2021-08-19 09:57:53 +02:00
{
"annotations" : {
"list" : [
{
"builtIn" : 1 ,
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "datasource" ,
"uid" : "grafana"
} ,
2021-08-19 09:57:53 +02:00
"enable" : true ,
"hide" : true ,
"iconColor" : "rgba(0, 211, 255, 1)" ,
"name" : "Annotations & Alerts" ,
2022-02-08 12:22:06 +01:00
"target" : {
"limit" : 100 ,
"matchAny" : false ,
"tags" : [ ] ,
"type" : "dashboard"
} ,
2021-08-19 09:57:53 +02:00
"type" : "dashboard"
}
]
} ,
2025-08-01 16:11:32 +05:30
"description" : "Metrics for Waku nodes written in Nim" ,
2021-08-19 09:57:53 +02:00
"editable" : true ,
2022-02-08 12:22:06 +01:00
"fiscalYearStartMonth" : 0 ,
2025-08-01 16:11:32 +05:30
"graphTooltip" : 1 ,
"id" : 58 ,
2021-08-19 09:57:53 +02:00
"links" : [ ] ,
"panels" : [
{
"collapsed" : false ,
"gridPos" : {
"h" : 1 ,
"w" : 24 ,
"x" : 0 ,
"y" : 0
} ,
"id" : 56 ,
"panels" : [ ] ,
"title" : "At a glance" ,
"type" : "row"
} ,
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2021-08-19 09:57:53 +02:00
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "thresholds"
} ,
"mappings" : [ ] ,
2022-02-08 12:22:06 +01:00
"min" : 0 ,
2021-08-19 09:57:53 +02:00
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 0
} ,
{
"color" : "yellow" ,
"value" : 1
} ,
{
"color" : "green" ,
"value" : 2
2022-02-08 12:22:06 +01:00
} ,
{
"color" : "#EAB839" ,
"value" : 120
} ,
{
"color" : "red" ,
"value" : 149
2021-08-19 09:57:53 +02:00
}
]
}
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 10 ,
2025-08-01 16:11:32 +05:30
"w" : 4 ,
2021-08-19 09:57:53 +02:00
"x" : 0 ,
"y" : 1
} ,
"id" : 52 ,
"options" : {
2024-08-21 17:10:29 +02:00
"minVizHeight" : 75 ,
"minVizWidth" : 75 ,
2022-02-08 12:22:06 +01:00
"orientation" : "auto" ,
2021-08-19 09:57:53 +02:00
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
} ,
"showThresholdLabels" : false ,
"showThresholdMarkers" : true ,
2025-08-01 16:11:32 +05:30
"sizing" : "auto"
2021-08-19 09:57:53 +02:00
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2021-08-19 09:57:53 +02:00
"targets" : [
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
"editorMode" : "code" ,
2021-08-19 09:57:53 +02:00
"exemplar" : true ,
2025-08-01 16:11:32 +05:30
"expr" : "libp2p_pubsub_peers{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}" ,
2021-08-19 09:57:53 +02:00
"interval" : "" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "{{fleet}}: {{datacenter}}" ,
2022-09-20 10:01:54 +01:00
"range" : true ,
2021-08-19 09:57:53 +02:00
"refId" : "A"
}
] ,
"title" : "Libp2p PubSub Peers" ,
"type" : "gauge"
} ,
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2021-08-19 09:57:53 +02:00
} ,
"fieldConfig" : {
"defaults" : {
2022-02-08 12:22:06 +01:00
"color" : {
2025-08-01 16:11:32 +05:30
"mode" : "thresholds"
2022-02-08 12:22:06 +01:00
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
2025-08-01 16:11:32 +05:30
"color" : "blue" ,
2022-02-08 12:22:06 +01:00
"value" : null
}
]
} ,
2025-08-01 16:11:32 +05:30
"unit" : "dateTimeAsIso"
2021-08-19 09:57:53 +02:00
} ,
"overrides" : [ ]
} ,
"gridPos" : {
2022-09-20 10:01:54 +01:00
"h" : 10 ,
2025-08-01 16:11:32 +05:30
"w" : 7 ,
"x" : 4 ,
2022-09-20 10:01:54 +01:00
"y" : 1
2021-08-19 09:57:53 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 46 ,
2021-08-19 09:57:53 +02:00
"options" : {
2025-08-01 16:11:32 +05:30
"colorMode" : "value" ,
"graphMode" : "none" ,
"justifyMode" : "auto" ,
"orientation" : "horizontal" ,
"percentChangeColorMode" : "standard" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
2022-02-08 12:22:06 +01:00
} ,
2025-08-01 16:11:32 +05:30
"showPercentChange" : false ,
"text" : {
"titleSize" : 18 ,
"valueSize" : 20
} ,
"textMode" : "auto" ,
"wideLayout" : true
2021-08-19 09:57:53 +02:00
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2021-08-19 09:57:53 +02:00
"targets" : [
{
2022-02-08 12:22:06 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-02-08 12:22:06 +01:00
} ,
2021-08-19 09:57:53 +02:00
"exemplar" : true ,
2025-08-01 16:11:32 +05:30
"expr" : "process_start_time_seconds{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"} * 1000" ,
2021-08-19 09:57:53 +02:00
"interval" : "" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "{{instance}}" ,
2021-08-19 09:57:53 +02:00
"refId" : "A"
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "Node start times (UTC)" ,
"type" : "stat"
2022-02-08 12:22:06 +01:00
} ,
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2022-02-08 12:22:06 +01:00
"fieldConfig" : {
"defaults" : {
"color" : {
2025-08-01 16:11:32 +05:30
"mode" : "thresholds"
2022-02-08 12:22:06 +01:00
} ,
"mappings" : [ ] ,
2025-08-01 16:11:32 +05:30
"max" : 100 ,
"min" : 0 ,
2022-02-08 12:22:06 +01:00
"thresholds" : {
2025-08-01 16:11:32 +05:30
"mode" : "percentage" ,
2022-02-08 12:22:06 +01:00
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
2025-08-01 16:11:32 +05:30
} ,
"unit" : "percent"
2022-02-08 12:22:06 +01:00
} ,
2022-09-20 10:01:54 +01:00
"overrides" : [ ]
2021-08-19 09:57:53 +02:00
} ,
2022-02-08 12:22:06 +01:00
"gridPos" : {
2022-09-20 10:01:54 +01:00
"h" : 10 ,
"w" : 8 ,
2025-08-01 16:11:32 +05:30
"x" : 11 ,
2022-09-20 10:01:54 +01:00
"y" : 1
2021-08-19 09:57:53 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 58 ,
2022-02-08 12:22:06 +01:00
"options" : {
2025-08-01 16:11:32 +05:30
"displayMode" : "lcd" ,
2022-02-08 12:22:06 +01:00
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
2022-09-20 10:01:54 +01:00
"placement" : "bottom" ,
2025-08-01 16:11:32 +05:30
"showLegend" : false
2022-02-08 12:22:06 +01:00
} ,
2025-08-01 16:11:32 +05:30
"maxVizHeight" : 300 ,
"minVizHeight" : 10 ,
"minVizWidth" : 0 ,
"namePlacement" : "auto" ,
"orientation" : "horizontal" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
} ,
"showUnfilled" : true ,
"sizing" : "auto" ,
"text" : { } ,
"valueMode" : "color"
2022-02-08 12:22:06 +01:00
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2022-02-08 12:22:06 +01:00
"targets" : [
2021-08-19 09:57:53 +02:00
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2025-08-01 16:11:32 +05:30
"exemplar" : true ,
"expr" : "avg by (instance)(netdata_cpu_cpu_percentage_average{dimension=\"user\", instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"})" ,
2022-02-08 12:22:06 +01:00
"interval" : "" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "{{instance}}" ,
2022-02-08 12:22:06 +01:00
"refId" : "A"
2021-08-19 09:57:53 +02:00
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "CPU Usage" ,
"type" : "bargauge"
2022-02-08 12:22:06 +01:00
} ,
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "thresholds"
} ,
"custom" : {
"align" : "auto" ,
"cellOptions" : {
"type" : "auto"
} ,
"inspect" : false
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
}
} ,
"overrides" : [
{
"matcher" : {
"id" : "byName" ,
"options" : "source"
} ,
"properties" : [
{
"id" : "custom.width" ,
"value" : 122
}
]
} ,
{
"matcher" : {
"id" : "byName" ,
"options" : "Time"
} ,
"properties" : [
{
"id" : "custom.width" ,
"value" : 181
}
]
}
]
2022-09-20 10:01:54 +01:00
} ,
"gridPos" : {
2025-08-01 16:11:32 +05:30
"h" : 10 ,
"w" : 5 ,
"x" : 19 ,
"y" : 1
2022-09-20 10:01:54 +01:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 85 ,
"options" : {
"cellHeight" : "sm" ,
"footer" : {
"countRows" : false ,
"fields" : "" ,
"reducer" : [
"sum"
] ,
"show" : false
} ,
"showHeader" : true ,
"sortBy" : [ ]
} ,
"pluginVersion" : "11.5.2" ,
2022-09-20 10:01:54 +01:00
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2025-08-01 16:11:32 +05:30
"editorMode" : "code" ,
"exemplar" : false ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "(waku_version{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"} or logos_delivery_version{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"})" ,
2025-08-01 16:11:32 +05:30
"format" : "table" ,
"instant" : true ,
"legendFormat" : "__auto" ,
"range" : false ,
2022-09-20 10:01:54 +01:00
"refId" : "A"
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "Version" ,
"transformations" : [
{
"id" : "filterFieldsByName" ,
"options" : {
"include" : {
"names" : [
"version" ,
"source" ,
"Time"
]
}
}
}
] ,
"type" : "table"
2022-09-20 10:01:54 +01:00
} ,
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2022-02-08 12:22:06 +01:00
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
2024-08-21 17:10:29 +02:00
"axisBorderShow" : false ,
2022-09-20 10:01:54 +01:00
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
2022-02-08 12:22:06 +01:00
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
2025-08-01 16:11:32 +05:30
"barWidthFactor" : 0.6 ,
2022-02-08 12:22:06 +01:00
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
2024-08-21 17:10:29 +02:00
"insertNulls" : false ,
2022-02-08 12:22:06 +01:00
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
}
} ,
"overrides" : [ ]
} ,
"gridPos" : {
2025-08-01 16:11:32 +05:30
"h" : 9 ,
2022-02-08 12:22:06 +01:00
"w" : 12 ,
"x" : 0 ,
2025-08-01 16:11:32 +05:30
"y" : 11
2022-02-08 12:22:06 +01:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 81 ,
2022-02-08 12:22:06 +01:00
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
2022-09-20 10:01:54 +01:00
"placement" : "bottom" ,
"showLegend" : true
2022-02-08 12:22:06 +01:00
} ,
"tooltip" : {
2025-08-01 16:11:32 +05:30
"hideZeros" : false ,
2022-09-20 10:01:54 +01:00
"mode" : "single" ,
"sort" : "none"
2022-02-08 12:22:06 +01:00
}
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2022-02-08 12:22:06 +01:00
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-02-08 12:22:06 +01:00
} ,
2022-09-20 10:01:54 +01:00
"editorMode" : "code" ,
2025-08-01 16:11:32 +05:30
"expr" : "libp2p_autonat_reachability_confidence{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\", reachability=\"Reachable\"}" ,
"legendFormat" : "{{instance}}:{{reachability}}" ,
2022-09-20 10:01:54 +01:00
"range" : true ,
2022-02-08 12:22:06 +01:00
"refId" : "A"
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "Node is Reachable (Experimental)" ,
2022-02-08 12:22:06 +01:00
"type" : "timeseries"
} ,
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2022-02-08 12:22:06 +01:00
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
2024-08-21 17:10:29 +02:00
"axisBorderShow" : false ,
2022-09-20 10:01:54 +01:00
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
2022-02-08 12:22:06 +01:00
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
2025-08-01 16:11:32 +05:30
"barWidthFactor" : 0.6 ,
2022-02-08 12:22:06 +01:00
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
2024-08-21 17:10:29 +02:00
"insertNulls" : false ,
2022-02-08 12:22:06 +01:00
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
}
} ,
"overrides" : [ ]
} ,
"gridPos" : {
2025-08-01 16:11:32 +05:30
"h" : 9 ,
2022-02-08 12:22:06 +01:00
"w" : 12 ,
"x" : 12 ,
2025-08-01 16:11:32 +05:30
"y" : 11
2022-02-08 12:22:06 +01:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 82 ,
2022-02-08 12:22:06 +01:00
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
2022-09-20 10:01:54 +01:00
"placement" : "bottom" ,
"showLegend" : true
2022-02-08 12:22:06 +01:00
} ,
"tooltip" : {
2025-08-01 16:11:32 +05:30
"hideZeros" : false ,
2022-09-20 10:01:54 +01:00
"mode" : "single" ,
"sort" : "none"
2022-02-08 12:22:06 +01:00
}
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2022-02-08 12:22:06 +01:00
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-02-08 12:22:06 +01:00
} ,
2022-09-20 10:01:54 +01:00
"editorMode" : "code" ,
2025-08-01 16:11:32 +05:30
"expr" : "libp2p_autonat_reachability_confidence{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\", reachability=\"NotReachable\"}" ,
"legendFormat" : "{{instance}}:{{reachability}}" ,
2022-09-20 10:01:54 +01:00
"range" : true ,
2022-02-08 12:22:06 +01:00
"refId" : "A"
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "Node is NotReachable (Experimental)" ,
2022-02-08 12:22:06 +01:00
"type" : "timeseries"
} ,
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-02-08 12:22:06 +01:00
} ,
2025-08-01 16:11:32 +05:30
"description" : "" ,
2021-08-19 09:57:53 +02:00
"fieldConfig" : {
"defaults" : {
2025-08-01 16:11:32 +05:30
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisBorderShow" : false ,
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
"barWidthFactor" : 0.6 ,
"drawStyle" : "line" ,
"fillOpacity" : 10 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"insertNulls" : false ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "never" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"links" : [ ] ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
} ,
"unit" : "binBps"
2021-08-19 09:57:53 +02:00
} ,
"overrides" : [ ]
} ,
"gridPos" : {
2025-08-01 16:11:32 +05:30
"h" : 9 ,
2021-08-19 09:57:53 +02:00
"w" : 12 ,
"x" : 0 ,
2025-08-01 16:11:32 +05:30
"y" : 20
2021-08-19 09:57:53 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 78 ,
"interval" : "15s" ,
"maxDataPoints" : 1000 ,
2021-08-19 09:57:53 +02:00
"options" : {
2025-08-01 16:11:32 +05:30
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
"hideZeros" : false ,
"mode" : "single" ,
"sort" : "none"
}
} ,
"pluginVersion" : "11.5.2" ,
2021-08-19 09:57:53 +02:00
"targets" : [
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
"editorMode" : "code" ,
2025-08-01 16:11:32 +05:30
"exemplar" : true ,
"expr" : "rate(libp2p_network_bytes_total{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\", direction=\"in\"}[$__rate_interval])" ,
2021-08-19 09:57:53 +02:00
"interval" : "" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "{{instance}}:{{direction}}" ,
2022-09-20 10:01:54 +01:00
"range" : true ,
2021-08-19 09:57:53 +02:00
"refId" : "A"
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "Inbound Traffic" ,
"type" : "timeseries"
2021-08-19 09:57:53 +02:00
} ,
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2025-08-01 16:11:32 +05:30
"description" : "" ,
2021-08-19 09:57:53 +02:00
"fieldConfig" : {
"defaults" : {
2025-08-01 16:11:32 +05:30
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisBorderShow" : false ,
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
"barWidthFactor" : 0.6 ,
"drawStyle" : "line" ,
"fillOpacity" : 10 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"insertNulls" : false ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "never" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"links" : [ ] ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
} ,
"unit" : "binBps"
2021-08-19 09:57:53 +02:00
} ,
"overrides" : [ ]
} ,
"gridPos" : {
2025-08-01 16:11:32 +05:30
"h" : 9 ,
2021-08-19 09:57:53 +02:00
"w" : 12 ,
"x" : 12 ,
2025-08-01 16:11:32 +05:30
"y" : 20
2021-08-19 09:57:53 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 79 ,
2021-08-19 09:57:53 +02:00
"options" : {
2025-08-01 16:11:32 +05:30
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
"hideZeros" : false ,
"mode" : "single" ,
"sort" : "none"
}
} ,
"pluginVersion" : "11.5.2" ,
2021-08-19 09:57:53 +02:00
"targets" : [
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
"editorMode" : "code" ,
2025-08-01 16:11:32 +05:30
"exemplar" : true ,
"expr" : "rate(libp2p_network_bytes_total{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\", direction=\"out\"}[$__rate_interval])" ,
2021-08-19 09:57:53 +02:00
"interval" : "" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "{{instance}}:{{direction}}" ,
2022-09-20 10:01:54 +01:00
"range" : true ,
2021-08-19 09:57:53 +02:00
"refId" : "A"
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "Outbound Traffic" ,
"type" : "timeseries"
2021-08-19 09:57:53 +02:00
} ,
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2025-08-01 16:11:32 +05:30
"description" : "" ,
2021-08-19 09:57:53 +02:00
"fieldConfig" : {
"defaults" : {
2025-08-01 16:11:32 +05:30
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisBorderShow" : false ,
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
"barWidthFactor" : 0.6 ,
"drawStyle" : "line" ,
"fillOpacity" : 10 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"insertNulls" : false ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "never" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"links" : [ ] ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
} ,
"unit" : "short"
2021-08-19 09:57:53 +02:00
} ,
"overrides" : [ ]
} ,
"gridPos" : {
2025-08-01 16:11:32 +05:30
"h" : 9 ,
2021-08-19 09:57:53 +02:00
"w" : 12 ,
"x" : 0 ,
2025-08-01 16:11:32 +05:30
"y" : 29
2021-08-19 09:57:53 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 11 ,
2021-08-19 09:57:53 +02:00
"options" : {
2025-08-01 16:11:32 +05:30
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
"hideZeros" : false ,
"mode" : "single" ,
"sort" : "none"
}
} ,
"pluginVersion" : "11.5.2" ,
2021-08-19 09:57:53 +02:00
"targets" : [
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
"editorMode" : "code" ,
2025-08-01 16:11:32 +05:30
"exemplar" : true ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "((increase(waku_node_messages_total{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"}[1m]) or increase(logos_delivery_node_messages_total{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"}[1m])))" ,
2021-08-19 09:57:53 +02:00
"interval" : "" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "{{type}}: {{instance}}" ,
2022-09-20 10:01:54 +01:00
"range" : true ,
2021-08-19 09:57:53 +02:00
"refId" : "A"
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "Messages (1m rate)" ,
"type" : "timeseries"
2021-08-19 09:57:53 +02:00
} ,
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2021-08-19 09:57:53 +02:00
"fieldConfig" : {
"defaults" : {
2025-08-01 16:11:32 +05:30
"color" : {
"mode" : "palette-classic"
2022-09-20 10:01:54 +01:00
} ,
2025-08-01 16:11:32 +05:30
"custom" : {
"axisBorderShow" : false ,
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
"barWidthFactor" : 0.6 ,
"drawStyle" : "line" ,
"fillOpacity" : 9 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"insertNulls" : false ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
2022-09-20 10:01:54 +01:00
} ,
2025-08-01 16:11:32 +05:30
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
}
2021-08-19 09:57:53 +02:00
} ,
"overrides" : [ ]
} ,
"gridPos" : {
2025-08-01 16:11:32 +05:30
"h" : 9 ,
2021-08-19 09:57:53 +02:00
"w" : 12 ,
2025-08-01 16:11:32 +05:30
"x" : 12 ,
"y" : 29
2021-08-19 09:57:53 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 54 ,
2021-08-19 09:57:53 +02:00
"options" : {
2025-08-01 16:11:32 +05:30
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
2021-08-19 09:57:53 +02:00
} ,
2025-08-01 16:11:32 +05:30
"tooltip" : {
"hideZeros" : false ,
"mode" : "single" ,
"sort" : "none"
2021-08-19 09:57:53 +02:00
}
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2022-02-08 12:22:06 +01:00
"targets" : [
2021-08-19 09:57:53 +02:00
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
"editorMode" : "code" ,
2025-08-01 16:11:32 +05:30
"exemplar" : false ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "sum by (type)((increase(waku_peers_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval]) or increase(logos_delivery_peers_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval])))" ,
2021-08-19 09:57:53 +02:00
"interval" : "" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "peer {{type}}" ,
2022-09-20 10:01:54 +01:00
"range" : true ,
2022-02-08 12:22:06 +01:00
"refId" : "A"
2022-09-20 10:01:54 +01:00
} ,
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
"editorMode" : "code" ,
2025-08-01 16:11:32 +05:30
"exemplar" : false ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "sum by (type)((increase(waku_store_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval]) or increase(logos_delivery_store_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval])))" ,
2022-09-20 10:01:54 +01:00
"hide" : false ,
"interval" : "" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "store {{type}}" ,
2022-09-20 10:01:54 +01:00
"range" : true ,
"refId" : "B"
} ,
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
"editorMode" : "code" ,
2025-08-01 16:11:32 +05:30
"exemplar" : false ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "sum by (type)((increase(waku_node_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval]) or increase(logos_delivery_node_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval])))" ,
2022-09-20 10:01:54 +01:00
"hide" : false ,
"interval" : "" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "node {{type}}" ,
2022-09-20 10:01:54 +01:00
"range" : true ,
"refId" : "C"
2021-08-19 09:57:53 +02:00
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "Waku Errors" ,
"type" : "timeseries"
2021-08-19 09:57:53 +02:00
} ,
2024-08-21 17:10:29 +02:00
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2024-08-21 17:10:29 +02:00
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisBorderShow" : false ,
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
2025-08-01 16:11:32 +05:30
"barWidthFactor" : 0.6 ,
2024-08-21 17:10:29 +02:00
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"insertNulls" : false ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
2025-08-01 16:11:32 +05:30
}
2024-08-21 17:10:29 +02:00
} ,
"overrides" : [ ]
} ,
"gridPos" : {
2025-08-01 16:11:32 +05:30
"h" : 8 ,
2024-08-21 17:10:29 +02:00
"w" : 12 ,
"x" : 0 ,
2025-08-01 16:11:32 +05:30
"y" : 38
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 66 ,
2024-08-21 17:10:29 +02:00
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
2025-08-01 16:11:32 +05:30
"hideZeros" : false ,
2024-08-21 17:10:29 +02:00
"mode" : "single" ,
"sort" : "none"
}
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2024-08-21 17:10:29 +02:00
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"exemplar" : true ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "count(count by (contentTopic)((waku_node_messages_total or logos_delivery_node_messages_total)))" ,
2025-08-01 16:11:32 +05:30
"interval" : "" ,
"legendFormat" : "content topics" ,
2024-08-21 17:10:29 +02:00
"refId" : "A"
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "Total Content Topics" ,
2024-08-21 17:10:29 +02:00
"type" : "timeseries"
} ,
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2024-08-21 17:10:29 +02:00
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisBorderShow" : false ,
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
2025-08-01 16:11:32 +05:30
"barWidthFactor" : 0.6 ,
2024-08-21 17:10:29 +02:00
"drawStyle" : "line" ,
2025-08-01 16:11:32 +05:30
"fillOpacity" : 5 ,
2024-08-21 17:10:29 +02:00
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"insertNulls" : false ,
2025-08-01 16:11:32 +05:30
"lineInterpolation" : "stepBefore" ,
"lineStyle" : {
"fill" : "solid"
} ,
"lineWidth" : 2 ,
2024-08-21 17:10:29 +02:00
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
2025-08-01 16:11:32 +05:30
}
2024-08-21 17:10:29 +02:00
} ,
"overrides" : [ ]
} ,
"gridPos" : {
2025-08-01 16:11:32 +05:30
"h" : 8 ,
2024-08-21 17:10:29 +02:00
"w" : 12 ,
"x" : 12 ,
2025-08-01 16:11:32 +05:30
"y" : 38
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 68 ,
2024-08-21 17:10:29 +02:00
"options" : {
"legend" : {
"calcs" : [ ] ,
2025-08-01 16:11:32 +05:30
"displayMode" : "table" ,
"placement" : "right" ,
2024-08-21 17:10:29 +02:00
"showLegend" : true
} ,
"tooltip" : {
2025-08-01 16:11:32 +05:30
"hideZeros" : false ,
"mode" : "multi" ,
"sort" : "desc"
2024-08-21 17:10:29 +02:00
}
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2024-08-21 17:10:29 +02:00
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2024-08-21 17:10:29 +02:00
} ,
"editorMode" : "code" ,
2025-08-01 16:11:32 +05:30
"exemplar" : true ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "(waku_version{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"} or logos_delivery_version{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"})" ,
2025-08-01 16:11:32 +05:30
"interval" : "" ,
"legendFormat" : "{{instance}}:{{version}}" ,
2024-08-21 17:10:29 +02:00
"range" : true ,
"refId" : "A"
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "Waku version" ,
2024-08-21 17:10:29 +02:00
"type" : "timeseries"
} ,
2025-08-01 16:11:32 +05:30
{
"collapsed" : false ,
"gridPos" : {
"h" : 1 ,
"w" : 24 ,
"x" : 0 ,
"y" : 46
} ,
"id" : 17 ,
"panels" : [ ] ,
"title" : "General" ,
"type" : "row"
} ,
2021-08-19 09:57:53 +02:00
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2021-08-19 09:57:53 +02:00
"description" : "" ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
2024-08-21 17:10:29 +02:00
"axisBorderShow" : false ,
2022-09-20 10:01:54 +01:00
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
2021-08-19 09:57:53 +02:00
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
2025-08-01 16:11:32 +05:30
"barWidthFactor" : 0.6 ,
2021-08-19 09:57:53 +02:00
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
2024-08-21 17:10:29 +02:00
"insertNulls" : false ,
2021-08-19 09:57:53 +02:00
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
2025-08-01 16:11:32 +05:30
}
2021-08-19 09:57:53 +02:00
} ,
"overrides" : [ ]
} ,
"gridPos" : {
2025-08-01 16:11:32 +05:30
"h" : 6 ,
2021-08-19 09:57:53 +02:00
"w" : 12 ,
"x" : 0 ,
2025-08-01 16:11:32 +05:30
"y" : 47
2021-08-19 09:57:53 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 48 ,
2021-08-19 09:57:53 +02:00
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
2022-09-20 10:01:54 +01:00
"placement" : "bottom" ,
"showLegend" : true
2021-08-19 09:57:53 +02:00
} ,
"tooltip" : {
2025-08-01 16:11:32 +05:30
"hideZeros" : false ,
2022-09-20 10:01:54 +01:00
"mode" : "single" ,
"sort" : "none"
2021-08-19 09:57:53 +02:00
}
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2021-08-19 09:57:53 +02:00
"targets" : [
{
2022-02-08 12:22:06 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-02-08 12:22:06 +01:00
} ,
2021-08-19 09:57:53 +02:00
"exemplar" : true ,
2025-08-01 16:11:32 +05:30
"expr" : "waku_node_filters{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}" ,
2021-08-19 09:57:53 +02:00
"interval" : "" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "{{instance}}" ,
2021-08-19 09:57:53 +02:00
"refId" : "A"
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "Waku Node Filters" ,
2021-08-19 09:57:53 +02:00
"type" : "timeseries"
} ,
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2021-08-19 09:57:53 +02:00
"fieldConfig" : {
"defaults" : {
2022-02-08 12:22:06 +01:00
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
2024-08-21 17:10:29 +02:00
"axisBorderShow" : false ,
2022-09-20 10:01:54 +01:00
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
2022-02-08 12:22:06 +01:00
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
2025-08-01 16:11:32 +05:30
"barWidthFactor" : 0.6 ,
2022-02-08 12:22:06 +01:00
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
2024-08-21 17:10:29 +02:00
"insertNulls" : false ,
2022-02-08 12:22:06 +01:00
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
2025-08-01 16:11:32 +05:30
}
2021-08-19 09:57:53 +02:00
} ,
"overrides" : [ ]
} ,
"gridPos" : {
2025-08-01 16:11:32 +05:30
"h" : 6 ,
2021-08-19 09:57:53 +02:00
"w" : 12 ,
"x" : 12 ,
2025-08-01 16:11:32 +05:30
"y" : 47
2021-08-19 09:57:53 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 50 ,
2021-08-19 09:57:53 +02:00
"options" : {
2022-02-08 12:22:06 +01:00
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
2022-09-20 10:01:54 +01:00
"placement" : "bottom" ,
"showLegend" : true
2022-02-08 12:22:06 +01:00
} ,
"tooltip" : {
2025-08-01 16:11:32 +05:30
"hideZeros" : false ,
2022-09-20 10:01:54 +01:00
"mode" : "single" ,
"sort" : "none"
2022-02-08 12:22:06 +01:00
}
2021-08-19 09:57:53 +02:00
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2021-08-19 09:57:53 +02:00
"targets" : [
{
2022-02-08 12:22:06 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-02-08 12:22:06 +01:00
} ,
2021-08-19 09:57:53 +02:00
"exemplar" : true ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "(waku_node_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"} or logos_delivery_node_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"})" ,
2021-08-19 09:57:53 +02:00
"interval" : "" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "{{type}}: {{instance}}" ,
2021-08-19 09:57:53 +02:00
"refId" : "A"
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "Waku Node Errors" ,
2022-02-08 12:22:06 +01:00
"type" : "timeseries"
2021-08-19 09:57:53 +02:00
} ,
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2021-08-19 09:57:53 +02:00
"fieldConfig" : {
"defaults" : {
2025-08-01 16:11:32 +05:30
"color" : {
"mode" : "palette-classic"
2022-09-20 10:01:54 +01:00
} ,
2025-08-01 16:11:32 +05:30
"custom" : {
"axisBorderShow" : false ,
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
"barWidthFactor" : 0.6 ,
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"insertNulls" : false ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
}
2021-08-19 09:57:53 +02:00
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 6 ,
"w" : 12 ,
2025-08-01 16:11:32 +05:30
"x" : 0 ,
2024-08-21 17:10:29 +02:00
"y" : 53
2021-08-19 09:57:53 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 60 ,
2021-08-19 09:57:53 +02:00
"options" : {
2025-08-01 16:11:32 +05:30
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
"hideZeros" : false ,
"mode" : "single" ,
"sort" : "none"
}
} ,
"pluginVersion" : "11.5.2" ,
2021-08-19 09:57:53 +02:00
"targets" : [
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2025-08-01 16:11:32 +05:30
"exemplar" : true ,
"expr" : "libp2p_pubsub_topics {instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"}" ,
2021-08-19 09:57:53 +02:00
"interval" : "" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "Topics: {{instance}}" ,
2021-08-19 09:57:53 +02:00
"refId" : "A"
} ,
{
2025-08-01 16:11:32 +05:30
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"exemplar" : true ,
"expr" : "libp2p_pubsub_subscriptions_total {instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"}" ,
"hide" : false ,
"interval" : "" ,
"legendFormat" : "Subscriptions: {{instance}}" ,
"refId" : "B"
} ,
2022-09-20 10:01:54 +01:00
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2025-08-01 16:11:32 +05:30
"exemplar" : true ,
"expr" : "libp2p_pubsub_unsubscriptions_total {instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"}" ,
"hide" : false ,
"interval" : "" ,
"legendFormat" : "Unsubscriptions: {{instance}}" ,
"refId" : "C"
2022-09-20 10:01:54 +01:00
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "Pubsub Topics" ,
"type" : "timeseries"
2021-08-19 09:57:53 +02:00
} ,
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2021-08-19 09:57:53 +02:00
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
2024-08-21 17:10:29 +02:00
"axisBorderShow" : false ,
2022-09-20 10:01:54 +01:00
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
2021-08-19 09:57:53 +02:00
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
2025-08-01 16:11:32 +05:30
"barWidthFactor" : 0.6 ,
2021-08-19 09:57:53 +02:00
"drawStyle" : "line" ,
2025-08-01 16:11:32 +05:30
"fillOpacity" : 50 ,
2021-08-19 09:57:53 +02:00
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
2024-08-21 17:10:29 +02:00
"insertNulls" : false ,
2021-08-19 09:57:53 +02:00
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
2025-08-01 16:11:32 +05:30
"showPoints" : "never" ,
2021-08-19 09:57:53 +02:00
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
2025-08-01 16:11:32 +05:30
"mode" : "normal"
2021-08-19 09:57:53 +02:00
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
2025-08-01 16:11:32 +05:30
"links" : [ ] ,
2021-08-19 09:57:53 +02:00
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
2025-08-01 16:11:32 +05:30
} ,
"unit" : "short"
2021-08-19 09:57:53 +02:00
} ,
"overrides" : [ ]
} ,
"gridPos" : {
2022-09-20 10:01:54 +01:00
"h" : 6 ,
2022-02-08 12:22:06 +01:00
"w" : 12 ,
2025-08-01 16:11:32 +05:30
"x" : 12 ,
"y" : 53
2021-08-19 09:57:53 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 8 ,
2021-08-19 09:57:53 +02:00
"options" : {
2025-08-01 16:11:32 +05:30
"alertThreshold" : true ,
2021-08-19 09:57:53 +02:00
"legend" : {
2025-08-01 16:11:32 +05:30
"calcs" : [
"mean"
] ,
2021-08-19 09:57:53 +02:00
"displayMode" : "list" ,
2022-09-20 10:01:54 +01:00
"placement" : "bottom" ,
"showLegend" : true
2021-08-19 09:57:53 +02:00
} ,
"tooltip" : {
2025-08-01 16:11:32 +05:30
"hideZeros" : false ,
"mode" : "multi" ,
"sort" : "desc"
2021-08-19 09:57:53 +02:00
}
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2021-08-19 09:57:53 +02:00
"targets" : [
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2025-08-01 16:11:32 +05:30
"expr" : "sum by (instance)(libp2p_pubsub_peers{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"})" ,
2021-08-19 09:57:53 +02:00
"interval" : "" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "{{instance}}" ,
2021-08-19 09:57:53 +02:00
"refId" : "A"
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "LibP2P PubSub Peers" ,
2021-08-19 09:57:53 +02:00
"type" : "timeseries"
} ,
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2021-08-19 09:57:53 +02:00
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
2024-08-21 17:10:29 +02:00
"axisBorderShow" : false ,
2022-09-20 10:01:54 +01:00
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
2021-08-19 09:57:53 +02:00
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
2025-08-01 16:11:32 +05:30
"barWidthFactor" : 0.6 ,
2021-08-19 09:57:53 +02:00
"drawStyle" : "line" ,
2025-08-01 16:11:32 +05:30
"fillOpacity" : 50 ,
2021-08-19 09:57:53 +02:00
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
2024-08-21 17:10:29 +02:00
"insertNulls" : false ,
2021-08-19 09:57:53 +02:00
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
2025-08-01 16:11:32 +05:30
"showPoints" : "never" ,
2021-08-19 09:57:53 +02:00
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
2025-08-01 16:11:32 +05:30
"mode" : "normal"
2021-08-19 09:57:53 +02:00
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
2025-08-01 16:11:32 +05:30
"links" : [ ] ,
2021-08-19 09:57:53 +02:00
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
2025-08-01 16:11:32 +05:30
} ,
"unit" : "short"
2021-08-19 09:57:53 +02:00
} ,
"overrides" : [ ]
} ,
"gridPos" : {
2022-09-20 10:01:54 +01:00
"h" : 6 ,
2022-02-08 12:22:06 +01:00
"w" : 12 ,
2025-08-01 16:11:32 +05:30
"x" : 0 ,
"y" : 59
2021-08-19 09:57:53 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 2 ,
2021-08-19 09:57:53 +02:00
"options" : {
2025-08-01 16:11:32 +05:30
"alertThreshold" : true ,
2021-08-19 09:57:53 +02:00
"legend" : {
2025-08-01 16:11:32 +05:30
"calcs" : [
"mean"
] ,
2021-08-19 09:57:53 +02:00
"displayMode" : "list" ,
2022-09-20 10:01:54 +01:00
"placement" : "bottom" ,
"showLegend" : true
2021-08-19 09:57:53 +02:00
} ,
"tooltip" : {
2025-08-01 16:11:32 +05:30
"hideZeros" : false ,
"mode" : "multi" ,
"sort" : "desc"
2021-08-19 09:57:53 +02:00
}
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2021-08-19 09:57:53 +02:00
"targets" : [
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2025-08-01 16:11:32 +05:30
"expr" : "sum by (instance)(libp2p_peers{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"})" ,
2021-08-19 09:57:53 +02:00
"interval" : "" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "{{instance}}" ,
2021-08-19 09:57:53 +02:00
"refId" : "A"
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "LibP2P Peers" ,
2021-08-19 09:57:53 +02:00
"type" : "timeseries"
} ,
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2022-02-08 12:22:06 +01:00
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
2024-08-21 17:10:29 +02:00
"axisBorderShow" : false ,
2022-09-20 10:01:54 +01:00
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
2022-02-08 12:22:06 +01:00
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
2025-08-01 16:11:32 +05:30
"barWidthFactor" : 0.6 ,
2022-02-08 12:22:06 +01:00
"drawStyle" : "line" ,
2025-08-01 16:11:32 +05:30
"fillOpacity" : 3 ,
2022-02-08 12:22:06 +01:00
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
2024-08-21 17:10:29 +02:00
"insertNulls" : false ,
2022-02-08 12:22:06 +01:00
"lineInterpolation" : "linear" ,
2025-08-01 16:11:32 +05:30
"lineStyle" : {
"fill" : "solid"
} ,
2022-02-08 12:22:06 +01:00
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
2025-08-01 16:11:32 +05:30
"showPoints" : "never" ,
2022-02-08 12:22:06 +01:00
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
2025-08-01 16:11:32 +05:30
"links" : [ ] ,
2022-02-08 12:22:06 +01:00
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
2025-08-01 16:11:32 +05:30
} ,
"unit" : "short"
2022-02-08 12:22:06 +01:00
} ,
2022-09-20 10:01:54 +01:00
"overrides" : [ ]
2022-02-08 12:22:06 +01:00
} ,
"gridPos" : {
2022-09-20 10:01:54 +01:00
"h" : 6 ,
2022-02-08 12:22:06 +01:00
"w" : 12 ,
2025-08-01 16:11:32 +05:30
"x" : 12 ,
"y" : 59
2022-02-08 12:22:06 +01:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 83 ,
2022-02-08 12:22:06 +01:00
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
2022-09-20 10:01:54 +01:00
"placement" : "bottom" ,
"showLegend" : true
2022-02-08 12:22:06 +01:00
} ,
"tooltip" : {
2025-08-01 16:11:32 +05:30
"hideZeros" : false ,
"mode" : "multi" ,
"sort" : "desc"
2022-02-08 12:22:06 +01:00
}
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2022-02-08 12:22:06 +01:00
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-02-08 12:22:06 +01:00
} ,
2022-09-20 10:01:54 +01:00
"editorMode" : "code" ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "(waku_peer_store_size{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"} or logos_delivery_peer_store_size{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"})" ,
2022-02-08 12:22:06 +01:00
"interval" : "" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "{{instance}}" ,
2022-09-20 10:01:54 +01:00
"range" : true ,
2022-02-08 12:22:06 +01:00
"refId" : "A"
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "Peer Store Size" ,
2022-02-08 12:22:06 +01:00
"type" : "timeseries"
} ,
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2021-08-19 09:57:53 +02:00
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
2024-08-21 17:10:29 +02:00
"axisBorderShow" : false ,
2022-09-20 10:01:54 +01:00
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
2021-08-19 09:57:53 +02:00
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
2025-08-01 16:11:32 +05:30
"barWidthFactor" : 0.6 ,
2021-08-19 09:57:53 +02:00
"drawStyle" : "line" ,
2025-08-01 16:11:32 +05:30
"fillOpacity" : 10 ,
2021-08-19 09:57:53 +02:00
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
2024-08-21 17:10:29 +02:00
"insertNulls" : false ,
2021-08-19 09:57:53 +02:00
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
2025-08-01 16:11:32 +05:30
"showPoints" : "never" ,
2021-08-19 09:57:53 +02:00
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
2025-08-01 16:11:32 +05:30
"links" : [ ] ,
2021-08-19 09:57:53 +02:00
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
2025-08-01 16:11:32 +05:30
} ,
"unit" : "short"
2021-08-19 09:57:53 +02:00
} ,
"overrides" : [ ]
} ,
"gridPos" : {
2022-09-20 10:01:54 +01:00
"h" : 6 ,
2022-02-08 12:22:06 +01:00
"w" : 12 ,
2025-08-01 16:11:32 +05:30
"x" : 0 ,
"y" : 65
2021-08-19 09:57:53 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 3 ,
2021-08-19 09:57:53 +02:00
"options" : {
2025-08-01 16:11:32 +05:30
"alertThreshold" : true ,
2021-08-19 09:57:53 +02:00
"legend" : {
2025-08-01 16:11:32 +05:30
"calcs" : [
"mean"
] ,
2021-08-19 09:57:53 +02:00
"displayMode" : "list" ,
2025-08-01 16:11:32 +05:30
"placement" : "right" ,
2022-09-20 10:01:54 +01:00
"showLegend" : true
2021-08-19 09:57:53 +02:00
} ,
"tooltip" : {
2025-08-01 16:11:32 +05:30
"hideZeros" : false ,
"mode" : "multi" ,
"sort" : "desc"
2021-08-19 09:57:53 +02:00
}
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2021-08-19 09:57:53 +02:00
"targets" : [
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2025-08-01 16:11:32 +05:30
"expr" : "sum by (type)(libp2p_open_streams{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"})" ,
2021-08-19 09:57:53 +02:00
"interval" : "" ,
2022-09-20 10:01:54 +01:00
"legendFormat" : "{{type}}" ,
2021-08-19 09:57:53 +02:00
"refId" : "A"
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "LibP2P Open Streams" ,
2021-08-19 09:57:53 +02:00
"type" : "timeseries"
} ,
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
"fieldConfig" : {
"defaults" : {
2025-08-01 16:11:32 +05:30
"color" : {
"mode" : "palette-classic"
} ,
2022-09-20 10:01:54 +01:00
"custom" : {
2025-08-01 16:11:32 +05:30
"axisBorderShow" : false ,
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
"barWidthFactor" : 0.6 ,
"drawStyle" : "line" ,
"fillOpacity" : 10 ,
"gradientMode" : "none" ,
2022-09-20 10:01:54 +01:00
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
2025-08-01 16:11:32 +05:30
"insertNulls" : false ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
2022-09-20 10:01:54 +01:00
"scaleDistribution" : {
"type" : "linear"
2025-08-01 16:11:32 +05:30
} ,
"showPoints" : "never" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
2022-09-20 10:01:54 +01:00
}
2025-08-01 16:11:32 +05:30
} ,
"links" : [ ] ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
} ,
"unit" : "short"
2022-09-20 10:01:54 +01:00
} ,
"overrides" : [ ]
} ,
2021-08-19 09:57:53 +02:00
"gridPos" : {
2025-08-01 16:11:32 +05:30
"h" : 6 ,
2022-09-20 10:01:54 +01:00
"w" : 12 ,
2025-08-01 16:11:32 +05:30
"x" : 12 ,
"y" : 65
2022-09-20 10:01:54 +01:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 9 ,
2022-09-20 10:01:54 +01:00
"options" : {
2025-08-01 16:11:32 +05:30
"alertThreshold" : true ,
2022-09-20 10:01:54 +01:00
"legend" : {
2025-08-01 16:11:32 +05:30
"calcs" : [
"mean"
] ,
"displayMode" : "table" ,
"placement" : "right" ,
"showLegend" : true
2022-09-20 10:01:54 +01:00
} ,
"tooltip" : {
2025-08-01 16:11:32 +05:30
"hideZeros" : false ,
"mode" : "multi" ,
"sort" : "desc"
2022-09-20 10:01:54 +01:00
}
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2022-09-20 10:01:54 +01:00
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2025-08-01 16:11:32 +05:30
"exemplar" : true ,
"expr" : "libp2p_pubsub_validation_success_total{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"}" ,
"hide" : false ,
2022-09-20 10:01:54 +01:00
"interval" : "" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "success {{instance}}" ,
2022-09-20 10:01:54 +01:00
"refId" : "A"
} ,
2021-08-19 09:57:53 +02:00
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2025-08-01 16:11:32 +05:30
"exemplar" : true ,
"expr" : "libp2p_pubsub_validation_failure_total{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"}" ,
2021-08-19 09:57:53 +02:00
"hide" : false ,
"interval" : "" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "failure {{instance}}" ,
2022-09-20 10:01:54 +01:00
"refId" : "B"
2025-08-01 16:11:32 +05:30
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"exemplar" : true ,
"expr" : "libp2p_pubsub_validation_ignore_total{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"}" ,
"hide" : false ,
"interval" : "" ,
"legendFormat" : "ignore {{instance}}" ,
"refId" : "C"
2022-09-20 10:01:54 +01:00
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "LibP2P Validations" ,
"type" : "timeseries"
2022-09-20 10:01:54 +01:00
} ,
2021-08-19 09:57:53 +02:00
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2021-08-19 09:57:53 +02:00
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
2024-08-21 17:10:29 +02:00
"axisBorderShow" : false ,
2022-09-20 10:01:54 +01:00
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
2021-08-19 09:57:53 +02:00
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
2025-08-01 16:11:32 +05:30
"barWidthFactor" : 0.6 ,
2021-08-19 09:57:53 +02:00
"drawStyle" : "line" ,
2025-08-01 16:11:32 +05:30
"fillOpacity" : 10 ,
2021-08-19 09:57:53 +02:00
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
2024-08-21 17:10:29 +02:00
"insertNulls" : false ,
2021-08-19 09:57:53 +02:00
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
2025-08-01 16:11:32 +05:30
"showPoints" : "never" ,
2021-08-19 09:57:53 +02:00
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
2025-08-01 16:11:32 +05:30
"links" : [ ] ,
2021-08-19 09:57:53 +02:00
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"unit" : "short"
2021-08-19 09:57:53 +02:00
} ,
"overrides" : [ ]
} ,
"gridPos" : {
2025-08-01 16:11:32 +05:30
"h" : 6 ,
"w" : 12 ,
2022-09-20 10:01:54 +01:00
"x" : 0 ,
2025-08-01 16:11:32 +05:30
"y" : 71
2021-08-19 09:57:53 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 6 ,
2021-08-19 09:57:53 +02:00
"options" : {
2025-08-01 16:11:32 +05:30
"alertThreshold" : true ,
2021-08-19 09:57:53 +02:00
"legend" : {
2025-08-01 16:11:32 +05:30
"calcs" : [
"mean"
] ,
2021-08-19 09:57:53 +02:00
"displayMode" : "list" ,
2022-09-20 10:01:54 +01:00
"placement" : "bottom" ,
"showLegend" : true
2021-08-19 09:57:53 +02:00
} ,
"tooltip" : {
2025-08-01 16:11:32 +05:30
"hideZeros" : false ,
"mode" : "multi" ,
"sort" : "desc"
2021-08-19 09:57:53 +02:00
}
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2021-08-19 09:57:53 +02:00
"targets" : [
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2025-08-01 16:11:32 +05:30
"expr" : "sum by (instance)(process_open_fds{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"})" ,
"interval" : "" ,
"legendFormat" : "{{instance}}" ,
2021-08-19 09:57:53 +02:00
"refId" : "A"
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "Open File Descriptors" ,
2021-08-19 09:57:53 +02:00
"type" : "timeseries"
} ,
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2021-08-19 09:57:53 +02:00
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
2024-08-21 17:10:29 +02:00
"axisBorderShow" : false ,
2022-09-20 10:01:54 +01:00
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
2021-08-19 09:57:53 +02:00
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
2025-08-01 16:11:32 +05:30
"barWidthFactor" : 0.6 ,
2021-08-19 09:57:53 +02:00
"drawStyle" : "line" ,
2025-08-01 16:11:32 +05:30
"fillOpacity" : 10 ,
2021-08-19 09:57:53 +02:00
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
2024-08-21 17:10:29 +02:00
"insertNulls" : false ,
2021-08-19 09:57:53 +02:00
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
2025-08-01 16:11:32 +05:30
"showPoints" : "never" ,
2021-08-19 09:57:53 +02:00
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
2025-08-01 16:11:32 +05:30
"links" : [ ] ,
2021-08-19 09:57:53 +02:00
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"unit" : "short"
2021-08-19 09:57:53 +02:00
} ,
"overrides" : [ ]
} ,
"gridPos" : {
2025-08-01 16:11:32 +05:30
"h" : 6 ,
"w" : 12 ,
"x" : 12 ,
"y" : 71
2021-08-19 09:57:53 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 7 ,
2021-08-19 09:57:53 +02:00
"options" : {
2025-08-01 16:11:32 +05:30
"alertThreshold" : true ,
2021-08-19 09:57:53 +02:00
"legend" : {
2025-08-01 16:11:32 +05:30
"calcs" : [
"mean"
] ,
2021-08-19 09:57:53 +02:00
"displayMode" : "list" ,
2022-09-20 10:01:54 +01:00
"placement" : "bottom" ,
"showLegend" : true
2021-08-19 09:57:53 +02:00
} ,
"tooltip" : {
2025-08-01 16:11:32 +05:30
"hideZeros" : false ,
"mode" : "multi" ,
"sort" : "desc"
2021-08-19 09:57:53 +02:00
}
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2021-08-19 09:57:53 +02:00
"targets" : [
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2025-08-01 16:11:32 +05:30
"exemplar" : true ,
"expr" : "libp2p_total_dial_attempts_total{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"}" ,
"format" : "time_series" ,
"hide" : false ,
"interval" : "" ,
"legendFormat" : "Attempts: {{instance}}" ,
2021-08-19 09:57:53 +02:00
"refId" : "A"
2025-08-01 16:11:32 +05:30
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"exemplar" : true ,
"expr" : "libp2p_failed_dials_total{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"}" ,
"hide" : false ,
"interval" : "" ,
"legendFormat" : "Failed: {{instance}}" ,
"refId" : "B"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"exemplar" : true ,
"expr" : "libp2p_successful_dials_total{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"}" ,
"hide" : false ,
"interval" : "" ,
"legendFormat" : "Successful: {{instance}}" ,
"refId" : "C"
2021-08-19 09:57:53 +02:00
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "LibP2P Dials" ,
2021-08-19 09:57:53 +02:00
"type" : "timeseries"
} ,
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2021-08-19 09:57:53 +02:00
} ,
2025-08-01 16:11:32 +05:30
"description" : "" ,
2021-08-19 09:57:53 +02:00
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
2024-08-21 17:10:29 +02:00
"axisBorderShow" : false ,
2022-09-20 10:01:54 +01:00
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
2021-08-19 09:57:53 +02:00
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
2025-08-01 16:11:32 +05:30
"barWidthFactor" : 0.6 ,
2021-08-19 09:57:53 +02:00
"drawStyle" : "line" ,
2025-08-01 16:11:32 +05:30
"fillOpacity" : 4 ,
2021-08-19 09:57:53 +02:00
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
2024-08-21 17:10:29 +02:00
"insertNulls" : false ,
2021-08-19 09:57:53 +02:00
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"unit" : "decbytes"
2021-08-19 09:57:53 +02:00
} ,
"overrides" : [ ]
} ,
"gridPos" : {
2025-08-01 16:11:32 +05:30
"h" : 8 ,
"w" : 12 ,
"x" : 0 ,
"y" : 77
2021-08-19 09:57:53 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 44 ,
2021-08-19 09:57:53 +02:00
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
2022-09-20 10:01:54 +01:00
"placement" : "bottom" ,
"showLegend" : true
2021-08-19 09:57:53 +02:00
} ,
"tooltip" : {
2025-08-01 16:11:32 +05:30
"hideZeros" : false ,
2022-09-20 10:01:54 +01:00
"mode" : "single" ,
"sort" : "none"
2021-08-19 09:57:53 +02:00
}
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2021-08-19 09:57:53 +02:00
"targets" : [
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2025-08-01 16:11:32 +05:30
"exemplar" : true ,
"expr" : "nim_gc_mem_bytes{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}" ,
"interval" : "" ,
"legendFormat" : "Nim total memory: {{instance}}" ,
2021-08-19 09:57:53 +02:00
"refId" : "A"
2025-08-01 16:11:32 +05:30
} ,
2022-09-20 10:01:54 +01:00
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2025-08-01 16:11:32 +05:30
"exemplar" : true ,
"expr" : "nim_gc_mem_occupied_bytes{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}" ,
"hide" : false ,
"interval" : "" ,
"legendFormat" : "Nim occupied memory: {{instance}}" ,
"refId" : "B"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"exemplar" : true ,
"expr" : "nim_gc_heap_instance_occupied_summed_bytes{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}" ,
"hide" : false ,
"interval" : "" ,
"legendFormat" : "Nim total heap: {{instance}}" ,
"refId" : "C"
2022-09-20 10:01:54 +01:00
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "Nim Memory Usage" ,
"type" : "timeseries"
2022-09-20 10:01:54 +01:00
} ,
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2021-08-19 09:57:53 +02:00
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
2024-08-21 17:10:29 +02:00
"axisBorderShow" : false ,
2022-09-20 10:01:54 +01:00
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
2021-08-19 09:57:53 +02:00
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
2025-08-01 16:11:32 +05:30
"barWidthFactor" : 0.6 ,
2021-08-19 09:57:53 +02:00
"drawStyle" : "line" ,
2025-08-01 16:11:32 +05:30
"fillOpacity" : 10 ,
2021-08-19 09:57:53 +02:00
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
2024-08-21 17:10:29 +02:00
"insertNulls" : false ,
2021-08-19 09:57:53 +02:00
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
2025-08-01 16:11:32 +05:30
"showPoints" : "never" ,
2021-08-19 09:57:53 +02:00
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
2025-08-01 16:11:32 +05:30
"links" : [ ] ,
2021-08-19 09:57:53 +02:00
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
2025-08-01 16:11:32 +05:30
} ,
"unit" : "percent"
2021-08-19 09:57:53 +02:00
} ,
"overrides" : [ ]
} ,
"gridPos" : {
2025-08-01 16:11:32 +05:30
"h" : 6 ,
"w" : 12 ,
"x" : 12 ,
"y" : 77
2021-08-19 09:57:53 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 10 ,
2021-08-19 09:57:53 +02:00
"options" : {
2025-08-01 16:11:32 +05:30
"alertThreshold" : true ,
2021-08-19 09:57:53 +02:00
"legend" : {
2025-08-01 16:11:32 +05:30
"calcs" : [
"max"
] ,
2021-08-19 09:57:53 +02:00
"displayMode" : "list" ,
2022-09-20 10:01:54 +01:00
"placement" : "bottom" ,
"showLegend" : true
2021-08-19 09:57:53 +02:00
} ,
"tooltip" : {
2025-08-01 16:11:32 +05:30
"hideZeros" : false ,
"mode" : "multi" ,
"sort" : "desc"
2021-08-19 09:57:53 +02:00
}
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2021-08-19 09:57:53 +02:00
"targets" : [
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2021-08-19 09:57:53 +02:00
"exemplar" : true ,
2025-08-01 16:11:32 +05:30
"expr" : "avg by (instance)(netdata_cpu_cpu_percentage_average{dimension=\"user\", instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"})" ,
2024-08-21 17:10:29 +02:00
"hide" : false ,
2021-08-19 09:57:53 +02:00
"interval" : "" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "{{instance}}" ,
2021-08-19 09:57:53 +02:00
"refId" : "A"
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "CPU Usage" ,
2021-08-19 09:57:53 +02:00
"type" : "timeseries"
} ,
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2021-08-19 09:57:53 +02:00
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
2024-08-21 17:10:29 +02:00
"axisBorderShow" : false ,
2022-09-20 10:01:54 +01:00
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
2021-08-19 09:57:53 +02:00
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
2025-08-01 16:11:32 +05:30
"barWidthFactor" : 0.6 ,
2021-08-19 09:57:53 +02:00
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
2024-08-21 17:10:29 +02:00
"insertNulls" : false ,
2021-08-19 09:57:53 +02:00
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
2025-08-01 16:11:32 +05:30
} ,
"unit" : "decbytes"
2021-08-19 09:57:53 +02:00
} ,
"overrides" : [ ]
} ,
"gridPos" : {
2022-09-20 10:01:54 +01:00
"h" : 8 ,
2025-08-01 16:11:32 +05:30
"w" : 12 ,
"x" : 12 ,
"y" : 83
2021-08-19 09:57:53 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 64 ,
2021-08-19 09:57:53 +02:00
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
2022-09-20 10:01:54 +01:00
"placement" : "bottom" ,
"showLegend" : true
2021-08-19 09:57:53 +02:00
} ,
"tooltip" : {
2025-08-01 16:11:32 +05:30
"hideZeros" : false ,
2022-09-20 10:01:54 +01:00
"mode" : "single" ,
"sort" : "none"
2021-08-19 09:57:53 +02:00
}
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2021-08-19 09:57:53 +02:00
"targets" : [
{
2022-09-20 10:01:54 +01:00
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2022-09-20 10:01:54 +01:00
} ,
2021-08-19 09:57:53 +02:00
"exemplar" : true ,
2025-08-01 16:11:32 +05:30
"expr" : "nim_gc_heap_instance_occupied_bytes{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}" ,
2021-08-19 09:57:53 +02:00
"interval" : "" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "{{instance}} {{type_name}}" ,
2021-08-19 09:57:53 +02:00
"refId" : "A"
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "Heap allocation" ,
2024-08-21 17:10:29 +02:00
"type" : "timeseries"
} ,
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2024-08-21 17:10:29 +02:00
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisBorderShow" : false ,
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
2025-08-01 16:11:32 +05:30
"barWidthFactor" : 0.6 ,
2024-08-21 17:10:29 +02:00
"drawStyle" : "line" ,
2025-08-01 16:11:32 +05:30
"fillOpacity" : 10 ,
2024-08-21 17:10:29 +02:00
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"insertNulls" : false ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
2025-08-01 16:11:32 +05:30
"showPoints" : "never" ,
2024-08-21 17:10:29 +02:00
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
2025-08-01 16:11:32 +05:30
"links" : [ ] ,
2024-08-21 17:10:29 +02:00
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
2025-08-01 16:11:32 +05:30
} ,
"unit" : "decbytes"
2024-08-21 17:10:29 +02:00
} ,
"overrides" : [ ]
} ,
"gridPos" : {
2025-08-01 16:11:32 +05:30
"h" : 6 ,
"w" : 12 ,
"x" : 0 ,
"y" : 85
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 4 ,
2024-08-21 17:10:29 +02:00
"options" : {
2025-08-01 16:11:32 +05:30
"alertThreshold" : true ,
2024-08-21 17:10:29 +02:00
"legend" : {
2025-08-01 16:11:32 +05:30
"calcs" : [
"mean"
] ,
2024-08-21 17:10:29 +02:00
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
2025-08-01 16:11:32 +05:30
"hideZeros" : false ,
"mode" : "multi" ,
"sort" : "desc"
2024-08-21 17:10:29 +02:00
}
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2024-08-21 17:10:29 +02:00
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"expr" : "sum by (instance)(process_virtual_memory_bytes{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"})" ,
2024-08-21 17:10:29 +02:00
"interval" : "" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "{{instance}}" ,
2024-08-21 17:10:29 +02:00
"refId" : "A"
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "Virtual Memory" ,
2024-08-21 17:10:29 +02:00
"type" : "timeseries"
} ,
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2024-08-21 17:10:29 +02:00
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisBorderShow" : false ,
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
2025-08-01 16:11:32 +05:30
"barWidthFactor" : 0.6 ,
2024-08-21 17:10:29 +02:00
"drawStyle" : "line" ,
2025-08-01 16:11:32 +05:30
"fillOpacity" : 10 ,
2024-08-21 17:10:29 +02:00
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"insertNulls" : false ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
2025-08-01 16:11:32 +05:30
"showPoints" : "never" ,
2024-08-21 17:10:29 +02:00
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
2025-08-01 16:11:32 +05:30
"links" : [ ] ,
2024-08-21 17:10:29 +02:00
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
} ,
2025-08-01 16:11:32 +05:30
"unit" : "decbytes"
2024-08-21 17:10:29 +02:00
} ,
"overrides" : [ ]
} ,
"gridPos" : {
2025-08-01 16:11:32 +05:30
"h" : 6 ,
"w" : 12 ,
"x" : 12 ,
"y" : 91
} ,
"id" : 5 ,
"options" : {
"alertThreshold" : true ,
"legend" : {
"calcs" : [
"mean"
] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
"hideZeros" : false ,
"mode" : "multi" ,
"sort" : "desc"
}
} ,
"pluginVersion" : "11.5.2" ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"expr" : "sum by (instance)(process_resident_memory_bytes{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"})" ,
"interval" : "" ,
"legendFormat" : "{{instance}}" ,
"refId" : "A"
}
] ,
"title" : "Resident Memory" ,
"type" : "timeseries"
} ,
{
"collapsed" : true ,
"gridPos" : {
"h" : 1 ,
"w" : 24 ,
"x" : 0 ,
"y" : 97
} ,
"id" : 72 ,
"panels" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
"drawStyle" : "line" ,
"fillOpacity" : 3 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green"
} ,
{
"color" : "red" ,
"value" : 80
}
]
}
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 8 ,
"w" : 12 ,
"x" : 0 ,
"y" : 122
} ,
"id" : 70 ,
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
"mode" : "single" ,
"sort" : "none"
}
} ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"exemplar" : true ,
"expr" : "increase(waku_bridge_transfers_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[10m])" ,
"interval" : "" ,
"legendFormat" : "{{fleet}} : {{type}}" ,
"refId" : "A"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"exemplar" : true ,
"expr" : "increase(envelopes_valid_total{instance=~\"bridge*[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[10m])" ,
"hide" : false ,
"interval" : "" ,
"legendFormat" : "{{fleet}} : v1_envelopes" ,
"refId" : "B"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"exemplar" : true ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "(increase(waku_node_messages_total{instance=~\"bridge*[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[10m]) or increase(logos_delivery_node_messages_total{instance=~\"bridge*[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[10m]))" ,
2025-08-01 16:11:32 +05:30
"hide" : false ,
"interval" : "" ,
"legendFormat" : "{{fleet}} : v2_messages" ,
"refId" : "C"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"exemplar" : true ,
"expr" : "increase(envelopes_dropped_total{instance=~\"bridge*[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[10m])" ,
"hide" : false ,
"interval" : "" ,
"legendFormat" : "{{fleet}} : v1_envelopes_dropped ({{reason}})" ,
"refId" : "D"
}
] ,
"title" : "Bridge (10m rate)" ,
"type" : "timeseries"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green"
} ,
{
"color" : "red" ,
"value" : 80
}
]
}
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 8 ,
"w" : 12 ,
"x" : 12 ,
"y" : 122
} ,
"id" : 74 ,
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
"mode" : "multi" ,
"sort" : "none"
}
} ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"exemplar" : true ,
"expr" : "connected_peers{instance=~\"bridge*[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}" ,
"interval" : "" ,
"legendFormat" : "v1_connected_peers" ,
"refId" : "A"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"exemplar" : true ,
"expr" : "libp2p_pubsub_peers{instance=~\"bridge*[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}" ,
"hide" : false ,
"interval" : "" ,
"legendFormat" : "v2_connected_peers" ,
"refId" : "B"
}
] ,
"title" : "Connected Peers" ,
"type" : "timeseries"
}
] ,
"title" : "Bridge" ,
"type" : "row"
} ,
{
"collapsed" : true ,
"gridPos" : {
"h" : 1 ,
"w" : 24 ,
"x" : 0 ,
"y" : 98
} ,
"id" : 34 ,
"panels" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green"
} ,
{
"color" : "red" ,
"value" : 80
}
]
}
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 6 ,
"w" : 12 ,
"x" : 0 ,
"y" : 99
} ,
"id" : 36 ,
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
"mode" : "single" ,
"sort" : "none"
}
} ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"exemplar" : true ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "(waku_store_peers{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"} or logos_delivery_store_peers{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"})" ,
2025-08-01 16:11:32 +05:30
"interval" : "" ,
"legendFormat" : "{{instance}}" ,
"refId" : "A"
}
] ,
"title" : "Waku Store Peers" ,
"type" : "timeseries"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
"drawStyle" : "line" ,
"fillOpacity" : 2 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green"
} ,
{
"color" : "red" ,
"value" : 80
}
]
}
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 6 ,
"w" : 12 ,
"x" : 12 ,
"y" : 99
} ,
"id" : 38 ,
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : false
} ,
"tooltip" : {
"mode" : "multi" ,
"sort" : "none"
}
} ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"editorMode" : "code" ,
"exemplar" : true ,
"expr" : "waku_store_messages{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}" ,
"hide" : false ,
"interval" : "" ,
"legendFormat" : "{{type}}: {{instance}}" ,
"range" : true ,
"refId" : "A"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"editorMode" : "code" ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "(waku_archive_messages{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"} or logos_delivery_archive_messages{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"})" ,
2025-08-01 16:11:32 +05:30
"hide" : false ,
"legendFormat" : "{{type}}: {{instance}}" ,
"range" : true ,
"refId" : "B"
}
] ,
"title" : "Waku Archive Messages" ,
"type" : "timeseries"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
"drawStyle" : "line" ,
"fillOpacity" : 3 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green"
} ,
{
"color" : "red" ,
"value" : 80
}
]
}
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 6 ,
"w" : 12 ,
"x" : 0 ,
"y" : 105
} ,
"id" : 62 ,
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
"mode" : "single" ,
"sort" : "none"
}
} ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"editorMode" : "code" ,
"exemplar" : true ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "(increase(waku_store_queries_total{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"}[1m]) or increase(logos_delivery_store_queries_total{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"}[1m]))" ,
2025-08-01 16:11:32 +05:30
"interval" : "" ,
"legendFormat" : "{{instance}}" ,
"range" : true ,
"refId" : "A"
}
] ,
"title" : "Waku Store Queries (1m rate)" ,
"type" : "timeseries"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green"
} ,
{
"color" : "red" ,
"value" : 80
}
]
}
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 6 ,
"w" : 12 ,
"x" : 12 ,
"y" : 105
} ,
"id" : 40 ,
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
"mode" : "single" ,
"sort" : "none"
}
} ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"editorMode" : "code" ,
"exemplar" : true ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "sum by (type)((increase(waku_archive_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[1m]) or increase(logos_delivery_archive_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[1m])))" ,
2025-08-01 16:11:32 +05:30
"hide" : false ,
"interval" : "" ,
"legendFormat" : "{{type}}" ,
"range" : true ,
"refId" : "A"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"editorMode" : "code" ,
"exemplar" : true ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "sum by (type)((increase(waku_store_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[1m]) or increase(logos_delivery_store_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[1m])))" ,
2025-08-01 16:11:32 +05:30
"hide" : false ,
"interval" : "" ,
"legendFormat" : "{{type}}" ,
"range" : true ,
"refId" : "B"
}
] ,
"title" : "Waku Archive Errors (1m rate)" ,
"type" : "timeseries"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"fieldConfig" : {
"defaults" : {
"custom" : {
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"scaleDistribution" : {
"type" : "linear"
}
}
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 7 ,
"w" : 12 ,
"x" : 0 ,
"y" : 111
} ,
"id" : 77 ,
"maxDataPoints" : 60 ,
"options" : {
"calculate" : false ,
"calculation" : { } ,
"cellGap" : 2 ,
"cellValues" : { } ,
"color" : {
"exponent" : 0.5 ,
"fill" : "#b4ff00" ,
"mode" : "scheme" ,
"reverse" : false ,
"scale" : "exponential" ,
"scheme" : "RdYlGn" ,
"steps" : 128
} ,
"exemplars" : {
"color" : "rgba(255,0,255,0.7)"
} ,
"filterValues" : {
"le" : 1e-9
} ,
"legend" : {
"show" : false
} ,
"rowsFrame" : {
"layout" : "auto"
} ,
"showValue" : "never" ,
"tooltip" : {
"show" : true ,
"yHistogram" : true
} ,
"yAxis" : {
"axisPlacement" : "left" ,
"decimals" : 0 ,
"reverse" : false ,
"unit" : "s"
}
} ,
"pluginVersion" : "9.2.5" ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"editorMode" : "code" ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "sum((increase(waku_archive_query_duration_seconds_bucket{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval]) or increase(logos_delivery_archive_query_duration_seconds_bucket{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval]))) by (le)" ,
2025-08-01 16:11:32 +05:30
"format" : "heatmap" ,
"hide" : false ,
"legendFormat" : "{{le}}" ,
"range" : true ,
"refId" : "B"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"editorMode" : "code" ,
"expr" : "sum(increase(waku_store_query_duration_seconds_bucket{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval])) by (le)" ,
"format" : "heatmap" ,
"hide" : true ,
"legendFormat" : "{{le}}" ,
"range" : true ,
"refId" : "A"
}
] ,
"title" : "Waku Archive Query Duration" ,
"type" : "heatmap"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"fieldConfig" : {
"defaults" : {
"custom" : {
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"scaleDistribution" : {
"type" : "linear"
}
}
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 7 ,
"w" : 12 ,
"x" : 12 ,
"y" : 111
} ,
"id" : 75 ,
"maxDataPoints" : 60 ,
"options" : {
"calculate" : false ,
"calculation" : { } ,
"cellGap" : 2 ,
"cellValues" : { } ,
"color" : {
"exponent" : 0.5 ,
"fill" : "#b4ff00" ,
"mode" : "scheme" ,
"reverse" : false ,
"scale" : "exponential" ,
"scheme" : "RdYlGn" ,
"steps" : 128
} ,
"exemplars" : {
"color" : "rgba(255,0,255,0.7)"
} ,
"filterValues" : {
"le" : 1e-9
} ,
"legend" : {
"show" : false
} ,
"rowsFrame" : {
"layout" : "auto"
} ,
"showValue" : "never" ,
"tooltip" : {
"show" : true ,
"yHistogram" : true
} ,
"yAxis" : {
"axisPlacement" : "left" ,
"decimals" : 0 ,
"reverse" : false ,
"unit" : "s"
}
} ,
"pluginVersion" : "9.2.5" ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"editorMode" : "code" ,
"exemplar" : true ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "sum((increase(waku_archive_insert_duration_seconds_bucket{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval]) or increase(logos_delivery_archive_insert_duration_seconds_bucket{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval]))) by (le)" ,
2025-08-01 16:11:32 +05:30
"format" : "heatmap" ,
"hide" : false ,
"instant" : false ,
"interval" : "" ,
"intervalFactor" : 1 ,
"legendFormat" : "{{le}}" ,
"refId" : "B"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"editorMode" : "code" ,
"exemplar" : true ,
"expr" : "sum(increase(waku_store_insert_duration_seconds_bucket{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval])) by (le)" ,
"format" : "heatmap" ,
"hide" : true ,
"instant" : false ,
"interval" : "" ,
"intervalFactor" : 1 ,
"legendFormat" : "{{le}}" ,
"refId" : "A"
}
] ,
"title" : "Waku Archive Insert Duration" ,
"type" : "heatmap"
}
] ,
"title" : "Store/Archive" ,
"type" : "row"
} ,
{
"collapsed" : true ,
"gridPos" : {
"h" : 1 ,
"w" : 24 ,
"x" : 0 ,
"y" : 99
} ,
"id" : 87 ,
"panels" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green"
} ,
{
"color" : "red" ,
"value" : 80
}
]
}
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 8 ,
"w" : 8 ,
"x" : 0 ,
"y" : 135
} ,
"id" : 93 ,
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
"mode" : "single" ,
"sort" : "none"
}
} ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"editorMode" : "code" ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "(waku_filter_requests_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"} or logos_delivery_filter_requests_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"})" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "{{type}} : {{instance}}" ,
"range" : true ,
"refId" : "A"
}
] ,
"title" : "Waku Filter Requests" ,
"type" : "timeseries"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green"
} ,
{
"color" : "red" ,
"value" : 80
}
]
}
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 8 ,
"w" : 8 ,
"x" : 8 ,
"y" : 135
} ,
"id" : 89 ,
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
"mode" : "single" ,
"sort" : "none"
}
} ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"editorMode" : "code" ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "(waku_filter_subscriptions{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"} or logos_delivery_filter_subscriptions{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"})" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "{{instance}}" ,
"range" : true ,
"refId" : "A"
}
] ,
"title" : "Waku Filter Subscriptions" ,
"type" : "timeseries"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green"
} ,
{
"color" : "red" ,
"value" : 80
}
]
}
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 8 ,
"w" : 8 ,
"x" : 16 ,
"y" : 135
} ,
"id" : 91 ,
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
"mode" : "single" ,
"sort" : "none"
}
} ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"editorMode" : "code" ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "(waku_filter_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"} or logos_delivery_filter_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"})" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "{{type}} : {{instance}}" ,
"range" : true ,
"refId" : "A"
}
] ,
"title" : "Waku Filter Errors" ,
"type" : "timeseries"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"fieldConfig" : {
"defaults" : {
"custom" : {
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"scaleDistribution" : {
"type" : "linear"
}
}
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 8 ,
"w" : 12 ,
"x" : 0 ,
"y" : 143
} ,
"id" : 95 ,
"options" : {
"calculate" : false ,
"cellGap" : 2 ,
"color" : {
"exponent" : 0.5 ,
"fill" : "dark-orange" ,
"mode" : "scheme" ,
"reverse" : false ,
"scale" : "exponential" ,
"scheme" : "RdYlGn" ,
"steps" : 128
} ,
"exemplars" : {
"color" : "rgba(255,0,255,0.7)"
} ,
"filterValues" : {
"le" : 1e-9
} ,
"legend" : {
"show" : false
} ,
"rowsFrame" : {
"layout" : "auto"
} ,
"tooltip" : {
"show" : true ,
"yHistogram" : true
} ,
"yAxis" : {
"axisPlacement" : "left" ,
"decimals" : 0 ,
"reverse" : false ,
"unit" : "s"
}
} ,
"pluginVersion" : "9.2.5" ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"editorMode" : "code" ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "sum((increase(waku_filter_request_duration_seconds_bucket{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval]) or increase(logos_delivery_filter_request_duration_seconds_bucket{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval]))) by (le)" ,
2025-08-01 16:11:32 +05:30
"format" : "heatmap" ,
"interval" : "" ,
"legendFormat" : "{{le}}" ,
"range" : true ,
"refId" : "A"
}
] ,
"title" : "Waku Filter Request Duration" ,
"type" : "heatmap"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"fieldConfig" : {
"defaults" : {
"custom" : {
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"scaleDistribution" : {
"type" : "linear"
}
}
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 8 ,
"w" : 12 ,
"x" : 12 ,
"y" : 143
} ,
"id" : 97 ,
"options" : {
"calculate" : false ,
"cellGap" : 2 ,
"color" : {
"exponent" : 0.5 ,
"fill" : "dark-orange" ,
"mode" : "scheme" ,
"reverse" : false ,
"scale" : "exponential" ,
"scheme" : "RdYlGn" ,
"steps" : 128
} ,
"exemplars" : {
"color" : "rgba(255,0,255,0.7)"
} ,
"filterValues" : {
"le" : 1e-9
} ,
"legend" : {
"show" : false
} ,
"rowsFrame" : {
"layout" : "auto"
} ,
"tooltip" : {
"show" : true ,
"yHistogram" : false
} ,
"yAxis" : {
"axisPlacement" : "left" ,
"decimals" : 0 ,
"reverse" : false ,
"unit" : "s"
}
} ,
"pluginVersion" : "9.2.5" ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"editorMode" : "code" ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "sum((increase(waku_filter_handle_message_duration_seconds_bucket{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval]) or increase(logos_delivery_filter_handle_message_duration_seconds_bucket{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}[$__rate_interval]))) by (le)" ,
2025-08-01 16:11:32 +05:30
"format" : "heatmap" ,
"legendFormat" : "{{le}}" ,
"range" : true ,
"refId" : "A"
}
] ,
"title" : "Waku Filter Handle Message Duration" ,
"type" : "heatmap"
}
] ,
"title" : "Filter" ,
"type" : "row"
} ,
{
"collapsed" : true ,
"gridPos" : {
"h" : 1 ,
"w" : 24 ,
"x" : 0 ,
"y" : 100
} ,
"id" : 20 ,
"panels" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"description" : "Waku Filter Peers" ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green"
} ,
{
"color" : "red" ,
"value" : 80
}
]
}
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 8 ,
"w" : 12 ,
"x" : 0 ,
"y" : 149
} ,
"id" : 22 ,
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
"mode" : "single" ,
"sort" : "none"
}
} ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"exemplar" : true ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "(waku_filter_peers{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"} or logos_delivery_filter_peers{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"})" ,
2025-08-01 16:11:32 +05:30
"hide" : false ,
"interval" : "" ,
"legendFormat" : "{{instance}}" ,
"refId" : "A"
}
] ,
"title" : "Waku Filter Peers" ,
"type" : "timeseries"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"description" : "" ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green"
} ,
{
"color" : "red" ,
"value" : 80
}
]
}
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 8 ,
"w" : 12 ,
"x" : 12 ,
"y" : 149
} ,
"id" : 26 ,
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
"mode" : "single" ,
"sort" : "none"
}
} ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"editorMode" : "code" ,
"exemplar" : true ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "(waku_filter_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"} or logos_delivery_filter_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"})" ,
2025-08-01 16:11:32 +05:30
"interval" : "" ,
"legendFormat" : "{{type}}: {{instance}}" ,
"range" : true ,
"refId" : "A"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"editorMode" : "code" ,
"expr" : "waku_legacy_filter_errors{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}" ,
"hide" : false ,
"legendFormat" : "{{type}} : {{instance}}" ,
"range" : true ,
"refId" : "B"
}
] ,
"title" : "Waku Filter Errors" ,
"type" : "timeseries"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green"
} ,
{
"color" : "red" ,
"value" : 80
}
]
}
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 8 ,
"w" : 12 ,
"x" : 0 ,
"y" : 157
} ,
"id" : 99 ,
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
"mode" : "single" ,
"sort" : "none"
}
} ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"editorMode" : "code" ,
"expr" : "waku_filter_messages{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}" ,
"legendFormat" : "{{type}} : {{instance}}" ,
"range" : true ,
"refId" : "A"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"editorMode" : "code" ,
"expr" : "waku_legacy_filter_messages{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}" ,
"hide" : false ,
"legendFormat" : "{{type}} : {{instance}}" ,
"range" : true ,
"refId" : "B"
}
] ,
"title" : "Waku Filter Messages" ,
"type" : "timeseries"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
"drawStyle" : "line" ,
"fillOpacity" : 3 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green"
} ,
{
"color" : "red" ,
"value" : 80
}
]
}
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 7 ,
"w" : 12 ,
"x" : 12 ,
"y" : 157
} ,
"id" : 24 ,
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
"mode" : "single" ,
"sort" : "none"
}
} ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"editorMode" : "code" ,
"exemplar" : true ,
"expr" : "waku_filter_subscribers{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}" ,
"interval" : "" ,
"legendFormat" : "{{instance}}" ,
"range" : true ,
"refId" : "A"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"editorMode" : "code" ,
"expr" : "waku_legacy_filter_subscribers{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"}" ,
"hide" : false ,
"legendFormat" : "{{instance}}" ,
"range" : true ,
"refId" : "B"
}
] ,
"title" : "Waku Filter Subscribers" ,
"type" : "timeseries"
}
] ,
"title" : "Filter (Legacy)" ,
"type" : "row"
} ,
{
"collapsed" : true ,
"gridPos" : {
"h" : 1 ,
"w" : 24 ,
2024-08-21 17:10:29 +02:00
"x" : 0 ,
2025-08-01 16:11:32 +05:30
"y" : 101
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 28 ,
"panels" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green"
} ,
{
"color" : "red" ,
"value" : 80
}
]
}
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 8 ,
"w" : 12 ,
"x" : 0 ,
"y" : 129
} ,
"id" : 30 ,
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
"mode" : "single" ,
"sort" : "none"
}
} ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"exemplar" : true ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "(waku_lightpush_peers{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"} or logos_delivery_lightpush_peers{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"})" ,
2025-08-01 16:11:32 +05:30
"interval" : "" ,
"legendFormat" : "{{instance}}" ,
"refId" : "A"
}
] ,
"title" : "Waku Lightpush Peers" ,
"type" : "timeseries"
2024-08-21 17:10:29 +02:00
} ,
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green"
} ,
{
"color" : "red" ,
"value" : 80
}
]
}
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 8 ,
"w" : 12 ,
"x" : 12 ,
"y" : 129
} ,
"id" : 32 ,
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
"mode" : "single" ,
"sort" : "none"
}
} ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"exemplar" : true ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "(waku_lightpush_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"} or logos_delivery_lightpush_errors_total{instance=~\"[[host]].([[dc:pipe]]).*.([[fleet:pipe]])\"})" ,
2025-08-01 16:11:32 +05:30
"interval" : "" ,
"legendFormat" : "{{type}}: {[instance}}" ,
"refId" : "A"
}
] ,
"title" : "Waku Lightpush Errors" ,
"type" : "timeseries"
2024-08-21 17:10:29 +02:00
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "Lightpush" ,
"type" : "row"
2024-08-21 17:10:29 +02:00
} ,
{
2025-08-01 16:11:32 +05:30
"collapsed" : true ,
"gridPos" : {
"h" : 1 ,
"w" : 24 ,
"x" : 0 ,
"y" : 102
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 15 ,
"panels" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green"
}
]
} ,
"unit" : "none"
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 8 ,
"w" : 12 ,
"x" : 0 ,
"y" : 122
} ,
"id" : 103 ,
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "right" ,
"showLegend" : true
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"tooltip" : {
"mode" : "single" ,
"sort" : "none"
}
} ,
"pluginVersion" : "9.2.5" ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"editorMode" : "code" ,
"exemplar" : false ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "((increase(waku_node_messages_total{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"}[1m]) or increase(logos_delivery_node_messages_total{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"}[1m])))/60" ,
2025-08-01 16:11:32 +05:30
"format" : "heatmap" ,
"instant" : false ,
"legendFormat" : "{{fleet}}_{{datacenter}}" ,
"range" : true ,
"refId" : "A"
}
] ,
"title" : "Messages/second" ,
"type" : "timeseries"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green"
}
]
} ,
"unit" : "deckbytes"
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 8 ,
"w" : 12 ,
"x" : 12 ,
"y" : 122
} ,
"id" : 102 ,
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "right" ,
"showLegend" : true
} ,
"tooltip" : {
"mode" : "single" ,
"sort" : "none"
2024-08-21 17:10:29 +02:00
}
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "9.2.5" ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"editorMode" : "code" ,
"exemplar" : false ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "(waku_histogram_message_size_sum{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"} or logos_delivery_histogram_message_size_sum{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"})/(waku_histogram_message_size_count{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"} or logos_delivery_histogram_message_size_count{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"})" ,
2025-08-01 16:11:32 +05:30
"format" : "heatmap" ,
"instant" : false ,
"legendFormat" : "{{fleet}}_{{datacenter}}" ,
"range" : true ,
"refId" : "A"
}
] ,
"title" : "Average msg size (kBytes)" ,
"type" : "timeseries"
} ,
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "thresholds"
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green"
}
]
} ,
"unit" : "percent"
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 8 ,
"w" : 24 ,
"x" : 0 ,
"y" : 130
} ,
"id" : 101 ,
"options" : {
"displayMode" : "gradient" ,
"minVizHeight" : 10 ,
"minVizWidth" : 0 ,
"orientation" : "auto" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
} ,
"showUnfilled" : true
} ,
"pluginVersion" : "9.2.5" ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"editorMode" : "code" ,
"exemplar" : false ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "(rate(waku_histogram_message_size_bucket{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"}[1h]) or rate(logos_delivery_histogram_message_size_bucket{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"}[1h]))/scalar((rate(waku_histogram_message_size_count{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"}[1h]) or rate(logos_delivery_histogram_message_size_count{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"}[1h])))*100" ,
2025-08-01 16:11:32 +05:30
"format" : "heatmap" ,
"instant" : false ,
"legendFormat" : "{{le}}" ,
"range" : true ,
"refId" : "A"
}
] ,
"title" : "Message distrubution %/kBytes (Last Hour)" ,
"type" : "bargauge"
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "thresholds"
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green"
}
]
} ,
"unit" : "none"
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 8 ,
"w" : 12 ,
"x" : 0 ,
"y" : 138
} ,
"id" : 105 ,
"options" : {
"colorMode" : "value" ,
"graphMode" : "none" ,
"justifyMode" : "auto" ,
"orientation" : "auto" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
} ,
"text" : {
"titleSize" : 15 ,
"valueSize" : 50
} ,
"textMode" : "auto"
} ,
"pluginVersion" : "9.2.5" ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"editorMode" : "code" ,
"exemplar" : false ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "(waku_connected_peers{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"} or logos_delivery_connected_peers{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"})" ,
2025-08-01 16:11:32 +05:30
"format" : "heatmap" ,
"instant" : false ,
"legendFormat" : "Direction:{{direction}} {{protocol}}" ,
"range" : true ,
"refId" : "A"
}
] ,
"title" : "Connected Peers per Protocol" ,
"type" : "stat"
2024-08-21 17:10:29 +02:00
} ,
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "thresholds"
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green"
}
]
} ,
"unit" : "none"
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 8 ,
"w" : 12 ,
"x" : 12 ,
"y" : 138
} ,
"id" : 104 ,
"options" : {
"colorMode" : "value" ,
"graphMode" : "none" ,
"justifyMode" : "auto" ,
"orientation" : "auto" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
} ,
"text" : {
"titleSize" : 15 ,
"valueSize" : 50
} ,
"textMode" : "auto"
} ,
"pluginVersion" : "9.2.5" ,
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"editorMode" : "code" ,
"exemplar" : false ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "(waku_streams_peers{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"} or logos_delivery_streams_peers{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"})" ,
2025-08-01 16:11:32 +05:30
"format" : "heatmap" ,
"instant" : false ,
"legendFormat" : "Direction:{{direction}} {{protocol}}" ,
"range" : true ,
"refId" : "A"
}
] ,
"title" : "Connected Streams per Protocol" ,
"type" : "stat"
2024-08-21 17:10:29 +02:00
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "Messages" ,
"type" : "row"
2024-08-21 17:10:29 +02:00
} ,
{
"collapsed" : false ,
"gridPos" : {
"h" : 1 ,
"w" : 24 ,
"x" : 0 ,
2025-08-01 16:11:32 +05:30
"y" : 103
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 112 ,
2024-08-21 17:10:29 +02:00
"panels" : [ ] ,
2025-08-01 16:11:32 +05:30
"title" : "RLN" ,
2024-08-21 17:10:29 +02:00
"type" : "row"
} ,
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2024-08-21 17:10:29 +02:00
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisBorderShow" : false ,
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
2025-08-01 16:11:32 +05:30
"barWidthFactor" : 0.6 ,
2024-08-21 17:10:29 +02:00
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"insertNulls" : false ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
}
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 8 ,
"w" : 12 ,
"x" : 0 ,
2025-08-01 16:11:32 +05:30
"y" : 104
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 107 ,
2024-08-21 17:10:29 +02:00
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
2025-08-01 16:11:32 +05:30
"hideZeros" : false ,
2024-08-21 17:10:29 +02:00
"mode" : "single" ,
"sort" : "none"
}
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2024-08-21 17:10:29 +02:00
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"editorMode" : "code" ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "(waku_rln_invalid_messages_total_total{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"} or logos_delivery_rln_invalid_messages_total_total{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"})" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "{{type}}_{{datacenter}}" ,
"range" : true ,
2024-08-21 17:10:29 +02:00
"refId" : "A"
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "Invalid Messages" ,
2024-08-21 17:10:29 +02:00
"type" : "timeseries"
} ,
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2024-08-21 17:10:29 +02:00
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisBorderShow" : false ,
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
2025-08-01 16:11:32 +05:30
"barWidthFactor" : 0.6 ,
2024-08-21 17:10:29 +02:00
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"insertNulls" : false ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
}
} ,
"overrides" : [ ]
} ,
"gridPos" : {
"h" : 8 ,
"w" : 12 ,
"x" : 12 ,
2025-08-01 16:11:32 +05:30
"y" : 104
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 110 ,
2024-08-21 17:10:29 +02:00
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
2025-08-01 16:11:32 +05:30
"hideZeros" : false ,
2024-08-21 17:10:29 +02:00
"mode" : "single" ,
"sort" : "none"
}
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2024-08-21 17:10:29 +02:00
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"editorMode" : "code" ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "(waku_rln_valid_messages_total_count{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"} or logos_delivery_rln_valid_messages_total_count{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"})" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "{{__name__}}_{{datacenter}}" ,
"range" : true ,
2024-08-21 17:10:29 +02:00
"refId" : "A"
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "Valid RLN Messages" ,
2024-08-21 17:10:29 +02:00
"type" : "timeseries"
} ,
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2024-08-21 17:10:29 +02:00
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisBorderShow" : false ,
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
2025-08-01 16:11:32 +05:30
"barWidthFactor" : 0.6 ,
2024-08-21 17:10:29 +02:00
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"insertNulls" : false ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
2025-08-01 16:11:32 +05:30
}
2024-08-21 17:10:29 +02:00
} ,
"overrides" : [ ]
} ,
"gridPos" : {
2025-08-01 16:11:32 +05:30
"h" : 8 ,
"w" : 12 ,
2024-08-21 17:10:29 +02:00
"x" : 0 ,
2025-08-01 16:11:32 +05:30
"y" : 112
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 109 ,
2024-08-21 17:10:29 +02:00
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
2025-08-01 16:11:32 +05:30
"hideZeros" : false ,
2024-08-21 17:10:29 +02:00
"mode" : "single" ,
"sort" : "none"
}
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2024-08-21 17:10:29 +02:00
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2024-08-21 17:10:29 +02:00
} ,
"editorMode" : "code" ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "(waku_rln_spam_messages_total_total{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"} or logos_delivery_rln_spam_messages_total_total{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"})" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "{{__name__}}_{{datacenter}}" ,
2024-08-21 17:10:29 +02:00
"range" : true ,
"refId" : "A"
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "Spam messages" ,
2024-08-21 17:10:29 +02:00
"type" : "timeseries"
} ,
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2024-08-21 17:10:29 +02:00
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisBorderShow" : false ,
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
2025-08-01 16:11:32 +05:30
"barWidthFactor" : 0.6 ,
2024-08-21 17:10:29 +02:00
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"insertNulls" : false ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
2025-08-01 16:11:32 +05:30
}
2024-08-21 17:10:29 +02:00
} ,
"overrides" : [ ]
} ,
"gridPos" : {
2025-08-01 16:11:32 +05:30
"h" : 8 ,
"w" : 12 ,
"x" : 12 ,
"y" : 112
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 108 ,
2024-08-21 17:10:29 +02:00
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
2025-08-01 16:11:32 +05:30
"hideZeros" : false ,
2024-08-21 17:10:29 +02:00
"mode" : "single" ,
"sort" : "none"
}
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2024-08-21 17:10:29 +02:00
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2024-08-21 17:10:29 +02:00
} ,
"editorMode" : "code" ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "(waku_rln_proof_verification_duration_seconds{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"} or logos_delivery_rln_proof_verification_duration_seconds{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"})" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "{{__name__}}_{{datacenter}}" ,
2024-08-21 17:10:29 +02:00
"range" : true ,
"refId" : "A"
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "Proof Verification (s)" ,
2024-08-21 17:10:29 +02:00
"type" : "timeseries"
} ,
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2024-08-21 17:10:29 +02:00
} ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"custom" : {
"axisBorderShow" : false ,
"axisCenteredZero" : false ,
"axisColorMode" : "text" ,
"axisLabel" : "" ,
"axisPlacement" : "auto" ,
"barAlignment" : 0 ,
2025-08-01 16:11:32 +05:30
"barWidthFactor" : 0.6 ,
2024-08-21 17:10:29 +02:00
"drawStyle" : "line" ,
"fillOpacity" : 0 ,
"gradientMode" : "none" ,
"hideFrom" : {
"legend" : false ,
"tooltip" : false ,
"viz" : false
} ,
"insertNulls" : false ,
"lineInterpolation" : "linear" ,
"lineWidth" : 1 ,
"pointSize" : 5 ,
"scaleDistribution" : {
"type" : "linear"
} ,
"showPoints" : "auto" ,
"spanNulls" : false ,
"stacking" : {
"group" : "A" ,
"mode" : "none"
} ,
"thresholdsStyle" : {
"mode" : "off"
}
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 80
}
]
2025-08-01 16:11:32 +05:30
}
2024-08-21 17:10:29 +02:00
} ,
"overrides" : [ ]
} ,
"gridPos" : {
2025-08-01 16:11:32 +05:30
"h" : 8 ,
"w" : 12 ,
"x" : 0 ,
"y" : 120
2024-08-21 17:10:29 +02:00
} ,
2025-08-01 16:11:32 +05:30
"id" : 113 ,
2024-08-21 17:10:29 +02:00
"options" : {
"legend" : {
"calcs" : [ ] ,
"displayMode" : "list" ,
"placement" : "bottom" ,
"showLegend" : true
} ,
"tooltip" : {
2025-08-01 16:11:32 +05:30
"hideZeros" : false ,
2024-08-21 17:10:29 +02:00
"mode" : "single" ,
"sort" : "none"
}
} ,
2025-08-01 16:11:32 +05:30
"pluginVersion" : "11.5.2" ,
2024-08-21 17:10:29 +02:00
"targets" : [
{
"datasource" : {
"type" : "prometheus" ,
2025-08-01 16:11:32 +05:30
"uid" : "P6693426190CB2316"
2024-08-21 17:10:29 +02:00
} ,
"editorMode" : "code" ,
refactor(metrics): give every metric a logos_delivery_ prefix (#4074)
* refactor(metrics): prefix node metrics with logos_delivery_
Every metric the node exports now starts with logos_delivery_. There was no
prefix mechanism before: nim-metrics derives the exported name from the Nim
identifier, no declaration passed an explicit `name = "..."`, and the waku_
convention was maintained by hand -- 69 of the 80 node metrics followed it and
11 did not (query_count, query_time_secs, event_loop_load,
event_loop_accumulated_lag_secs, postgres_payload_size_bytes, reconciliation_*,
total_* and the camelCase rendezvousPeerFoundTotal).
Identifiers are renamed rather than given a `name = "..."` argument, keeping the
invariant that the Nim identifier is the exported name and letting the compiler
check every call site.
rendezvousPeerFoundTotal becomes logos_delivery_rendezvous_peer_found: it was the
only camelCase metric, and the trailing Total was redundant since nim-metrics
already appends _total to counters at exposition time.
library/ is untouched on purpose -- `proc waku_version()` in
kernel_api/debug_node_api.nim is the exported libwaku C ABI symbol, not the gauge
of the same name in node_telemetry.nim.
BREAKING CHANGE: metric names change. Dashboards, alert rules and recording rules
that reference waku_* must be updated; see docs/operators/how-to/monitor.md.
* refactor(metrics): prefix auxiliary app metrics with logos_delivery_
Applies the same prefix to the tools shipped from this repo: liteprotocoltester
(lpt_*), networkmonitor (networkmonitor_*), chat2bridge (chat2_*) and the
lightpush_mix example (lp_mix_*).
These tools are not the delivery node and already had their own consistent
prefixes, so this commit is separable from the node rename if the intent was to
namespace only the node itself.
* chore(metrics): query old and new metric names in Grafana dashboards
212 expressions across 9 dashboards now match both the waku_* and the
logos_delivery_* spelling, so panels keep working across the upgrade and over
historical data:
sum by (type)((increase(waku_node_errors_total{...}[$__rate_interval])
or increase(logos_delivery_node_errors_total{...}[$__rate_interval])))
The `or` is placed around the leaf, inside every aggregation. That depth is
load-bearing: `or` keeps its right operand only for label sets absent from the
left, so `sum by (type)(old) or sum by (type)(new)` aggregates each half of the
fleet separately and then discards the right one entirely -- silently dropping
every already-upgraded node. 36 panels here collapse `instance`.
Measured against a local Prometheus scraping two targets, one exporting old names
at 10/s and one exporting new names at 20/s (truth 30/s): union outside the
aggregation gives 10, union around the leaf gives 30.
Where the leaf sits in a range vector the whole call is duplicated, since
`(a or b)[5m]` is not valid PromQL.
Once every scraped node runs a release with the new names and the old samples
have aged out of retention, the `or` half can be deleted.
* test(e2e): expect logos_delivery_-prefixed metric names
The e2e suite asserts against a live /metrics endpoint, which serves only the new
names, so these are replaced rather than unioned. libp2p_* entries are unchanged.
* docs(operators): document the logos_delivery_ metric prefix
Records that every metric the node exports is prefixed, that dependency metrics
(libp2p_*, nim_gc_*, process_*) keep their own names, and shows where the `or`
has to sit if operators maintain their own dashboards or alert rules.
* refactor(metrics): name the store fleet metrics after store, not relay
logos_delivery_relay_fleet_store_msg_size_bytes and _msg_count are declared in
waku_store/protocol_metrics.nim and recorded by the store client, but carried a
relay prefix. Renamed to logos_delivery_store_fleet_msg_size_bytes and
logos_delivery_store_fleet_msg_count.
The dashboard keeps matching the old exported name, which was
waku_relay_fleet_store_*.
Note that both metrics are wrong independently of their name, see the PR
description.
2026-07-29 18:56:50 +01:00
"expr" : "(waku_rln_number_registered_memberships{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"} or logos_delivery_rln_number_registered_memberships{instance=~\"[[host]].([[dc:pipe]]).([[fleet:pipe]])\"})" ,
2025-08-01 16:11:32 +05:30
"legendFormat" : "{{__name__}}_{{datacenter}}" ,
2024-08-21 17:10:29 +02:00
"range" : true ,
"refId" : "A"
}
] ,
2025-08-01 16:11:32 +05:30
"title" : "RLN Memberships" ,
2021-08-19 09:57:53 +02:00
"type" : "timeseries"
}
] ,
2025-08-01 16:11:32 +05:30
"preload" : false ,
"refresh" : "30s" ,
"schemaVersion" : 40 ,
2021-08-19 09:57:53 +02:00
"tags" : [ ] ,
"templating" : {
2025-08-01 16:11:32 +05:30
"list" : [
{
"current" : {
"text" : "node-.*" ,
"value" : "node-.*"
} ,
"includeAll" : false ,
"label" : "Hostname regex" ,
"name" : "host" ,
"options" : [
{
"selected" : true ,
"text" : "node-.*" ,
"value" : "node-.*"
}
] ,
"query" : "node-.*" ,
"type" : "custom"
} ,
{
"current" : {
"text" : [
"status.prod"
] ,
"value" : [
"status.prod"
]
} ,
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"definition" : "label_values(libp2p_peers, fleet)" ,
"includeAll" : false ,
"label" : "Fleet name" ,
"multi" : true ,
"name" : "fleet" ,
"options" : [ ] ,
"query" : {
"query" : "label_values(libp2p_peers, fleet)" ,
"refId" : "StandardVariableQuery"
} ,
"refresh" : 1 ,
"regex" : "/waku|status|shards/" ,
"type" : "query"
} ,
{
"current" : {
"text" : "All" ,
"value" : "$__all"
} ,
"datasource" : {
"type" : "prometheus" ,
"uid" : "P6693426190CB2316"
} ,
"definition" : "label_values(libp2p_peers, datacenter)" ,
"includeAll" : true ,
"label" : "Data Center" ,
"multi" : true ,
"name" : "dc" ,
"options" : [ ] ,
"query" : {
"query" : "label_values(libp2p_peers, datacenter)" ,
"refId" : "StandardVariableQuery"
} ,
"refresh" : 1 ,
"regex" : "" ,
"sort" : 1 ,
"type" : "query"
}
]
2021-08-19 09:57:53 +02:00
} ,
"time" : {
2025-08-01 16:11:32 +05:30
"from" : "now-10d" ,
"to" : "now"
2021-08-19 09:57:53 +02:00
} ,
"timepicker" : {
"refresh_intervals" : [
"10s" ,
"30s" ,
"1m" ,
"5m" ,
"15m" ,
"30m" ,
"1h" ,
"2h" ,
"1d"
]
} ,
2022-09-20 10:01:54 +01:00
"timezone" : "browser" ,
2025-08-01 16:11:32 +05:30
"title" : "Nim-Waku Single Node" ,
"uid" : "TgQ8wf8Vz" ,
"version" : 7 ,
2022-02-08 12:22:06 +01:00
"weekStart" : ""
2021-08-19 09:57:53 +02:00
}
