mirror of
https://github.com/GreptimeTeam/greptimedb.git
synced 2025-12-22 22:20:02 +00:00
chore: add limit in resources panel and Cache Miss panel (#6636)
chore: add `limit` in resources panel and 'Cache Miss' panel Signed-off-by: zyy17 <zyylsxm@gmail.com>
This commit is contained in:
File diff suppressed because it is too large
Load Diff
@@ -21,14 +21,14 @@
|
||||
# Resources
|
||||
| Title | Query | Type | Description | Datasource | Unit | Legend Format |
|
||||
| --- | --- | --- | --- | --- | --- | --- |
|
||||
| Datanode Memory per Instance | `sum(process_resident_memory_bytes{instance=~"$datanode"}) by (instance, pod)` | `timeseries` | Current memory usage by instance | `prometheus` | `decbytes` | `[{{instance}}]-[{{ pod }}]` |
|
||||
| Datanode CPU Usage per Instance | `sum(rate(process_cpu_seconds_total{instance=~"$datanode"}[$__rate_interval]) * 1000) by (instance, pod)` | `timeseries` | Current cpu usage by instance | `prometheus` | `none` | `[{{ instance }}]-[{{ pod }}]` |
|
||||
| Frontend Memory per Instance | `sum(process_resident_memory_bytes{instance=~"$frontend"}) by (instance, pod)` | `timeseries` | Current memory usage by instance | `prometheus` | `decbytes` | `[{{ instance }}]-[{{ pod }}]` |
|
||||
| Frontend CPU Usage per Instance | `sum(rate(process_cpu_seconds_total{instance=~"$frontend"}[$__rate_interval]) * 1000) by (instance, pod)` | `timeseries` | Current cpu usage by instance | `prometheus` | `none` | `[{{ instance }}]-[{{ pod }}]-cpu` |
|
||||
| Metasrv Memory per Instance | `sum(process_resident_memory_bytes{instance=~"$metasrv"}) by (instance, pod)` | `timeseries` | Current memory usage by instance | `prometheus` | `decbytes` | `[{{ instance }}]-[{{ pod }}]-resident` |
|
||||
| Metasrv CPU Usage per Instance | `sum(rate(process_cpu_seconds_total{instance=~"$metasrv"}[$__rate_interval]) * 1000) by (instance, pod)` | `timeseries` | Current cpu usage by instance | `prometheus` | `none` | `[{{ instance }}]-[{{ pod }}]` |
|
||||
| Flownode Memory per Instance | `sum(process_resident_memory_bytes{instance=~"$flownode"}) by (instance, pod)` | `timeseries` | Current memory usage by instance | `prometheus` | `decbytes` | `[{{ instance }}]-[{{ pod }}]` |
|
||||
| Flownode CPU Usage per Instance | `sum(rate(process_cpu_seconds_total{instance=~"$flownode"}[$__rate_interval]) * 1000) by (instance, pod)` | `timeseries` | Current cpu usage by instance | `prometheus` | `none` | `[{{ instance }}]-[{{ pod }}]` |
|
||||
| Datanode Memory per Instance | `sum(process_resident_memory_bytes{instance=~"$datanode"}) by (instance, pod)`<br/>`max(greptime_memory_limit_in_bytes{app="greptime-datanode"})` | `timeseries` | Current memory usage by instance | `prometheus` | `bytes` | `[{{instance}}]-[{{ pod }}]` |
|
||||
| Datanode CPU Usage per Instance | `sum(rate(process_cpu_seconds_total{instance=~"$datanode"}[$__rate_interval]) * 1000) by (instance, pod)`<br/>`max(greptime_cpu_limit_in_millicores{app="greptime-datanode"})` | `timeseries` | Current cpu usage by instance | `prometheus` | `none` | `[{{ instance }}]-[{{ pod }}]` |
|
||||
| Frontend Memory per Instance | `sum(process_resident_memory_bytes{instance=~"$frontend"}) by (instance, pod)`<br/>`max(greptime_memory_limit_in_bytes{app="greptime-frontend"})` | `timeseries` | Current memory usage by instance | `prometheus` | `bytes` | `[{{ instance }}]-[{{ pod }}]` |
|
||||
| Frontend CPU Usage per Instance | `sum(rate(process_cpu_seconds_total{instance=~"$frontend"}[$__rate_interval]) * 1000) by (instance, pod)`<br/>`max(greptime_cpu_limit_in_millicores{app="greptime-frontend"})` | `timeseries` | Current cpu usage by instance | `prometheus` | `none` | `[{{ instance }}]-[{{ pod }}]-cpu` |
|
||||
| Metasrv Memory per Instance | `sum(process_resident_memory_bytes{instance=~"$metasrv"}) by (instance, pod)`<br/>`max(greptime_memory_limit_in_bytes{app="greptime-metasrv"})` | `timeseries` | Current memory usage by instance | `prometheus` | `bytes` | `[{{ instance }}]-[{{ pod }}]-resident` |
|
||||
| Metasrv CPU Usage per Instance | `sum(rate(process_cpu_seconds_total{instance=~"$metasrv"}[$__rate_interval]) * 1000) by (instance, pod)`<br/>`max(greptime_cpu_limit_in_millicores{app="greptime-metasrv"})` | `timeseries` | Current cpu usage by instance | `prometheus` | `none` | `[{{ instance }}]-[{{ pod }}]` |
|
||||
| Flownode Memory per Instance | `sum(process_resident_memory_bytes{instance=~"$flownode"}) by (instance, pod)`<br/>`max(greptime_memory_limit_in_bytes{app="greptime-flownode"})` | `timeseries` | Current memory usage by instance | `prometheus` | `bytes` | `[{{ instance }}]-[{{ pod }}]` |
|
||||
| Flownode CPU Usage per Instance | `sum(rate(process_cpu_seconds_total{instance=~"$flownode"}[$__rate_interval]) * 1000) by (instance, pod)`<br/>`max(greptime_cpu_limit_in_millicores{app="greptime-flownode"})` | `timeseries` | Current cpu usage by instance | `prometheus` | `none` | `[{{ instance }}]-[{{ pod }}]` |
|
||||
# Frontend Requests
|
||||
| Title | Query | Type | Description | Datasource | Unit | Legend Format |
|
||||
| --- | --- | --- | --- | --- | --- | --- |
|
||||
@@ -72,6 +72,7 @@
|
||||
| Region Worker Handle Bulk Insert Requests | `histogram_quantile(0.95, sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_bucket[$__rate_interval])))`<br/>`sum by(instance, stage, pod) (rate(greptime_region_worker_handle_write_sum[$__rate_interval]))/sum by(instance, stage, pod) (rate(greptime_region_worker_handle_write_count[$__rate_interval]))` | `timeseries` | Per-stage elapsed time for region worker to handle bulk insert region requests. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{stage}}]-P95` |
|
||||
| Active Series and Field Builders Count | `sum by(instance, pod) (greptime_mito_memtable_active_series_count)`<br/>`sum by(instance, pod) (greptime_mito_memtable_field_builder_count)` | `timeseries` | Compaction oinput output bytes | `prometheus` | `none` | `[{{instance}}]-[{{pod}}]-series` |
|
||||
| Region Worker Convert Requests | `histogram_quantile(0.95, sum by(le, instance, stage, pod) (rate(greptime_datanode_convert_region_request_bucket[$__rate_interval])))`<br/>`sum by(le,instance, stage, pod) (rate(greptime_datanode_convert_region_request_sum[$__rate_interval]))/sum by(le,instance, stage, pod) (rate(greptime_datanode_convert_region_request_count[$__rate_interval]))` | `timeseries` | Per-stage elapsed time for region worker to decode requests. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{stage}}]-P95` |
|
||||
| Cache Miss | `sum by (instance,pod, type) (rate(greptime_mito_cache_miss{instance=~"$datanode"}[$__rate_interval]))` | `timeseries` | The local cache miss of the datanode. | `prometheus` | -- | `[{{instance}}]-[{{pod}}]-[{{type}}]` |
|
||||
# OpenDAL
|
||||
| Title | Query | Type | Description | Datasource | Unit | Legend Format |
|
||||
| --- | --- | --- | --- | --- | --- | --- |
|
||||
|
||||
@@ -180,13 +180,18 @@ groups:
|
||||
- title: Datanode Memory per Instance
|
||||
type: timeseries
|
||||
description: Current memory usage by instance
|
||||
unit: decbytes
|
||||
unit: bytes
|
||||
queries:
|
||||
- expr: sum(process_resident_memory_bytes{instance=~"$datanode"}) by (instance, pod)
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: '[{{instance}}]-[{{ pod }}]'
|
||||
- expr: max(greptime_memory_limit_in_bytes{app="greptime-datanode"})
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: limit
|
||||
- title: Datanode CPU Usage per Instance
|
||||
type: timeseries
|
||||
description: Current cpu usage by instance
|
||||
@@ -197,16 +202,26 @@ groups:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: '[{{ instance }}]-[{{ pod }}]'
|
||||
- expr: max(greptime_cpu_limit_in_millicores{app="greptime-datanode"})
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: limit
|
||||
- title: Frontend Memory per Instance
|
||||
type: timeseries
|
||||
description: Current memory usage by instance
|
||||
unit: decbytes
|
||||
unit: bytes
|
||||
queries:
|
||||
- expr: sum(process_resident_memory_bytes{instance=~"$frontend"}) by (instance, pod)
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: '[{{ instance }}]-[{{ pod }}]'
|
||||
- expr: max(greptime_memory_limit_in_bytes{app="greptime-frontend"})
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: limit
|
||||
- title: Frontend CPU Usage per Instance
|
||||
type: timeseries
|
||||
description: Current cpu usage by instance
|
||||
@@ -217,16 +232,26 @@ groups:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: '[{{ instance }}]-[{{ pod }}]-cpu'
|
||||
- expr: max(greptime_cpu_limit_in_millicores{app="greptime-frontend"})
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: limit
|
||||
- title: Metasrv Memory per Instance
|
||||
type: timeseries
|
||||
description: Current memory usage by instance
|
||||
unit: decbytes
|
||||
unit: bytes
|
||||
queries:
|
||||
- expr: sum(process_resident_memory_bytes{instance=~"$metasrv"}) by (instance, pod)
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: '[{{ instance }}]-[{{ pod }}]-resident'
|
||||
- expr: max(greptime_memory_limit_in_bytes{app="greptime-metasrv"})
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: limit
|
||||
- title: Metasrv CPU Usage per Instance
|
||||
type: timeseries
|
||||
description: Current cpu usage by instance
|
||||
@@ -237,16 +262,26 @@ groups:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: '[{{ instance }}]-[{{ pod }}]'
|
||||
- expr: max(greptime_cpu_limit_in_millicores{app="greptime-metasrv"})
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: limit
|
||||
- title: Flownode Memory per Instance
|
||||
type: timeseries
|
||||
description: Current memory usage by instance
|
||||
unit: decbytes
|
||||
unit: bytes
|
||||
queries:
|
||||
- expr: sum(process_resident_memory_bytes{instance=~"$flownode"}) by (instance, pod)
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: '[{{ instance }}]-[{{ pod }}]'
|
||||
- expr: max(greptime_memory_limit_in_bytes{app="greptime-flownode"})
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: limit
|
||||
- title: Flownode CPU Usage per Instance
|
||||
type: timeseries
|
||||
description: Current cpu usage by instance
|
||||
@@ -257,6 +292,11 @@ groups:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: '[{{ instance }}]-[{{ pod }}]'
|
||||
- expr: max(greptime_cpu_limit_in_millicores{app="greptime-flownode"})
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: limit
|
||||
- title: Frontend Requests
|
||||
panels:
|
||||
- title: HTTP QPS per Instance
|
||||
@@ -642,6 +682,15 @@ groups:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-AVG'
|
||||
- title: Cache Miss
|
||||
type: timeseries
|
||||
description: The local cache miss of the datanode.
|
||||
queries:
|
||||
- expr: sum by (instance,pod, type) (rate(greptime_mito_cache_miss{instance=~"$datanode"}[$__rate_interval]))
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: '[{{instance}}]-[{{pod}}]-[{{type}}]'
|
||||
- title: OpenDAL
|
||||
panels:
|
||||
- title: QPS per Instance
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -21,14 +21,14 @@
|
||||
# Resources
|
||||
| Title | Query | Type | Description | Datasource | Unit | Legend Format |
|
||||
| --- | --- | --- | --- | --- | --- | --- |
|
||||
| Datanode Memory per Instance | `sum(process_resident_memory_bytes{}) by (instance, pod)` | `timeseries` | Current memory usage by instance | `prometheus` | `decbytes` | `[{{instance}}]-[{{ pod }}]` |
|
||||
| Datanode CPU Usage per Instance | `sum(rate(process_cpu_seconds_total{}[$__rate_interval]) * 1000) by (instance, pod)` | `timeseries` | Current cpu usage by instance | `prometheus` | `none` | `[{{ instance }}]-[{{ pod }}]` |
|
||||
| Frontend Memory per Instance | `sum(process_resident_memory_bytes{}) by (instance, pod)` | `timeseries` | Current memory usage by instance | `prometheus` | `decbytes` | `[{{ instance }}]-[{{ pod }}]` |
|
||||
| Frontend CPU Usage per Instance | `sum(rate(process_cpu_seconds_total{}[$__rate_interval]) * 1000) by (instance, pod)` | `timeseries` | Current cpu usage by instance | `prometheus` | `none` | `[{{ instance }}]-[{{ pod }}]-cpu` |
|
||||
| Metasrv Memory per Instance | `sum(process_resident_memory_bytes{}) by (instance, pod)` | `timeseries` | Current memory usage by instance | `prometheus` | `decbytes` | `[{{ instance }}]-[{{ pod }}]-resident` |
|
||||
| Metasrv CPU Usage per Instance | `sum(rate(process_cpu_seconds_total{}[$__rate_interval]) * 1000) by (instance, pod)` | `timeseries` | Current cpu usage by instance | `prometheus` | `none` | `[{{ instance }}]-[{{ pod }}]` |
|
||||
| Flownode Memory per Instance | `sum(process_resident_memory_bytes{}) by (instance, pod)` | `timeseries` | Current memory usage by instance | `prometheus` | `decbytes` | `[{{ instance }}]-[{{ pod }}]` |
|
||||
| Flownode CPU Usage per Instance | `sum(rate(process_cpu_seconds_total{}[$__rate_interval]) * 1000) by (instance, pod)` | `timeseries` | Current cpu usage by instance | `prometheus` | `none` | `[{{ instance }}]-[{{ pod }}]` |
|
||||
| Datanode Memory per Instance | `sum(process_resident_memory_bytes{}) by (instance, pod)`<br/>`max(greptime_memory_limit_in_bytes{app="greptime-datanode"})` | `timeseries` | Current memory usage by instance | `prometheus` | `bytes` | `[{{instance}}]-[{{ pod }}]` |
|
||||
| Datanode CPU Usage per Instance | `sum(rate(process_cpu_seconds_total{}[$__rate_interval]) * 1000) by (instance, pod)`<br/>`max(greptime_cpu_limit_in_millicores{app="greptime-datanode"})` | `timeseries` | Current cpu usage by instance | `prometheus` | `none` | `[{{ instance }}]-[{{ pod }}]` |
|
||||
| Frontend Memory per Instance | `sum(process_resident_memory_bytes{}) by (instance, pod)`<br/>`max(greptime_memory_limit_in_bytes{app="greptime-frontend"})` | `timeseries` | Current memory usage by instance | `prometheus` | `bytes` | `[{{ instance }}]-[{{ pod }}]` |
|
||||
| Frontend CPU Usage per Instance | `sum(rate(process_cpu_seconds_total{}[$__rate_interval]) * 1000) by (instance, pod)`<br/>`max(greptime_cpu_limit_in_millicores{app="greptime-frontend"})` | `timeseries` | Current cpu usage by instance | `prometheus` | `none` | `[{{ instance }}]-[{{ pod }}]-cpu` |
|
||||
| Metasrv Memory per Instance | `sum(process_resident_memory_bytes{}) by (instance, pod)`<br/>`max(greptime_memory_limit_in_bytes{app="greptime-metasrv"})` | `timeseries` | Current memory usage by instance | `prometheus` | `bytes` | `[{{ instance }}]-[{{ pod }}]-resident` |
|
||||
| Metasrv CPU Usage per Instance | `sum(rate(process_cpu_seconds_total{}[$__rate_interval]) * 1000) by (instance, pod)`<br/>`max(greptime_cpu_limit_in_millicores{app="greptime-metasrv"})` | `timeseries` | Current cpu usage by instance | `prometheus` | `none` | `[{{ instance }}]-[{{ pod }}]` |
|
||||
| Flownode Memory per Instance | `sum(process_resident_memory_bytes{}) by (instance, pod)`<br/>`max(greptime_memory_limit_in_bytes{app="greptime-flownode"})` | `timeseries` | Current memory usage by instance | `prometheus` | `bytes` | `[{{ instance }}]-[{{ pod }}]` |
|
||||
| Flownode CPU Usage per Instance | `sum(rate(process_cpu_seconds_total{}[$__rate_interval]) * 1000) by (instance, pod)`<br/>`max(greptime_cpu_limit_in_millicores{app="greptime-flownode"})` | `timeseries` | Current cpu usage by instance | `prometheus` | `none` | `[{{ instance }}]-[{{ pod }}]` |
|
||||
# Frontend Requests
|
||||
| Title | Query | Type | Description | Datasource | Unit | Legend Format |
|
||||
| --- | --- | --- | --- | --- | --- | --- |
|
||||
@@ -72,6 +72,7 @@
|
||||
| Region Worker Handle Bulk Insert Requests | `histogram_quantile(0.95, sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_bucket[$__rate_interval])))`<br/>`sum by(instance, stage, pod) (rate(greptime_region_worker_handle_write_sum[$__rate_interval]))/sum by(instance, stage, pod) (rate(greptime_region_worker_handle_write_count[$__rate_interval]))` | `timeseries` | Per-stage elapsed time for region worker to handle bulk insert region requests. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{stage}}]-P95` |
|
||||
| Active Series and Field Builders Count | `sum by(instance, pod) (greptime_mito_memtable_active_series_count)`<br/>`sum by(instance, pod) (greptime_mito_memtable_field_builder_count)` | `timeseries` | Compaction oinput output bytes | `prometheus` | `none` | `[{{instance}}]-[{{pod}}]-series` |
|
||||
| Region Worker Convert Requests | `histogram_quantile(0.95, sum by(le, instance, stage, pod) (rate(greptime_datanode_convert_region_request_bucket[$__rate_interval])))`<br/>`sum by(le,instance, stage, pod) (rate(greptime_datanode_convert_region_request_sum[$__rate_interval]))/sum by(le,instance, stage, pod) (rate(greptime_datanode_convert_region_request_count[$__rate_interval]))` | `timeseries` | Per-stage elapsed time for region worker to decode requests. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{stage}}]-P95` |
|
||||
| Cache Miss | `sum by (instance,pod, type) (rate(greptime_mito_cache_miss{}[$__rate_interval]))` | `timeseries` | The local cache miss of the datanode. | `prometheus` | -- | `[{{instance}}]-[{{pod}}]-[{{type}}]` |
|
||||
# OpenDAL
|
||||
| Title | Query | Type | Description | Datasource | Unit | Legend Format |
|
||||
| --- | --- | --- | --- | --- | --- | --- |
|
||||
|
||||
@@ -180,13 +180,18 @@ groups:
|
||||
- title: Datanode Memory per Instance
|
||||
type: timeseries
|
||||
description: Current memory usage by instance
|
||||
unit: decbytes
|
||||
unit: bytes
|
||||
queries:
|
||||
- expr: sum(process_resident_memory_bytes{}) by (instance, pod)
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: '[{{instance}}]-[{{ pod }}]'
|
||||
- expr: max(greptime_memory_limit_in_bytes{app="greptime-datanode"})
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: limit
|
||||
- title: Datanode CPU Usage per Instance
|
||||
type: timeseries
|
||||
description: Current cpu usage by instance
|
||||
@@ -197,16 +202,26 @@ groups:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: '[{{ instance }}]-[{{ pod }}]'
|
||||
- expr: max(greptime_cpu_limit_in_millicores{app="greptime-datanode"})
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: limit
|
||||
- title: Frontend Memory per Instance
|
||||
type: timeseries
|
||||
description: Current memory usage by instance
|
||||
unit: decbytes
|
||||
unit: bytes
|
||||
queries:
|
||||
- expr: sum(process_resident_memory_bytes{}) by (instance, pod)
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: '[{{ instance }}]-[{{ pod }}]'
|
||||
- expr: max(greptime_memory_limit_in_bytes{app="greptime-frontend"})
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: limit
|
||||
- title: Frontend CPU Usage per Instance
|
||||
type: timeseries
|
||||
description: Current cpu usage by instance
|
||||
@@ -217,16 +232,26 @@ groups:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: '[{{ instance }}]-[{{ pod }}]-cpu'
|
||||
- expr: max(greptime_cpu_limit_in_millicores{app="greptime-frontend"})
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: limit
|
||||
- title: Metasrv Memory per Instance
|
||||
type: timeseries
|
||||
description: Current memory usage by instance
|
||||
unit: decbytes
|
||||
unit: bytes
|
||||
queries:
|
||||
- expr: sum(process_resident_memory_bytes{}) by (instance, pod)
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: '[{{ instance }}]-[{{ pod }}]-resident'
|
||||
- expr: max(greptime_memory_limit_in_bytes{app="greptime-metasrv"})
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: limit
|
||||
- title: Metasrv CPU Usage per Instance
|
||||
type: timeseries
|
||||
description: Current cpu usage by instance
|
||||
@@ -237,16 +262,26 @@ groups:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: '[{{ instance }}]-[{{ pod }}]'
|
||||
- expr: max(greptime_cpu_limit_in_millicores{app="greptime-metasrv"})
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: limit
|
||||
- title: Flownode Memory per Instance
|
||||
type: timeseries
|
||||
description: Current memory usage by instance
|
||||
unit: decbytes
|
||||
unit: bytes
|
||||
queries:
|
||||
- expr: sum(process_resident_memory_bytes{}) by (instance, pod)
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: '[{{ instance }}]-[{{ pod }}]'
|
||||
- expr: max(greptime_memory_limit_in_bytes{app="greptime-flownode"})
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: limit
|
||||
- title: Flownode CPU Usage per Instance
|
||||
type: timeseries
|
||||
description: Current cpu usage by instance
|
||||
@@ -257,6 +292,11 @@ groups:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: '[{{ instance }}]-[{{ pod }}]'
|
||||
- expr: max(greptime_cpu_limit_in_millicores{app="greptime-flownode"})
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: limit
|
||||
- title: Frontend Requests
|
||||
panels:
|
||||
- title: HTTP QPS per Instance
|
||||
@@ -642,6 +682,15 @@ groups:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-AVG'
|
||||
- title: Cache Miss
|
||||
type: timeseries
|
||||
description: The local cache miss of the datanode.
|
||||
queries:
|
||||
- expr: sum by (instance,pod, type) (rate(greptime_mito_cache_miss{}[$__rate_interval]))
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: ${metrics}
|
||||
legendFormat: '[{{instance}}]-[{{pod}}]-[{{type}}]'
|
||||
- title: OpenDAL
|
||||
panels:
|
||||
- title: QPS per Instance
|
||||
|
||||
@@ -26,7 +26,7 @@ check_dashboards_generation() {
|
||||
./grafana/scripts/gen-dashboards.sh
|
||||
|
||||
if [[ -n "$(git diff --name-only grafana/dashboards/metrics)" ]]; then
|
||||
echo "Error: The dashboards are not generated correctly. You should execute the `make dashboards` command."
|
||||
echo "Error: The dashboards are not generated correctly. You should execute the 'make dashboards' command."
|
||||
exit 1
|
||||
fi
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user