From b485aab7e71c1625cfc27e0f92c9509f42378458 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sun, 5 May 2024 13:19:16 +0200 Subject: Adding upstream version 1.45.3+dfsg. Signed-off-by: Daniel Baumann --- src/health/health.d/memory.conf | 76 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 76 insertions(+) create mode 100644 src/health/health.d/memory.conf (limited to 'src/health/health.d/memory.conf') diff --git a/src/health/health.d/memory.conf b/src/health/health.d/memory.conf new file mode 100644 index 000000000..2b2b4e4da --- /dev/null +++ b/src/health/health.d/memory.conf @@ -0,0 +1,76 @@ +# you can disable an alarm notification by setting the 'to' line to: silent + + alarm: 1hour_memory_hw_corrupted + on: mem.hwcorrupt + class: Errors + type: System + component: Memory +host labels: _os=linux + calc: $HardwareCorrupted + units: MB + every: 10s + warn: $this > 0 + delay: down 1h multiplier 1.5 max 1h + summary: System corrupted memory + info: Amount of memory corrupted due to a hardware failure + to: sysadmin + +## ECC Controller + + template: ecc_memory_mc_correctable + on: mem.edac_mc_errors + class: Errors + type: System + component: Memory +host labels: _os=linux + calc: $correctable + $correctable_noinfo + units: errors + every: 1m + warn: $this > 0 + summary: System ECC memory ${label:controller} correctable errors + info: Memory controller ${label:controller} ECC correctable errors + to: sysadmin + + template: ecc_memory_mc_uncorrectable + on: mem.edac_mc_errors + class: Errors + type: System + component: Memory +host labels: _os=linux + calc: $uncorrectable + $uncorrectable_noinfo + units: errors + every: 1m + crit: $this > 0 + summary: System ECC memory ${label:controller} uncorrectable errors + info: Memory controller ${label:controller} ECC uncorrectable errors + to: sysadmin + +## ECC DIMM + + template: ecc_memory_dimm_correctable + on: mem.edac_mc_dimm_errors + class: Errors + type: System + component: Memory +host labels: _os=linux + calc: $correctable + units: errors + every: 1m + warn: $this > 0 + summary: System ECC memory DIMM ${label:dimm} correctable errors + info: DIMM ${label:dimm} controller ${label:controller} (location ${label:dimm_location}) ECC correctable errors + to: sysadmin + + template: ecc_memory_dimm_uncorrectable + on: mem.edac_mc_dimm_errors + class: Errors + type: System + component: Memory +host labels: _os=linux + calc: $uncorrectable + units: errors + every: 1m + crit: $this > 0 + summary: System ECC memory DIMM ${label:dimm} uncorrectable errors + info: DIMM ${label:dimm} controller ${label:controller} (location ${label:dimm_location}) ECC uncorrectable errors + to: sysadmin -- cgit v1.2.3