Files
pezkuwi-subxt/polkadot/node/network/approval-distribution/src/metrics.rs
T
asynchronous rob 79ecc53801 Reduce network bandwidth, improve parablock times: optimize approval-distribution (#5164)
* gossip-support: be explicit about dimensions

* some guide updates

* update network-bridge to distinguish x and y dimensions

* get everything to compile

* beginnings

* some TODOs

* polkadot runtime: use relevant_authorities

* make gossip topologies per-session

* better formatting

* gossip support: use current session validators

* expand in comment

* adjust tests and fix index bug

* add past/present/future connection test and clean up code

* fmt

* network bridge: updated types

* update protocols to new gossip topology message

* guide updates

* add session to BlockApprovalMeta

* add session to block info

* refactor knowledge and remove most unify logic

* start replacing gossip_peers with new SessionTopologies

* add routing information to message state

* add some utilities to SessionTopology

* implement new gossip topology logic

* re-implement unify_with_peer

* distribute assignments according to topology

* finish grid topology implementation

* refactor network bridge slightly

* issue connection requests on all past/present/future

* fmt

* address grumbles

* tighten invariants in unify_with_peer

* implement random propagation

* refactor: extract required routing adjustment logic

* some block-age logic

* aggressively propagate messages when finality is slow

* overhaul aggression system to have 3 levels

* add aggression metrics

* remove aggression L3

* reduce random circulation

* remove PeerData

* get approval tests compiling

* use btree_map in known_by to make deterministic

* Revert "use btree_map in known_by to make deterministic"

This reverts commit 330d65343a7bb6fe4dd0f24bd8dbc15c0cbdbd9d.

* test XY grid propagation

* remove stray println

* test unshared dimension propagation

* add random gossip check

* test unify_with_peer better

* test sending after getting gossip topology

* test L1 aggression on originator

* test L1 aggression for non-originators

* test non-originator aggression L2

* fnt

* ~spellcheck

* fix statement-distribution tests

* fix flaky test

* fix metrics typo

* re-send periodically

* test resending

* typo

Co-authored-by: Bernhard Schuster <bernhard@ahoi.io>

* add more metrics about apd messages

* add back unify_with_peer logs

* make Resend an enum

* be more explicit when resending

* fmt

* fix error

* add a TODO for refactoring

* remove debug metrics

* add some guide stuff

* fmt

* update runtime API in test-runtim

Co-authored-by: Bernhard Schuster <bernhard@ahoi.io>
2022-04-19 20:26:55 +02:00

151 lines
4.8 KiB
Rust

// Copyright 2020 Parity Technologies (UK) Ltd.
// This file is part of Polkadot.
// Polkadot is free software: you can redistribute it and/or modify
// it under the terms of the GNU General Public License as published by
// the Free Software Foundation, either version 3 of the License, or
// (at your option) any later version.
// Polkadot is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU General Public License for more details.
// You should have received a copy of the GNU General Public License
// along with Polkadot. If not, see <http://www.gnu.org/licenses/>.
use polkadot_node_subsystem_util::metrics::{prometheus, Metrics as MetricsTrait};
/// Approval Distribution metrics.
#[derive(Default, Clone)]
pub struct Metrics(Option<MetricsInner>);
#[derive(Clone)]
struct MetricsInner {
assignments_imported_total: prometheus::Counter<prometheus::U64>,
approvals_imported_total: prometheus::Counter<prometheus::U64>,
unified_with_peer_total: prometheus::Counter<prometheus::U64>,
aggression_l1_messages_total: prometheus::Counter<prometheus::U64>,
aggression_l2_messages_total: prometheus::Counter<prometheus::U64>,
time_unify_with_peer: prometheus::Histogram,
time_import_pending_now_known: prometheus::Histogram,
time_awaiting_approval_voting: prometheus::Histogram,
}
impl Metrics {
pub(crate) fn on_assignment_imported(&self) {
if let Some(metrics) = &self.0 {
metrics.assignments_imported_total.inc();
}
}
pub(crate) fn on_approval_imported(&self) {
if let Some(metrics) = &self.0 {
metrics.approvals_imported_total.inc();
}
}
pub(crate) fn on_unify_with_peer(&self) {
if let Some(metrics) = &self.0 {
metrics.unified_with_peer_total.inc();
}
}
pub(crate) fn time_unify_with_peer(&self) -> Option<prometheus::prometheus::HistogramTimer> {
self.0.as_ref().map(|metrics| metrics.time_unify_with_peer.start_timer())
}
pub(crate) fn time_import_pending_now_known(
&self,
) -> Option<prometheus::prometheus::HistogramTimer> {
self.0
.as_ref()
.map(|metrics| metrics.time_import_pending_now_known.start_timer())
}
pub(crate) fn time_awaiting_approval_voting(
&self,
) -> Option<prometheus::prometheus::HistogramTimer> {
self.0
.as_ref()
.map(|metrics| metrics.time_awaiting_approval_voting.start_timer())
}
pub(crate) fn on_aggression_l1(&self) {
if let Some(metrics) = &self.0 {
metrics.aggression_l1_messages_total.inc();
}
}
pub(crate) fn on_aggression_l2(&self) {
if let Some(metrics) = &self.0 {
metrics.aggression_l2_messages_total.inc();
}
}
}
impl MetricsTrait for Metrics {
fn try_register(registry: &prometheus::Registry) -> Result<Self, prometheus::PrometheusError> {
let metrics = MetricsInner {
assignments_imported_total: prometheus::register(
prometheus::Counter::new(
"polkadot_parachain_assignments_imported_total",
"Number of valid assignments imported locally or from other peers.",
)?,
registry,
)?,
approvals_imported_total: prometheus::register(
prometheus::Counter::new(
"polkadot_parachain_approvals_imported_total",
"Number of valid approvals imported locally or from other peers.",
)?,
registry,
)?,
unified_with_peer_total: prometheus::register(
prometheus::Counter::new(
"polkadot_parachain_unified_with_peer_total",
"Number of times `unify_with_peer` is called.",
)?,
registry,
)?,
aggression_l1_messages_total: prometheus::register(
prometheus::Counter::new(
"polkadot_parachain_approval_distribution_aggression_l1_messages_total",
"Number of messages in approval distribution for which aggression L1 has been triggered",
)?,
registry,
)?,
aggression_l2_messages_total: prometheus::register(
prometheus::Counter::new(
"polkadot_parachain_approval_distribution_aggression_l2_messages_total",
"Number of messages in approval distribution for which aggression L2 has been triggered",
)?,
registry,
)?,
time_unify_with_peer: prometheus::register(
prometheus::Histogram::with_opts(prometheus::HistogramOpts::new(
"polkadot_parachain_time_unify_with_peer",
"Time spent within fn `unify_with_peer`.",
))?,
registry,
)?,
time_import_pending_now_known: prometheus::register(
prometheus::Histogram::with_opts(prometheus::HistogramOpts::new(
"polkadot_parachain_time_import_pending_now_known",
"Time spent on importing pending assignments and approvals.",
))?,
registry,
)?,
time_awaiting_approval_voting: prometheus::register(
prometheus::Histogram::with_opts(prometheus::HistogramOpts::new(
"polkadot_parachain_time_awaiting_approval_voting",
"Time spent awaiting a reply from the Approval Voting Subsystem.",
))?,
registry,
)?,
};
Ok(Metrics(Some(metrics)))
}
}