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

fix(metric): filter out NaN due to divide by zero in Grafana #16590

Merged
merged 1 commit into from
May 6, 2024
Merged

fix(metric): filter out NaN due to divide by zero in Grafana #16590

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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.

126 changes: 63 additions & 63 deletions grafana/risingwave-dev-dashboard.dashboard.py
View file
Open in desktop

Large diffs are not rendered by default.

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

Large diffs are not rendered by default.

20 changes: 10 additions & 10 deletions grafana/risingwave-user-dashboard.dashboard.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -113,7 +113,7 @@ def section_overview(panels):
)
+ [
panels.target(
f"rate({metric('meta_barrier_duration_seconds_sum')}[$__rate_interval]) / rate({metric('meta_barrier_duration_seconds_count')}[$__rate_interval])",
f"rate({metric('meta_barrier_duration_seconds_sum')}[$__rate_interval]) / rate({metric('meta_barrier_duration_seconds_count')}[$__rate_interval]) > 0",
"barrier_latency_avg",
),
],
Expand Down Expand Up @@ -409,35 +409,35 @@ def section_memory(outer_panels):
"",
[
panels.target(
f"(sum(rate({metric('stream_join_lookup_miss_count')}[$__rate_interval])) by (side, join_table_id, degree_table_id, actor_id) ) / (sum(rate({metric('stream_join_lookup_total_count')}[$__rate_interval])) by (side, join_table_id, degree_table_id, actor_id))",
f"(sum(rate({metric('stream_join_lookup_miss_count')}[$__rate_interval])) by (side, join_table_id, degree_table_id, actor_id) ) / (sum(rate({metric('stream_join_lookup_total_count')}[$__rate_interval])) by (side, join_table_id, degree_table_id, actor_id)) >=0 ",
"join executor cache miss ratio - - {{side}} side, join_table_id {{join_table_id}} degree_table_id {{degree_table_id}} actor {{actor_id}}",
),
panels.target(
f"(sum(rate({metric('stream_agg_lookup_miss_count')}[$__rate_interval])) by (table_id, actor_id) ) / (sum(rate({metric('stream_agg_lookup_total_count')}[$__rate_interval])) by (table_id, actor_id))",
f"(sum(rate({metric('stream_agg_lookup_miss_count')}[$__rate_interval])) by (table_id, actor_id) ) / (sum(rate({metric('stream_agg_lookup_total_count')}[$__rate_interval])) by (table_id, actor_id)) >=0 ",
"Agg cache miss ratio - table {{table_id}} actor {{actor_id}} ",
),
panels.target(
f"(sum(rate({metric('stream_agg_distinct_cache_miss_count')}[$__rate_interval])) by (table_id, actor_id) ) / (sum(rate({metric('stream_agg_distinct_total_cache_count')}[$__rate_interval])) by (table_id, actor_id))",
f"(sum(rate({metric('stream_agg_distinct_cache_miss_count')}[$__rate_interval])) by (table_id, actor_id) ) / (sum(rate({metric('stream_agg_distinct_total_cache_count')}[$__rate_interval])) by (table_id, actor_id)) >=0",
"Distinct agg cache miss ratio - table {{table_id}} actor {{actor_id}} ",
),
panels.target(
f"(sum(rate({metric('stream_group_top_n_cache_miss_count')}[$__rate_interval])) by (table_id, actor_id) ) / (sum(rate({metric('stream_group_top_n_total_query_cache_count')}[$__rate_interval])) by (table_id, actor_id))",
f"(sum(rate({metric('stream_group_top_n_cache_miss_count')}[$__rate_interval])) by (table_id, actor_id) ) / (sum(rate({metric('stream_group_top_n_total_query_cache_count')}[$__rate_interval])) by (table_id, actor_id)) >=0",
"Stream group top n cache miss ratio - table {{table_id}} actor {{actor_id}} ",
),
panels.target(
f"(sum(rate({metric('stream_group_top_n_appendonly_cache_miss_count')}[$__rate_interval])) by (table_id, actor_id) ) / (sum(rate({metric('stream_group_top_n_appendonly_total_query_cache_count')}[$__rate_interval])) by (table_id, actor_id))",
f"(sum(rate({metric('stream_group_top_n_appendonly_cache_miss_count')}[$__rate_interval])) by (table_id, actor_id) ) / (sum(rate({metric('stream_group_top_n_appendonly_total_query_cache_count')}[$__rate_interval])) by (table_id, actor_id)) >=0",
"Stream group top n appendonly cache miss ratio - table {{table_id}} actor {{actor_id}} ",
),
panels.target(
f"(sum(rate({metric('stream_lookup_cache_miss_count')}[$__rate_interval])) by (table_id, actor_id) ) / (sum(rate({metric('stream_lookup_total_query_cache_count')}[$__rate_interval])) by (table_id, actor_id))",
f"(sum(rate({metric('stream_lookup_cache_miss_count')}[$__rate_interval])) by (table_id, actor_id) ) / (sum(rate({metric('stream_lookup_total_query_cache_count')}[$__rate_interval])) by (table_id, actor_id)) >=0",
"Stream lookup cache miss ratio - table {{table_id}} actor {{actor_id}} ",
),
panels.target(
f"(sum(rate({metric('stream_temporal_join_cache_miss_count')}[$__rate_interval])) by (table_id, actor_id) ) / (sum(rate({metric('stream_temporal_join_total_query_cache_count')}[$__rate_interval])) by (table_id, actor_id))",
f"(sum(rate({metric('stream_temporal_join_cache_miss_count')}[$__rate_interval])) by (table_id, actor_id) ) / (sum(rate({metric('stream_temporal_join_total_query_cache_count')}[$__rate_interval])) by (table_id, actor_id)) >=0",
"Stream temporal join cache miss ratio - table {{table_id}} actor {{actor_id}} ",
),
panels.target(
f"1 - (sum(rate({metric('stream_materialize_cache_hit_count')}[$__rate_interval])) by (table_id, actor_id) ) / (sum(rate({metric('stream_materialize_cache_total_count')}[$__rate_interval])) by (table_id, actor_id))",
f"1 - (sum(rate({metric('stream_materialize_cache_hit_count')}[$__rate_interval])) by (table_id, actor_id) ) / (sum(rate({metric('stream_materialize_cache_total_count')}[$__rate_interval])) by (table_id, actor_id)) >=0",
"materialize executor cache miss ratio - table {{table_id}} - actor {{actor_id}} {{%s}}"
% NODE_LABEL,
),
Expand Down Expand Up @@ -648,7 +648,7 @@ def section_storage(outer_panels):
[50, 99],
),
panels.target(
f"sum by(le, {COMPONENT_LABEL}) (rate({metric('state_store_sync_size_sum')}[$__rate_interval])) / sum by(le, {COMPONENT_LABEL}) (rate({metric('state_store_sync_size_count')}[$__rate_interval]))",
f"sum by(le, {COMPONENT_LABEL}) (rate({metric('state_store_sync_size_sum')}[$__rate_interval])) / sum by(le, {COMPONENT_LABEL}) (rate({metric('state_store_sync_size_count')}[$__rate_interval])) > 0",
"avg - {{%s}}" % COMPONENT_LABEL,
),
],
Expand Down
2 changes: 1 addition & 1 deletion grafana/risingwave-user-dashboard.json
View file
Open in desktop

Large diffs are not rendered by default.

Loading