summaryrefslogtreecommitdiffstats
path: root/health/health.d/memory.conf
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-05-04 14:31:17 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-05-04 14:31:17 +0000
commit8020f71afd34d7696d7933659df2d763ab05542f (patch)
tree2fdf1b5447ffd8bdd61e702ca183e814afdcb4fc /health/health.d/memory.conf
parentInitial commit. (diff)
downloadnetdata-e890d4be52eb1357c01a46a479feae0989a44120.tar.xz
netdata-e890d4be52eb1357c01a46a479feae0989a44120.zip
Adding upstream version 1.37.1.upstream/1.37.1upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'health/health.d/memory.conf')
-rw-r--r--health/health.d/memory.conf47
1 files changed, 47 insertions, 0 deletions
diff --git a/health/health.d/memory.conf b/health/health.d/memory.conf
new file mode 100644
index 0000000..010cbbd
--- /dev/null
+++ b/health/health.d/memory.conf
@@ -0,0 +1,47 @@
+
+# you can disable an alarm notification by setting the 'to' line to: silent
+
+ alarm: 1hour_ecc_memory_correctable
+ on: mem.ecc_ce
+ class: Errors
+ type: System
+component: Memory
+ 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 in the last 10 minutes
+ to: sysadmin
+
+ alarm: 1hour_ecc_memory_uncorrectable
+ on: mem.ecc_ue
+ class: Errors
+ type: System
+component: Memory
+ 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 in the last 10 minutes
+ to: sysadmin
+
+ alarm: 1hour_memory_hw_corrupted
+ on: mem.hwcorrupt
+ class: Errors
+ type: System
+component: Memory
+ 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