Add Prometheus timers to the subsystems (#1923)

* reexport prometheus-super for ease of use of other subsystems

* add some prometheus timers for collation generation subsystem

* add timing metrics to av-store

* add metrics to candidate backing

* add timing metric to bitfield signing

* add timing metrics to candidate selection

* add timing metrics to candidate-validation

* add timing metrics to chain-api

* add timing metrics to provisioner

* add timing metrics to runtime-api

* add timing metrics to availability-distribution

* add timing metrics to bitfield-distribution

* add timing metrics to collator protocol: collator side

* add timing metrics to collator protocol: validator side

* fix candidate validation test failures

* add timing metrics to pov distribution

* add timing metrics to statement-distribution

* use substrate_prometheus_endpoint prometheus reexport instead of prometheus_super

* don't include JOB_DELAY in bitfield-signing metrics

* give adder-collator ability to easily export its genesis-state and validation code

* wip: adder-collator pushbutton script

* don't attempt to register the adder-collator automatically

Instead, get these values with

```sh
target/release/adder-collator export-genesis-state
target/release/adder-collator export-genesis-wasm
```

And then register the parachain on https://polkadot.js.org/apps/?rpc=ws%3A%2F%2F127.0.0.1%3A9944#/explorer

To collect prometheus data, after running the script, create `prometheus.yml` per the instructions
at https://www.notion.so/paritytechnologies/Setting-up-Prometheus-locally-835cb3a9df7541a781c381006252b5ff
and then run:

```sh
docker run -v `pwd`/prometheus.yml:/etc/prometheus/prometheus.yml:z --network host prom/prometheus
```

Demonstrates that data makes it across to prometheus, though it is likely to be useful in the future
to tweak the buckets.

* Update parachain/test-parachains/adder/collator/src/cli.rs

Co-authored-by: Andronik Ordian <write@reusable.software>

* use the grandpa-pause parameter

* skip metrics in tracing instrumentation

* remove unnecessary grandpa_pause cli param

Co-authored-by: Andronik Ordian <write@reusable.software>
This commit is contained in:
Peter Goodspeed-Niklaus
2020-11-20 15:04:51 +01:00
committed by GitHub
parent e49989971d
commit 0a5bc82529
23 changed files with 1199 additions and 87 deletions
@@ -204,6 +204,8 @@ impl CandidateSelectionJob {
para_id: ParaId,
collator_id: CollatorId,
) {
let _timer = self.metrics.time_handle_collation();
if self.seconded_candidate.is_none() {
let (candidate_receipt, pov) =
match get_collation(
@@ -240,6 +242,8 @@ impl CandidateSelectionJob {
#[tracing::instrument(level = "trace", skip(self), fields(subsystem = LOG_TARGET))]
async fn handle_invalid(&mut self, candidate_receipt: CandidateReceipt) {
let _timer = self.metrics.time_handle_invalid();
let received_from = match &self.seconded_candidate {
Some(peer) => peer,
None => {
@@ -336,6 +340,8 @@ async fn forward_invalidity_note(
struct MetricsInner {
seconds: prometheus::CounterVec<prometheus::U64>,
invalid_selections: prometheus::CounterVec<prometheus::U64>,
handle_collation: prometheus::Histogram,
handle_invalid: prometheus::Histogram,
}
/// Candidate selection metrics.
@@ -356,6 +362,16 @@ impl Metrics {
metrics.invalid_selections.with_label_values(&[label]).inc();
}
}
/// Provide a timer for `handle_collation` which observes on drop.
fn time_handle_collation(&self) -> Option<metrics::prometheus::prometheus::HistogramTimer> {
self.0.as_ref().map(|metrics| metrics.handle_collation.start_timer())
}
/// Provide a timer for `handle_invalid` which observes on drop.
fn time_handle_invalid(&self) -> Option<metrics::prometheus::prometheus::HistogramTimer> {
self.0.as_ref().map(|metrics| metrics.handle_invalid.start_timer())
}
}
impl metrics::Metrics for Metrics {
@@ -381,6 +397,24 @@ impl metrics::Metrics for Metrics {
)?,
registry,
)?,
handle_collation: prometheus::register(
prometheus::Histogram::with_opts(
prometheus::HistogramOpts::new(
"parachain_candidate_selection_handle_collation",
"Time spent within `candidate_selection::handle_collation`",
)
)?,
registry,
)?,
handle_invalid: prometheus::register(
prometheus::Histogram::with_opts(
prometheus::HistogramOpts::new(
"parachain_candidate_selection:handle_invalid",
"Time spent within `candidate_selection::handle_invalid`",
)
)?,
registry,
)?,
};
Ok(Metrics(Some(metrics)))
}