From 56a7e0d03aebe4fedcca2c1e816d9e56b8545671 Mon Sep 17 00:00:00 2001 From: Brett Beutell Date: Fri, 26 Jan 2024 04:09:35 +0100 Subject: [PATCH] Update rule for host memory underutilization to use avg_over_time instead of rate, since node_memory_MemAvailable_bytes is a gauge (#400) --- dist/rules/host-and-hardware/node-exporter.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/dist/rules/host-and-hardware/node-exporter.yml b/dist/rules/host-and-hardware/node-exporter.yml index c63e0c866..fd27d811f 100644 --- a/dist/rules/host-and-hardware/node-exporter.yml +++ b/dist/rules/host-and-hardware/node-exporter.yml @@ -23,7 +23,7 @@ groups: description: "The node is under heavy memory pressure. High rate of major page faults\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostMemoryIsUnderutilized - expr: '(100 - (rate(node_memory_MemAvailable_bytes[30m]) / node_memory_MemTotal_bytes * 100) < 20) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '(100 - (avg_over_time(node_memory_MemAvailable_bytes[30m]) / node_memory_MemTotal_bytes * 100) < 20) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' for: 1w labels: severity: info