From c6fc3fa94deb7300bd2816fc2a7d088d40954ceb Mon Sep 17 00:00:00 2001 From: Roman Khavronenko Date: Tue, 13 Apr 2021 06:10:23 +0100 Subject: [PATCH] alerts: make alerting rule `RPCErrors` compatible with PromQL (#1204) Original query can't be executed via PromQL which results in error if expression is evaluated by Prometheus. The new expression is compatible with both engines. --- deployment/docker/alerts.yml | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/deployment/docker/alerts.yml b/deployment/docker/alerts.yml index ad5fd58a32..c537bf8e28 100644 --- a/deployment/docker/alerts.yml +++ b/deployment/docker/alerts.yml @@ -82,7 +82,16 @@ groups: Please verify if clients are sending correct requests." - alert: RPCErrors - expr: sum(increase({__name__=~"vm_rpc_.*_errors_total"}[5m])) by(job, instance) > 0 + expr: | + ( + sum(increase(vm_rpc_connection_errors_total[5m])) by(job, instance) + + + sum(increase(vm_rpc_dial_errors_total[5m])) by(job, instance) + + + sum(increase(vm_rpc_handshake_errors_total[5m])) by(job, instance) + + + sum(increase(vm_rpc_reroute_errors_total[5m])) by(job, instance) + ) > 0 for: 15m labels: severity: warning