X-Git-Url: https://iankelling.org/git/?p=distro-setup;a=blobdiff_plain;f=filesystem%2Fetc%2Fprometheus%2Frules%2Fiank.yml;h=4f3bb04ee5e8e0ee5129638dcbc43c6c6458ea9b;hp=971e392fd63b55387089c47529060ebd91543d03;hb=56c55d8e02cdd6ec67d2fe53cc03785d8876442e;hpb=da085f71e5ae00a9f78ed903be6ae675f66eacfa diff --git a/filesystem/etc/prometheus/rules/iank.yml b/filesystem/etc/prometheus/rules/iank.yml index 971e392..4f3bb04 100644 --- a/filesystem/etc/prometheus/rules/iank.yml +++ b/filesystem/etc/prometheus/rules/iank.yml @@ -115,6 +115,14 @@ groups: annotations: summary: '12 minutes down' + - alert: mailtest_check_unexpected_spamd_vps + expr: |- + mailtest_check_unexpected_spamd_results >= 1 + labels: + severity: day + annotations: + summary: 'jr -u mailtest-check -e' + - alert: mailtest_check_mailhost expr: |- time() - max by (folder,from) (mailtest_check_last_usec{job="node"}) >= 60 * 12 @@ -123,14 +131,14 @@ groups: annotations: summary: '12 minutes down' - # 42 mins: enough for a 30 min queue run plus 12 + # 20 minutes. just allow for more due to prod alert. - alert: mailtest_check_gnu_mailhost expr: |- - time() - max by (folder,from) (mailtest_check_last_usec{folder="/m/md/l/testignore", from="iank@gnu.org"}) >= 60 * 42 + time() - max by (folder,from) (mailtest_check_last_usec{folder="/m/md/l/testignore", from="iank@gnu.org"}) >= 60 * 20 labels: severity: prod annotations: - summary: '42 minutes down' + summary: '20 minutes down' - alert: 1pmtest