fix: use counter instead of gauge for metrics that only increase over time (#3355)

Co-authored-by: Ivan Folgueira Bande <ivansete@status.im>

metrics/waku-fleet-dashboard.json

@@ -1569,7 +1569,7 @@
               },
               "editorMode": "code",
               "exemplar": false,
-              "expr": "sum by (type)(increase(waku_peers_errors{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval]))",
+              "expr": "sum by (type)(increase(waku_peers_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval]))",
               "interval": "",
               "legendFormat": "peer {{type}}",
               "range": true,
@@ -1582,7 +1582,7 @@
               },
               "editorMode": "code",
               "exemplar": false,
-              "expr": "sum by (type)(increase(waku_store_errors{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval]))",
+              "expr": "sum by (type)(increase(waku_store_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval]))",
               "hide": false,
               "interval": "",
               "legendFormat": "store {{type}}",
@@ -1596,7 +1596,7 @@
               },
               "editorMode": "code",
               "exemplar": false,
-              "expr": "sum by (type)(increase(waku_node_errors{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval]))",
+              "expr": "sum by (type)(increase(waku_node_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval]))",
               "hide": false,
               "interval": "",
               "legendFormat": "node {{type}}",
@@ -1906,7 +1906,7 @@
                 "uid": "P6693426190CB2316"
               },
               "exemplar": true,
-              "expr": "waku_node_errors{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}",
+              "expr": "waku_node_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}",
               "interval": "",
               "legendFormat": "{{type}}: {{instance}}",
               "refId": "A"
@@ -4314,7 +4314,7 @@
               },
               "editorMode": "code",
               "exemplar": true,
-              "expr": "increase(waku_store_queries{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"}[1m])",
+              "expr": "increase(waku_store_queries_total{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"}[1m])",
               "interval": "",
               "legendFormat": "{{instance}}",
               "range": true,
@@ -4413,7 +4413,7 @@
               },
               "editorMode": "code",
               "exemplar": true,
-              "expr": "sum by (type)(increase(waku_archive_errors{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[1m]))",
+              "expr": "sum by (type)(increase(waku_archive_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[1m]))",
               "hide": false,
               "interval": "",
               "legendFormat": "{{type}}",
@@ -4427,7 +4427,7 @@
               },
               "editorMode": "code",
               "exemplar": true,
-              "expr": "sum by (type)(increase(waku_store_errors{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[1m]))",
+              "expr": "sum by (type)(increase(waku_store_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[1m]))",
               "hide": false,
               "interval": "",
               "legendFormat": "{{type}}",
@@ -6695,7 +6695,7 @@
                 "uid": "P6693426190CB2316"
               },
               "editorMode": "code",
-              "expr": "rate(waku_filter_requests{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval])",
+              "expr": "rate(waku_filter_requests_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval])",
               "legendFormat": "{{type}} : {{instance}}",
               "range": true,
               "refId": "A"
@@ -6887,7 +6887,7 @@
                 "uid": "P6693426190CB2316"
               },
               "editorMode": "code",
-              "expr": "rate(waku_filter_errors{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval])",
+              "expr": "rate(waku_filter_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval])",
               "legendFormat": "{{type}} : {{instance}}",
               "range": true,
               "refId": "A"
@@ -7460,7 +7460,7 @@
                 "uid": "P6693426190CB2316"
               },
               "exemplar": true,
-              "expr": "waku_lightpush_errors{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}",
+              "expr": "waku_lightpush_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}",
               "interval": "",
               "legendFormat": "{{type}}: {[instance}}",
               "refId": "A"

waku/discovery/waku_discv5.nim

@@ -16,7 +16,7 @@ export protocol, waku_enr
 
 declarePublicGauge waku_discv5_discovered_per_shard,
   "number of nodes discovered by each shard", labels = ["shard"]
-declarePublicGauge waku_discv5_errors, "number of waku discv5 errors", ["type"]
+declarePublicCounter waku_discv5_errors, "number of waku discv5 errors", ["type"]
 
 logScope:
   topics = "waku discv5"

waku/discovery/waku_dnsdisc.nim

@@ -23,7 +23,7 @@ import ../waku_core
 export client
 
 declarePublicGauge waku_dnsdisc_discovered, "number of nodes discovered"
-declarePublicGauge waku_dnsdisc_errors, "number of waku dnsdisc errors", ["type"]
+declarePublicCounter waku_dnsdisc_errors, "number of waku dnsdisc errors", ["type"]
 
 logScope:
   topics = "waku dnsdisc"

waku/node/peer_manager/peer_manager.nim

@@ -30,7 +30,7 @@ declareCounter waku_peers_dials, "Number of peer dials", ["outcome"]
 # TODO: Populate from PeerStore.Source when ready
 declarePublicCounter waku_node_conns_initiated,
   "Number of connections initiated", ["source"]
-declarePublicGauge waku_peers_errors, "Number of peer manager errors", ["type"]
+declarePublicCounter waku_peers_errors, "Number of peer manager errors", ["type"]
 declarePublicGauge waku_connected_peers,
   "Number of physical connections per direction and protocol",
   labels = ["direction", "protocol"]

waku/node/waku_node.nim

@@ -59,7 +59,7 @@ declarePublicHistogram waku_histogram_message_size,
 
 declarePublicGauge waku_version,
   "Waku version info (in git describe format)", ["version"]
-declarePublicGauge waku_node_errors, "number of wakunode errors", ["type"]
+declarePublicCounter waku_node_errors, "number of wakunode errors", ["type"]
 declarePublicGauge waku_lightpush_peers, "number of lightpush peers"
 declarePublicGauge waku_filter_peers, "number of filter peers"
 declarePublicGauge waku_store_peers, "number of store peers"

waku/waku_archive/archive_metrics.nim

@@ -5,8 +5,7 @@ import metrics
 declarePublicGauge waku_archive_messages, "number of historical messages", ["type"]
 declarePublicGauge waku_archive_messages_per_shard,
   "number of historical messages per shard ", ["shard"]
-declarePublicGauge waku_archive_errors, "number of store protocol errors", ["type"]
-declarePublicGauge waku_archive_queries, "number of store queries received"
+declarePublicCounter waku_archive_errors, "number of store protocol errors", ["type"]
 declarePublicHistogram waku_archive_insert_duration_seconds,
   "message insertion duration"
 declarePublicHistogram waku_archive_query_duration_seconds, "history query duration"

waku/waku_archive_legacy/archive_metrics.nim

@@ -7,9 +7,8 @@ import metrics
 
 declarePublicGauge waku_legacy_archive_messages,
   "number of historical messages", ["type"]
-declarePublicGauge waku_legacy_archive_errors,
+declarePublicCounter waku_legacy_archive_errors,
   "number of store protocol errors", ["type"]
-declarePublicGauge waku_legacy_archive_queries, "number of store queries received"
 declarePublicHistogram waku_legacy_archive_insert_duration_seconds,
   "message insertion duration"
 declarePublicHistogram waku_legacy_archive_query_duration_seconds,

waku/waku_filter_v2/protocol_metrics.nim

@@ -4,8 +4,8 @@ import metrics
 
 export metrics
 
-declarePublicGauge waku_filter_errors, "number of filter protocol errors", ["type"]
-declarePublicGauge waku_filter_requests,
+declarePublicCounter waku_filter_errors, "number of filter protocol errors", ["type"]
+declarePublicCounter waku_filter_requests,
   "number of filter subscribe requests received", ["type"]
 declarePublicGauge waku_filter_subscriptions, "number of subscribed filter clients"
 declarePublicHistogram waku_filter_request_duration_seconds,

waku/waku_lightpush/protocol_metrics.nim

@@ -2,9 +2,9 @@
 
 import metrics
 
-declarePublicGauge waku_lightpush_v3_errors,
+declarePublicCounter waku_lightpush_v3_errors,
   "number of lightpush protocol errors", ["type"]
-declarePublicGauge waku_lightpush_v3_messages,
+declarePublicCounter waku_lightpush_v3_messages,
   "number of lightpush messages received", ["type"]
 
 # Error types (metric label values)

waku/waku_lightpush_legacy/protocol_metrics.nim

@@ -2,9 +2,9 @@
 
 import metrics
 
-declarePublicGauge waku_lightpush_errors,
+declarePublicCounter waku_lightpush_errors,
   "number of lightpush protocol errors", ["type"]
-declarePublicGauge waku_lightpush_messages,
+declarePublicCounter waku_lightpush_messages,
   "number of lightpush messages received", ["type"]
 
 # Error types (metric label values)

waku/waku_store/protocol_metrics.nim

@@ -2,8 +2,8 @@
 
 import metrics
 
-declarePublicGauge waku_store_errors, "number of store protocol errors", ["type"]
-declarePublicGauge waku_store_queries, "number of store queries received"
+declarePublicCounter waku_store_errors, "number of store protocol errors", ["type"]
+declarePublicCounter waku_store_queries, "number of store queries received"
 
 ## "query-db-time" phase considers the time when node performs the query to the database.
 ## "send-store-resp-time" phase is the time when node writes the store response to the store-client.

waku/waku_store_legacy/protocol_metrics.nim

@@ -2,9 +2,10 @@
 
 import metrics
 
-declarePublicGauge waku_legacy_store_errors,
+declarePublicCounter waku_legacy_store_errors,
   "number of legacy store protocol errors", ["type"]
-declarePublicGauge waku_legacy_store_queries, "number of legacy store queries received"
+declarePublicCounter waku_legacy_store_queries,
+  "number of legacy store queries received"
 
 ## "query-db-time" phase considers the time when node performs the query to the database.
 ## "send-store-resp-time" phase is the time when node writes the store response to the store-client.