Skip to content

Add instance filter to TiCDC Grafana dashboards for better metric isolation #3929

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

Merged
ti-chi-bot merged 2 commits into from
Jan 9, 2026
Merged

Add instance filter to TiCDC Grafana dashboards for better metric isolation #3929

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0f26332
feat(grafana): add TiCDC instance filter to Prometheus queries
tenfyzhong Jan 5, 2026
f49409b
feat(metrics): add instance filter to TiCDC process uptime panels
tenfyzhong Jan 5, 2026
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
40 changes: 20 additions & 20 deletions metrics/grafana/ticdc_new_arch.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1161,7 +1161,7 @@
"targets": [
{
"exemplar": true,
"expr": "max(ticdc_maintainer_checkpoint_ts_lag{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", namespace=~\"$namespace\", changefeed=~\"$changefeed\"}) by (namespace, changefeed)",
"expr": "max(ticdc_maintainer_checkpoint_ts_lag{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", namespace=~\"$namespace\", changefeed=~\"$changefeed\", instance=~\"$ticdc_instance\"}) by (namespace, changefeed)",
Copy link

@gemini-code-assist gemini-code-assist bot Jan 5, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

There's an extra space in the PromQL query before changefeed=~\"$changefeed\". While Prometheus is tolerant of this, removing it would improve consistency with other queries in this file. A similar issue exists on line 6497.

Suggested change
"expr": "max(ticdc_maintainer_checkpoint_ts_lag{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", namespace=~\"$namespace\", changefeed=~\"$changefeed\", instance=~\"$ticdc_instance\"}) by (namespace, changefeed)",
"expr": "max(ticdc_maintainer_checkpoint_ts_lag{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", namespace=~\"$namespace\", changefeed=~\"$changefeed\", instance=~\"$ticdc_instance\"}) by (namespace, changefeed)",

"format": "time_series",
"interval": "",
"intervalFactor": 1,
Expand Down Expand Up @@ -1258,7 +1258,7 @@
"targets": [
{
"exemplar": true,
"expr": "max(ticdc_maintainer_resolved_ts_lag{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", namespace=~\"$namespace\", changefeed=~\"$changefeed\"}) by (namespace,changefeed)",
"expr": "max(ticdc_maintainer_resolved_ts_lag{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", namespace=~\"$namespace\", changefeed=~\"$changefeed\", instance=~\"$ticdc_instance\"}) by (namespace,changefeed)",
Copy link

@gemini-code-assist gemini-code-assist bot Jan 5, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

For consistency with other queries, consider adding a space after the comma in the by clause: by (namespace, changefeed). A similar issue exists on line 6600.

Suggested change
"expr": "max(ticdc_maintainer_resolved_ts_lag{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", namespace=~\"$namespace\", changefeed=~\"$changefeed\", instance=~\"$ticdc_instance\"}) by (namespace,changefeed)",
"expr": "max(ticdc_maintainer_resolved_ts_lag{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", namespace=~\"$namespace\", changefeed=~\"$changefeed\", instance=~\"$ticdc_instance\"}) by (namespace, changefeed)",

"format": "time_series",
"interval": "",
"intervalFactor": 1,
Expand Down Expand Up @@ -1955,7 +1955,7 @@
"targets": [
{
"exemplar": true,
"expr": "ticdc_kvclient_pull_event_count",
"expr": "ticdc_kvclient_pull_event_count{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", instance=~\"$ticdc_instance\"}",
"hide": false,
"interval": "",
"legendFormat": "{{instance}}-{{type}}",
Expand Down Expand Up @@ -2580,7 +2580,7 @@
"targets": [
{
"exemplar": true,
"expr": "sum(ticdc_sink_batch_row_count_sum{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", namespace=~\"$namespace\",changefeed=~\"$changefeed\"}) by (namespace,changefeed, instance)",
"expr": "sum(ticdc_sink_batch_row_count_sum{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", namespace=~\"$namespace\",changefeed=~\"$changefeed\", instance=~\"$ticdc_instance\"}) by (namespace,changefeed, instance)",
"format": "time_series",
"interval": "",
"intervalFactor": 1,
Expand Down Expand Up @@ -2823,14 +2823,14 @@
"steppedLine": false,
"targets": [
{
"expr": "rate(process_cpu_seconds_total{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", job=~\".*ticdc.*\"}[1m])",
"expr": "rate(process_cpu_seconds_total{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", job=~\".*ticdc.*\", instance=~\"$ticdc_instance\"}[1m])",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{instance}}",
"refId": "A"
},
{
"expr": "ticdc_server_go_max_procs{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", job=~\".*ticdc.*\"}",
"expr": "ticdc_server_go_max_procs{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", job=~\".*ticdc.*\", instance=~\"$ticdc_instance\"}",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "quota-{{instance}}",
Expand Down Expand Up @@ -2931,14 +2931,14 @@
"steppedLine": false,
"targets": [
{
"expr": " go_goroutines{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", job=~\".*ticdc.*\"}",
"expr": " go_goroutines{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", job=~\".*ticdc.*\", instance=~\"$ticdc_instance\"}",
Copy link

@gemini-code-assist gemini-code-assist bot Jan 5, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

There's a leading space in the PromQL query before go_goroutines. While Prometheus is tolerant of this, removing it would improve consistency.

Suggested change
"expr": " go_goroutines{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", job=~\".*ticdc.*\", instance=~\"$ticdc_instance\"}",
"expr": "go_goroutines{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", job=~\".*ticdc.*\", instance=~\"$ticdc_instance\"}",

"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{instance}}",
"refId": "A"
},
{
"expr": "go_threads{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", job=~\".*ticdc.*\"}",
"expr": "go_threads{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", job=~\".*ticdc.*\", instance=~\"$ticdc_instance\"}",
"format": "time_series",
"hide": true,
"intervalFactor": 1,
Expand Down Expand Up @@ -3041,14 +3041,14 @@
"steppedLine": false,
"targets": [
{
"expr": "process_resident_memory_bytes{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", job=~\".*ticdc.*\"}",
"expr": "process_resident_memory_bytes{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", job=~\".*ticdc.*\", instance=~\"$ticdc_instance\"}",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "process-{{instance}}",
"refId": "A"
},
{
"expr": "go_memstats_heap_alloc_bytes{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", job=~\".*ticdc.*\"}",
"expr": "go_memstats_heap_alloc_bytes{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", job=~\".*ticdc.*\", instance=~\"$ticdc_instance\"}",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "heap-{{instance}}",
Expand Down Expand Up @@ -3149,7 +3149,7 @@
"steppedLine": false,
"targets": [
{
"expr": "process_open_fds{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", job=~\".*ticdc.*\"}",
"expr": "process_open_fds{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", job=~\".*ticdc.*\", instance=~\"$ticdc_instance\"}",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{instance}}",
Expand Down Expand Up @@ -3248,7 +3248,7 @@
"targets": [
{
"exemplar": true,
"expr": "sum(rate(ticdc_owner_ownership_counter{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\"}[240s])) by (instance) > BOOL 0.5",
"expr": "sum(rate(ticdc_owner_ownership_counter{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", instance=~\"$ticdc_instance\"}[240s])) by (instance) > BOOL 0.5",
"format": "time_series",
"interval": "30s",
"intervalFactor": 1,
Expand Down Expand Up @@ -6375,7 +6375,7 @@
"targets": [
{
"exemplar": true,
"expr": "sum(rate(ticdc_owner_ownership_counter{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\"}[240s])) by (instance) > BOOL 0.5",
"expr": "sum(rate(ticdc_owner_ownership_counter{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", instance=~\"$ticdc_instance\"}[240s])) by (instance) > BOOL 0.5",
"format": "time_series",
"interval": "30s",
"intervalFactor": 1,
Expand Down Expand Up @@ -6494,7 +6494,7 @@
"targets": [
{
"exemplar": true,
"expr": "max(ticdc_maintainer_checkpoint_ts_lag{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", namespace=~\"$namespace\", changefeed=~\"$changefeed\"}) by (namespace, changefeed)",
"expr": "max(ticdc_maintainer_checkpoint_ts_lag{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", namespace=~\"$namespace\", changefeed=~\"$changefeed\", instance=~\"$ticdc_instance\"}) by (namespace, changefeed)",
"format": "time_series",
"interval": "",
"intervalFactor": 1,
Expand Down Expand Up @@ -6597,7 +6597,7 @@
"targets": [
{
"exemplar": true,
"expr": "max(ticdc_maintainer_resolved_ts_lag{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", namespace=~\"$namespace\", changefeed=~\"$changefeed\"}) by (namespace,changefeed)",
"expr": "max(ticdc_maintainer_resolved_ts_lag{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", namespace=~\"$namespace\", changefeed=~\"$changefeed\", instance=~\"$ticdc_instance\"}) by (namespace,changefeed)",
"format": "time_series",
"interval": "",
"intervalFactor": 1,
Expand Down Expand Up @@ -7052,7 +7052,7 @@
"targets": [
{
"exemplar": true,
"expr": "ticdc_subscription_client_requested_region_count",
"expr": "ticdc_subscription_client_requested_region_count{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", instance=~\"$ticdc_instance\"}",
"hide": false,
"interval": "",
"legendFormat": "{{instance}}-count",
Expand Down Expand Up @@ -7252,7 +7252,7 @@
"targets": [
{
"exemplar": true,
"expr": "ticdc_subscription_client_subscribed_region_count",
"expr": "ticdc_subscription_client_subscribed_region_count{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", instance=~\"$ticdc_instance\"}",
"hide": false,
"interval": "",
"legendFormat": "{{instance}}-count",
Expand Down Expand Up @@ -7515,7 +7515,7 @@
"targets": [
{
"exemplar": true,
"expr": "sum(rate(ticdc_subscription_client_resolve_lock_task_drop_count[1m])) by (instance)",
"expr": "sum(rate(ticdc_subscription_client_resolve_lock_task_drop_count{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", instance=~\"$ticdc_instance\"}[1m])) by (instance)",
"hide": false,
"interval": "",
"legendFormat": "{{instance}}",
Expand Down Expand Up @@ -15536,7 +15536,7 @@
"targets": [
{
"exemplar": true,
"expr": "max(ticdc_sink_mq_checkpoint_ts_message_count{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", namespace=~\"$namespace\",changefeed=~\"$changefeed\"}) by (namespace,changefeed, instance)",
"expr": "max(ticdc_sink_mq_checkpoint_ts_message_count{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", namespace=~\"$namespace\",changefeed=~\"$changefeed\", instance=~\"$ticdc_instance\"}) by (namespace,changefeed, instance)",
"interval": "",
"legendFormat": "{{namespace}}-{{changefeed}}-{{instance}}-P999",
"queryType": "randomWalk",
Expand Down Expand Up @@ -19697,7 +19697,7 @@
},
{
"exemplar": true,
"expr": "sum(rate(ticdc_redo_total_rows_count{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", changefeed=~\"$changefeed\"}[1m])) by (changefeed)",
"expr": "sum(rate(ticdc_redo_total_rows_count{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", changefeed=~\"$changefeed\", instance=~\"$ticdc_instance\"}[1m])) by (changefeed)",
"format": "time_series",
"hide": false,
"interval": "",
Expand Down
Loading