Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat(cdc): add cdc backfill grafana metrics #13777

Merged
merged 2 commits into from
Dec 4, 2023
Merged

feat(cdc): add cdc backfill grafana metrics #13777

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6175473
add cdc backfill metrics
StrikeW Dec 3, 2023
3ea305f
Merge remote-tracking branch 'origin/main' into siyuan/cdc-backfill-m…
StrikeW Dec 4, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion docker/dashboards/risingwave-dev-dashboard.json
View file
Open in desktop

Large diffs are not rendered by default.

2 changes: 1 addition & 1 deletion docker/dashboards/risingwave-user-dashboard.json
View file
Open in desktop

Large diffs are not rendered by default.

22 changes: 22 additions & 0 deletions grafana/risingwave-dev-dashboard.dashboard.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -827,6 +827,28 @@ def section_streaming(outer_panels):
),
],
),
panels.timeseries_rowsps(
"CDC Backfill Snapshot Read Throughput(rows)",
"Total number of rows that have been read from the cdc backfill snapshot",
[
panels.target(
f"rate({table_metric('stream_cdc_backfill_snapshot_read_row_count')}[$__rate_interval])",
"table_id={{table_id}} actor={{actor_id}} @ {{%s}}"
% NODE_LABEL,
),
],
),
panels.timeseries_rowsps(
"CDC Backfill Upstream Throughput(rows)",
"Total number of rows that have been output from the cdc backfill upstream",
[
panels.target(
f"rate({table_metric('stream_cdc_backfill_upstream_output_row_count')}[$__rate_interval])",
"table_id={{table_id}} actor={{actor_id}} @ {{%s}}"
% NODE_LABEL,
),
],
),
panels.timeseries_count(
"Barrier Number",
"The number of barriers that have been ingested but not completely processed. This metric reflects the "
Expand Down
2 changes: 1 addition & 1 deletion grafana/risingwave-dev-dashboard.json
View file
Open in desktop

Large diffs are not rendered by default.

2 changes: 1 addition & 1 deletion grafana/risingwave-user-dashboard.json
View file
Open in desktop

Large diffs are not rendered by default.

4 changes: 2 additions & 2 deletions src/stream/src/executor/backfill/cdc/cdc_backfill.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -337,15 +337,15 @@ impl<S: StateStore> CdcBackfillExecutor<S> {
}

self.metrics
.backfill_snapshot_read_row_count
.cdc_backfill_snapshot_read_row_count
.with_label_values(&[
upstream_table_id.to_string().as_str(),
self.actor_ctx.id.to_string().as_str(),
])
.inc_by(cur_barrier_snapshot_processed_rows);

self.metrics
.backfill_upstream_output_row_count
.cdc_backfill_upstream_output_row_count
.with_label_values(&[
upstream_table_id.to_string().as_str(),
self.actor_ctx.id.to_string().as_str(),
Expand Down
22 changes: 22 additions & 0 deletions src/stream/src/executor/monitor/streaming_stats.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,6 +122,10 @@ pub struct StreamingMetrics {
pub arrangement_backfill_snapshot_read_row_count: GenericCounterVec<AtomicU64>,
pub arrangement_backfill_upstream_output_row_count: GenericCounterVec<AtomicU64>,

// CDC Backfill
pub cdc_backfill_snapshot_read_row_count: GenericCounterVec<AtomicU64>,
pub cdc_backfill_upstream_output_row_count: GenericCounterVec<AtomicU64>,

// Over Window
pub over_window_cached_entry_count: GenericGaugeVec<AtomicI64>,
pub over_window_cache_lookup_count: GenericCounterVec<AtomicU64>,
Expand Down Expand Up @@ -684,6 +688,22 @@ impl StreamingMetrics {
)
.unwrap();

let cdc_backfill_snapshot_read_row_count = register_int_counter_vec_with_registry!(
"stream_cdc_backfill_snapshot_read_row_count",
"Total number of rows that have been read from the cdc_backfill snapshot",
&["table_id", "actor_id"],
registry
)
.unwrap();

let cdc_backfill_upstream_output_row_count = register_int_counter_vec_with_registry!(
"stream_cdc_backfill_upstream_output_row_count",
"Total number of rows that have been output from the cdc_backfill upstream",
&["table_id", "actor_id"],
registry
)
.unwrap();

let over_window_cached_entry_count = register_int_gauge_vec_with_registry!(
"stream_over_window_cached_entry_count",
"Total entry (partition) count in over window executor cache",
Expand Down Expand Up @@ -980,6 +1000,8 @@ impl StreamingMetrics {
backfill_upstream_output_row_count,
arrangement_backfill_snapshot_read_row_count,
arrangement_backfill_upstream_output_row_count,
cdc_backfill_snapshot_read_row_count,
cdc_backfill_upstream_output_row_count,
over_window_cached_entry_count,
over_window_cache_lookup_count,
over_window_cache_miss_count,
Expand Down
Loading