From ded0ff5379278a8ece8e93804ccb690a59814ec0 Mon Sep 17 00:00:00 2001 From: michaelact <86778470+michaelact@users.noreply.github.com> Date: Tue, 6 Dec 2022 13:17:38 +0700 Subject: [PATCH] chore: not using for, instead in rule --- _data/rules.yml | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) diff --git a/_data/rules.yml b/_data/rules.yml index ba573ba..218855d 100644 --- a/_data/rules.yml +++ b/_data/rules.yml @@ -308,25 +308,20 @@ groups: query: 'node_reboot_required > 0' severity: info for: 4h + + # You may be want to increase the alert manager 'repeat_interval' for this type of alert to daily or weekly - name: node-exporter slug: node-exporter-under-utilized doc_url: https://github.com/prometheus/node_exporter rules: - name: Host Memory is under utilized description: 'Node memory is not fully used (> 80% free) for 1 week. Consider reducing memory space.' - query: 'node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 > 80' + query: 'min_over_time(node_memory_MemAvailable_bytes[1w]) / node_memory_MemTotal_bytes * 100 > 80' severity: info - for: 7d - name: Host Cpu is under utilized description: 'CPU load is < 20% for 1 week. Consider reducing the number of CPUs.' - query: '100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[2m])) * 100) < 20' + query: '100 - (max by(instance) (rate(node_cpu_seconds_total{mode="idle"}[1w])) * 100) < 20' severity: info - for: 7d - - name: Host lots of free Disk space - description: 'Disk space is not fully used (> 80% free) for 1 week. Consider reducing disk space.' - query: '(node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes > 80 and ON (instance, device, mountpoint) node_filesystem_readonly == 0' - severity: info - for: 7d - name: Docker containers exporters: