Igor Sirotin 8125cd0262
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

180 lines
6.0 KiB
Nim

## Example showing how a resource restricted client may
## subscribe to messages without relay
import
system/ansi_c,
chronicles,
chronos,
chronos/timer as chtimer,
stew/byteutils,
results,
serialization,
json_serialization as js
import
logos_delivery/waku/[
common/logging,
node/peer_manager,
waku_node,
waku_core,
waku_filter_v2/client,
waku_filter_v2/common,
waku_core/multiaddrstr,
],
./tester_config,
./tester_message,
./statistics,
./diagnose_connections,
./service_peer_management,
./lpt_metrics
var actualFilterPeer {.threadvar.}: RemotePeerInfo
proc unsubscribe(
wakuNode: WakuNode, filterPubsubTopic: PubsubTopic, filterContentTopic: ContentTopic
) {.async.} =
notice "unsubscribing from filter"
let unsubscribeRes = await wakuNode.wakuFilterClient.unsubscribe(
actualFilterPeer, filterPubsubTopic, @[filterContentTopic]
)
if unsubscribeRes.isErr:
notice "unsubscribe request failed", err = unsubscribeRes.error
else:
notice "unsubscribe request successful"
proc maintainSubscription(
wakuNode: WakuNode,
filterPubsubTopic: PubsubTopic,
filterContentTopic: ContentTopic,
preventPeerSwitch: bool,
) {.async.} =
const maxFailedSubscribes = 3
const maxFailedServiceNodeSwitches = 10
var noFailedSubscribes = 0
var noFailedServiceNodeSwitches = 0
var isFirstPingOnNewPeer = true
const RetryWaitMs = 2.seconds # Quick retry interval
const SubscriptionMaintenanceMs = 30.seconds # Subscription maintenance interval
while true:
info "maintaining subscription at", peer = constructMultiaddrStr(actualFilterPeer)
# First use filter-ping to check if we have an active subscription
let pingErr = (await wakuNode.wakuFilterClient.ping(actualFilterPeer)).errorOr:
await sleepAsync(SubscriptionMaintenanceMs)
info "subscription is live."
continue
if isFirstPingOnNewPeer == false:
# Very first ping expected to fail as we have not yet subscribed at all
logos_delivery_lpt_receiver_lost_subscription_count.inc()
isFirstPingOnNewPeer = false
# No subscription found. Let's subscribe.
error "ping failed.", error = pingErr
trace "no subscription found. Sending subscribe request"
let subscribeErr = (
await wakuNode.filterSubscribe(
Opt.some(filterPubsubTopic), filterContentTopic, actualFilterPeer
)
).errorOr:
await sleepAsync(SubscriptionMaintenanceMs)
if noFailedSubscribes > 0:
noFailedSubscribes -= 1
notice "subscribe request successful."
continue
noFailedSubscribes += 1
logos_delivery_lpt_service_peer_failure_count.inc(
labelValues = ["receiver", actualFilterPeer.getAgent()]
)
error "Subscribe request failed.",
err = subscribeErr, peer = actualFilterPeer, failCount = noFailedSubscribes
# TODO: disconnet from failed actualFilterPeer
# asyncSpawn(wakuNode.peerManager.switch.disconnect(p))
# wakunode.peerManager.peerStore.delete(actualFilterPeer)
if noFailedSubscribes < maxFailedSubscribes:
await sleepAsync(RetryWaitMs) # Wait a bit before retrying
elif not preventPeerSwitch:
# try again with new peer without delay
actualFilterPeer = selectRandomServicePeer(
wakuNode.peerManager, Opt.some(actualFilterPeer), WakuFilterSubscribeCodec
).valueOr:
error "Failed to find new service peer. Exiting."
noFailedServiceNodeSwitches += 1
break
info "Found new peer for codec",
codec = filterPubsubTopic, peer = constructMultiaddrStr(actualFilterPeer)
noFailedSubscribes = 0
logos_delivery_lpt_change_service_peer_count.inc(labelValues = ["receiver"])
isFirstPingOnNewPeer = true
else:
await sleepAsync(SubscriptionMaintenanceMs)
proc setupAndListen*(
wakuNode: WakuNode, conf: LiteProtocolTesterConf, servicePeer: RemotePeerInfo
) =
if isNil(wakuNode.wakuFilterClient):
# if we have not yet initialized lightpush client, then do it as the only way we can get here is
# by having a service peer discovered.
waitFor wakuNode.mountFilterClient()
info "Start receiving messages to service node using filter",
servicePeer = servicePeer
var stats: PerPeerStatistics
actualFilterPeer = servicePeer
let pushHandler = proc(
pubsubTopic: PubsubTopic, message: WakuMessage
): Future[void] {.async, closure.} =
let payloadStr = string.fromBytes(message.payload)
let testerMessage = js.Json.decode(payloadStr, ProtocolTesterMessage)
let msgHash = computeMessageHash(pubsubTopic, message).to0xHex
stats.addMessage(testerMessage.sender, testerMessage, msgHash)
notice "message received",
index = testerMessage.index,
count = testerMessage.count,
startedAt = $testerMessage.startedAt,
sinceStart = $testerMessage.sinceStart,
sincePrev = $testerMessage.sincePrev,
size = $testerMessage.size,
pubsubTopic = pubsubTopic,
hash = msgHash
wakuNode.wakuFilterClient.registerPushHandler(pushHandler)
let interval = millis(20000)
var printStats: CallbackFunc
# calculate max wait after the last known message arrived before exiting
# 20% of expected messages times the expected interval but capped to 10min
let maxWaitForLastMessage: Duration =
min(conf.messageInterval.milliseconds * (conf.numMessages div 5), 10.minutes)
printStats = CallbackFunc(
proc(udata: pointer) {.gcsafe.} =
stats.echoStats()
if conf.numMessages > 0 and
waitFor stats.checkIfAllMessagesReceived(maxWaitForLastMessage):
waitFor unsubscribe(wakuNode, conf.getPubsubTopic(), conf.contentTopics[0])
info "All messages received. Exiting."
## for gracefull shutdown through signal hooks
discard c_raise(ansi_c.SIGTERM)
else:
discard setTimer(Moment.fromNow(interval), printStats)
)
discard setTimer(Moment.fromNow(interval), printStats)
# Start maintaining subscription
asyncSpawn maintainSubscription(
wakuNode, conf.getPubsubTopic(), conf.contentTopics[0], conf.fixedServicePeer
)