From da49844e2c8ec49ff8931fb58052b080705f566e Mon Sep 17 00:00:00 2001 From: mfordjody <11638005@qq.com> Date: Mon, 30 Sep 2024 15:21:08 +0800 Subject: [PATCH] [horus] Developing standards for downtime (#405) --- manifests/horus/horus.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/manifests/horus/horus.yaml b/manifests/horus/horus.yaml index 704a3e7b..a6f6d0e2 100644 --- a/manifests/horus/horus.yaml +++ b/manifests/horus/horus.yaml @@ -78,7 +78,7 @@ nodeDownTime: promQueryTimeSecond: 60 abnormalityQL: - 100 - (avg by (node) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80 - - (avg by (node) (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100) < 20 + - (avg by (node) (node_memory_MemFree_bytes / node_memory_MemTotal_bytes )) * 100 < 10 - node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"} * 100 < 15 nodeNameToIPs: node_os_info{node="%s"}