From a64a253794ac64cb40befee54db53bde17dd0d49 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Wed, 7 Nov 2018 13:19:29 +0100 Subject: New upstream version 1.11.0+dfsg Signed-off-by: Daniel Baumann --- health/health.d/memory.conf | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 health/health.d/memory.conf (limited to 'health/health.d/memory.conf') diff --git a/health/health.d/memory.conf b/health/health.d/memory.conf new file mode 100644 index 000000000..4a0e6e522 --- /dev/null +++ b/health/health.d/memory.conf @@ -0,0 +1,38 @@ + +# you can disable an alarm notification by setting the 'to' line to: silent + + alarm: 1hour_ecc_memory_correctable + on: mem.ecc_ce + os: linux + hosts: * + lookup: sum -10m unaligned + units: errors + every: 1m + warn: $this > 0 + delay: down 1h multiplier 1.5 max 1h + info: number of ECC correctable errors during the last hour + to: sysadmin + + alarm: 1hour_ecc_memory_uncorrectable + on: mem.ecc_ue + os: linux + hosts: * + lookup: sum -10m unaligned + units: errors + every: 1m + crit: $this > 0 + delay: down 1h multiplier 1.5 max 1h + info: number of ECC uncorrectable errors during the last hour + to: sysadmin + + alarm: 1hour_memory_hw_corrupted + on: mem.hwcorrupt + os: linux + hosts: * + calc: $HardwareCorrupted + units: MB + every: 10s + warn: $this > 0 + delay: down 1h multiplier 1.5 max 1h + info: amount of memory corrupted due to a hardware failure + to: sysadmin -- cgit v1.2.3