solution: reports for request errors/failures (#151)

dashboard/alerts/dshackle.yml

@@ -0,0 +1,61 @@
+groups:
+- name: Dshackle
+  rules:
+  - alert: JsonRpcDshackleErrorRateIsHigh
+    expr: rate(dshackle_request_jsonrpc_err_total[1m]) > 0.1
+    for: 1m
+    labels:
+      severity: critical
+    annotations:
+      summary: "Json RPC erorr rate is high for (instance {{ $labels.instance }})"
+
+  - alert: JsonRpcDshackleFailRateIsHigh
+    expr: rate(dshackle_request_jsonrpc_fail_total[1m]) > 0.1
+    for: 1m
+    labels:
+      severity: critical
+    annotations:
+      summary: "Json RPC erorr rate is high for (instance {{ $labels.instance }})"
+
+
+  - alert: JsonRpcDshackleRateToHigh
+    expr: rate(dshackle_request_jsonrpc_request_total[1m]) > 1000
+    for: 1m
+    labels:
+      severity: critical
+    annotations:
+      summary: "Json RPC rate is high for (instance {{ $labels.instance }})"
+
+
+  - alert: WsRpcDshackleErrorRateIsHigh
+    expr: rate(dshackle_upstream_ws_err_total[1m]) > 0.1
+    for: 1m
+    labels:
+      severity: critical
+    annotations:
+      summary: "WS RPC erorr rate is high for (instance {{ $labels.instance }})"
+
+  - alert: UpstreamUnavailable
+    expr: dshackle_upstreams_availability{status!~"(ok|lagging)"} > 0
+    for: 1m
+    labels:
+      severity: warning
+    annotations:
+      summary: "One of the eth node is broken (instance {{ $labels.instance }})"
+
+  - alert: NoEthNodesForNetwork
+    expr: dshackle_upstreams_connected < 1
+    for: 1m
+    labels:
+      severity: critical
+    annotations:
+      summary: "No nodes for network on (instance {{ $labels.instance }})"
+
+  - alert: UpstreamIsNotSyncing
+    expr: rate(dshackle_upstreams_lag[5m]) < 0
+    for: 1m
+    labels:
+      severity: critical
+    annotations:
+      summary: "ETH Node is not syncing on host (instance {{ $labels.instance }})"
+