mirror of
https://github.com/kubernetes/node-problem-detector.git
synced 2026-08-19 12:16:26 +00:00
Ciprian Hacman
87dfadb120
config/disk-log-message-filelog.json contained trailing commas and no trailing newline, so it could not be parsed by encoding/json and NPD would fail to start when configured with it. - Fix the invalid JSON - Add TestShippedConfigs, which verifies that every shipped JSON config under config/ (top level and one directory down) parses (catching trailing commas, UTF-8 BOMs and other syntax errors) and is in the canonical format (2-space indent, trailing newline), showing a diff on failure - Add `make fmt-configs` to rewrite nonconforming files in place (UPDATE_EXPECTED=y) - Normalize the existing config files to the canonical format (whitespace-only changes)
101 lines
2.6 KiB
JSON
101 lines
2.6 KiB
JSON
{
|
|
"plugin": "kmsg",
|
|
"logPath": "/dev/kmsg",
|
|
"lookback": "5m",
|
|
"bufferSize": 10,
|
|
"source": "kernel-monitor",
|
|
"metricsReporting": true,
|
|
"conditions": [
|
|
{
|
|
"type": "KernelDeadlock",
|
|
"reason": "KernelHasNoDeadlock",
|
|
"message": "kernel has no deadlock"
|
|
},
|
|
{
|
|
"type": "XfsShutdown",
|
|
"reason": "XfsHasNotShutDown",
|
|
"message": "XFS has not shutdown"
|
|
},
|
|
{
|
|
"type": "CperHardwareErrorFatal",
|
|
"reason": "CperHardwareHasNoFatalError",
|
|
"message": "UEFI CPER has no fatal error"
|
|
}
|
|
],
|
|
"rules": [
|
|
{
|
|
"type": "temporary",
|
|
"reason": "OOMKilling",
|
|
"pattern": "Killed process \\d+ (.+) total-vm:\\d+kB, anon-rss:\\d+kB, file-rss:\\d+kB.*"
|
|
},
|
|
{
|
|
"type": "temporary",
|
|
"reason": "TaskHung",
|
|
"pattern": "task [\\S ]+:\\w+ blocked for more than \\w+ seconds\\."
|
|
},
|
|
{
|
|
"type": "temporary",
|
|
"reason": "UnregisterNetDevice",
|
|
"pattern": "unregister_netdevice: waiting for \\w+ to become free. Usage count = \\d+"
|
|
},
|
|
{
|
|
"type": "temporary",
|
|
"reason": "KernelOops",
|
|
"pattern": "BUG: unable to handle kernel NULL pointer dereference at .*"
|
|
},
|
|
{
|
|
"type": "temporary",
|
|
"reason": "KernelOops",
|
|
"pattern": "divide error: 0000 \\[#\\d+\\] SMP"
|
|
},
|
|
{
|
|
"type": "temporary",
|
|
"reason": "Ext4Error",
|
|
"pattern": "EXT4-fs error .*"
|
|
},
|
|
{
|
|
"type": "temporary",
|
|
"reason": "Ext4Warning",
|
|
"pattern": "EXT4-fs warning .*"
|
|
},
|
|
{
|
|
"type": "temporary",
|
|
"reason": "IOError",
|
|
"pattern": "Buffer I/O error .*"
|
|
},
|
|
{
|
|
"type": "permanent",
|
|
"condition": "XfsShutdown",
|
|
"reason": "XfsHasShutdown",
|
|
"pattern": "XFS .* Shutting down filesystem.?"
|
|
},
|
|
{
|
|
"type": "temporary",
|
|
"reason": "MemoryReadError",
|
|
"pattern": "CE memory read error .*"
|
|
},
|
|
{
|
|
"type": "temporary",
|
|
"reason": "CperHardwareErrorCorrected",
|
|
"pattern": ".*\\[Hardware Error\\]: event severity: corrected$"
|
|
},
|
|
{
|
|
"type": "temporary",
|
|
"reason": "CperHardwareErrorRecoverable",
|
|
"pattern": ".*\\[Hardware Error\\]: event severity: recoverable$"
|
|
},
|
|
{
|
|
"type": "permanent",
|
|
"condition": "CperHardwareErrorFatal",
|
|
"reason": "CperHardwareErrorFatal",
|
|
"pattern": ".*\\[Hardware Error\\]: event severity: fatal$"
|
|
},
|
|
{
|
|
"type": "permanent",
|
|
"condition": "KernelDeadlock",
|
|
"reason": "DockerHung",
|
|
"pattern": "task docker:\\w+ blocked for more than \\w+ seconds\\."
|
|
}
|
|
]
|
|
}
|