Documentation/op-guide: fix failed RPC rate, leader election metrics

This fixes failed RPC rate query, where we do not need subtraction because we already query by the status code. Also adds grpc_method to make it more specific. Most of the time, the failure recovers within 10-second, which is our Prometheus scrap interval, so 'rate' query might not cover that time window, showing as 0s, but still shows up in the graph. Signed-off-by: Gyu-Ho Lee <[email protected]>
etcd-io · Jun 14, 2017 · 943a113 · 943a113
1 parent 750dc7f
commit 943a113
Showing 1 changed file with 7 additions and 7 deletions.
diff --git a/Documentation/op-guide/grafana.json b/Documentation/op-guide/grafana.json
@@ -115,17 +115,17 @@
                     "stack": false,
                     "steppedLine": false,
                     "targets": [{
-                            "expr": "sum(rate(grpc_server_started_total{grpc_type=\"unary\"} [1m]))",
+                            "expr": "sum(rate(grpc_server_started_total{grpc_type=\"unary\"}[1m])) by (grpc_method)",
                             "intervalFactor": 2,
-                            "legendFormat": "{{instance}} RPC Rate",
+                            "legendFormat": "{{grpc_method}} RPC Rate",
                             "metric": "grpc_server_started_total",
                             "refId": "A",
                             "step": 2
                         },
                         {
-                            "expr": "sum(rate(grpc_server_started_total{grpc_type=\"unary\"} [1m])) - sum(rate(grpc_server_handled_total{grpc_type=\"unary\",grpc_code!=\"OK\"} [1m]))",
+                            "expr": "rate(grpc_server_handled_total{grpc_type=\"unary\",grpc_code!=\"OK\"}[1m])",
                             "intervalFactor": 2,
-                            "legendFormat": "{{instance}} RPC Failed Rate",
+                            "legendFormat": "{{instance}} {{grpc_method}} RPC Failed Rate",
                             "metric": "grpc_server_handled_total",
                             "refId": "B",
                             "step": 2
@@ -924,15 +924,15 @@
                     "targets": [{
                         "expr": "etcd_server_leader_changes_seen_total",
                         "intervalFactor": 2,
-                        "legendFormat": "{{instance}} Leader Change Seen",
+                        "legendFormat": "{{instance}} Total Leader Changes",
                         "metric": "etcd_server_leader_changes_seen_total",
                         "refId": "A",
                         "step": 2
                     }],
                     "thresholds": [],
                     "timeFrom": null,
                     "timeShift": null,
-                    "title": "Rate Leader Elections",
+                    "title": "Total Leader Elections",
                     "tooltip": {
                         "msResolution": false,
                         "shared": true,
@@ -1009,4 +1009,4 @@
     "version": 215,
     "links": [],
     "gnetId": null
-}
+}