From e8c48caf363eae6ac2d69b7074186767180698d9 Mon Sep 17 00:00:00 2001 From: Christian Pointner Date: Sun, 20 Aug 2023 12:44:02 +0200 Subject: monitoring/prometheus: ingore remote filesystems for diskfull alerts --- roles/monitoring/prometheus/server/defaults/main/rules_node.yml | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'roles/monitoring/prometheus') diff --git a/roles/monitoring/prometheus/server/defaults/main/rules_node.yml b/roles/monitoring/prometheus/server/defaults/main/rules_node.yml index 0f9e025e..5493da57 100644 --- a/roles/monitoring/prometheus/server/defaults/main/rules_node.yml +++ b/roles/monitoring/prometheus/server/defaults/main/rules_node.yml @@ -29,7 +29,7 @@ prometheus_server_rules_node: description: "The node reports {{ '{{' }} $value {{ '}}' }} bytes of corrupted memory.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}" - alert: HostOutOfDiskSpace - expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0 + expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) node_filesystem_readonly{fstype!~"(tmpfs|nfs4?|cifs)"} == 0 for: 2m labels: severity: warning @@ -38,7 +38,7 @@ prometheus_server_rules_node: description: "Disk is almost full (< 10% left)\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}" - alert: HostDiskWillFillIn24Hours - expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) predict_linear(node_filesystem_avail_bytes{fstype!~"tmpfs"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly == 0 + expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) predict_linear(node_filesystem_avail_bytes{fstype!~"(tmpfs|nfs4?|cifs)"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly == 0 for: 2m labels: severity: warning @@ -47,7 +47,7 @@ prometheus_server_rules_node: description: "Filesystem is predicted to run out of space within the next 24 hours at current write rate\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}" - alert: HostOutOfInodes - expr: node_filesystem_files_free{mountpoint="/rootfs"} / node_filesystem_files{mountpoint="/rootfs"} * 100 < 10 and ON (instance, device, mountpoint) node_filesystem_readonly{mountpoint="/rootfs"} == 0 + expr: node_filesystem_files_free / node_filesystem_files * 100 < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0 for: 2m labels: severity: warning @@ -56,7 +56,7 @@ prometheus_server_rules_node: description: "Disk is almost running out of available inodes (< 10% left)\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}" - alert: HostInodesWillFillIn24Hours - expr: node_filesystem_files_free{mountpoint="/rootfs"} / node_filesystem_files{mountpoint="/rootfs"} * 100 < 10 and predict_linear(node_filesystem_files_free{mountpoint="/rootfs"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly{mountpoint="/rootfs"} == 0 + expr: node_filesystem_files_free / node_filesystem_files * 100 < 10 and predict_linear(node_filesystem_files_free[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly == 0 for: 2m labels: severity: warning -- cgit v1.2.3