVec.size()) {
LOGP(error, "IDC CRU {:3}: number of IDC packets {} does not match max over all CRUs {} in TF {}", cru, packetsInTF, infVec.size(), tfCounter);
LOGP(critical, "IDC CRU {:3}: number of IDC packets {} does not match max over all CRUs {} in TF {}", cru, packetsInTF, infVec.size(), tfCounter);
hasErrors = true;
}

if (!std::equal(infVecComp->begin(), infVecComp->end(), infVec.begin())) {
LOGP(error, "IDC CRU {:3}: mismatch in orbit numbers", cru);
LOGP(critical, "IDC CRU {:3}: mismatch in orbit numbers", cru);
hasErrors = true;
}
}
Expand Down
4 changes: 2 additions & 2 deletions Framework/Core/src/CommonServices.cxx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -579,7 +579,7 @@ auto decongestionCallbackOrdered = [](AsyncTask& task, size_t id) -> void {
if (state.transitionHandling != TransitionHandlingState::NoTransition && DefaultsHelpers::onlineDeploymentMode()) {
O2_SIGNPOST_EVENT_EMIT_WARN(async_queue, cid, "oldest_possible_timeslice", "Stop transition requested. Some Lifetime::Timeframe data got dropped starting at %" PRIi64, oldNextTimeslice);
} else {
O2_SIGNPOST_EVENT_EMIT_ERROR(async_queue, cid, "oldest_possible_timeslice", "Some Lifetime::Timeframe data got dropped starting at %" PRIi64, oldNextTimeslice);
O2_SIGNPOST_EVENT_EMIT_CRITICAL(async_queue, cid, "oldest_possible_timeslice", "Some Lifetime::Timeframe data got dropped starting at %" PRIi64, oldNextTimeslice);
}
timesliceIndex.rescan();
}
Expand Down Expand Up @@ -650,7 +650,7 @@ o2::framework::ServiceSpec
if (state.transitionHandling != TransitionHandlingState::NoTransition && DefaultsHelpers::onlineDeploymentMode()) {
O2_SIGNPOST_EVENT_EMIT_WARN(data_processor_context, cid, "oldest_possible_timeslice", "Stop transition requested. Some Lifetime::Timeframe data got dropped starting at %" PRIi64, oldNextTimeslice);
} else {
O2_SIGNPOST_EVENT_EMIT_ERROR(data_processor_context, cid, "oldest_possible_timeslice", "Some Lifetime::Timeframe data got dropped starting at %" PRIi64, oldNextTimeslice);
O2_SIGNPOST_EVENT_EMIT_CRITICAL(data_processor_context, cid, "oldest_possible_timeslice", "Some Lifetime::Timeframe data got dropped starting at %" PRIi64, oldNextTimeslice);
}
timesliceIndex.rescan();
}
Expand Down
15 changes: 7 additions & 8 deletions Utilities/EPNMonitoring/src/EPNstderrMonitor.cxx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,7 +77,7 @@ class EPNMonitor
std::unordered_map<std::string, fileMon> mFiles;
std::string mPath;
std::vector<std::regex> mFilters;
std::unordered_map<std::string, std::pair<InfoLogger::InfoLogger::Severity, int>> mMapRootLogTypes;
std::unordered_map<std::string, std::pair<InfoLogger::InfoLogger::Severity, int>> mMapLogTypes;
volatile unsigned int mRunNumber;
std::string mPartition;
unsigned int nLines = 0;
Expand All @@ -95,12 +95,11 @@ EPNMonitor::EPNMonitor(std::string path, bool infoLogger, int runNumber, std::st
mFilters.emplace_back("^Warning in <TGraph");
mFilters.emplace_back("^Warning in <TInterpreter");
mFilters.emplace_back("Dividing histograms with different labels");
mMapRootLogTypes.emplace("Info in <", std::pair<InfoLogger::InfoLogger::Severity, int>{InfoLogger::InfoLogger::Severity::Info, 13});
mMapRootLogTypes.emplace("Print in <", std::pair<InfoLogger::InfoLogger::Severity, int>{InfoLogger::InfoLogger::Severity::Info, 13});
mMapRootLogTypes.emplace("Warning in <", std::pair<InfoLogger::InfoLogger::Severity, int>{InfoLogger::InfoLogger::Severity::Warning, 11});
mMapRootLogTypes.emplace("Error in <", std::pair<InfoLogger::InfoLogger::Severity, int>{InfoLogger::InfoLogger::Severity::Error, 2});
mMapRootLogTypes.emplace("Fatal in <", std::pair<InfoLogger::InfoLogger::Severity, int>{InfoLogger::InfoLogger::Severity::Fatal, 1});
mMapRootLogTypes.emplace("*** Break ***", std::pair<InfoLogger::InfoLogger::Severity, int>{InfoLogger::InfoLogger::Severity::Fatal, 1});
mMapLogTypes.emplace("(core dumped)", std::pair<InfoLogger::InfoLogger::Severity, int>{InfoLogger::InfoLogger::Severity::Error, 1});
mMapLogTypes.emplace("Warning in <", std::pair<InfoLogger::InfoLogger::Severity, int>{InfoLogger::InfoLogger::Severity::Warning, 11});
mMapLogTypes.emplace("Error in <", std::pair<InfoLogger::InfoLogger::Severity, int>{InfoLogger::InfoLogger::Severity::Error, 2});
mMapLogTypes.emplace("Fatal in <", std::pair<InfoLogger::InfoLogger::Severity, int>{InfoLogger::InfoLogger::Severity::Fatal, 1});
mMapLogTypes.emplace("*** Break ***", std::pair<InfoLogger::InfoLogger::Severity, int>{InfoLogger::InfoLogger::Severity::Fatal, 1});
mInfoLoggerActive = infoLogger;
mPath = path;
mRunNumber = runNumber;
Expand Down Expand Up @@ -214,7 +213,7 @@ void EPNMonitor::thread()
// assign proper severity / level for remaining ROOT log messages
auto severity{InfoLogger::InfoLogger::Severity::Error};
int level{3};
for (const auto& logType : mMapRootLogTypes) {
for (const auto& logType : mMapLogTypes) {
if (line.find(logType.first) != std::string::npos) {
severity = std::get<InfoLogger::InfoLogger::Severity>(logType.second);
level = std::get<int>(logType.second);
Expand Down