chore: update flush failure metric name and update grafana dashboard (#6138)

* 1. rename `greptime_mito_flush_errors_total` metric to `greptime_mito_flush_errors_total` for consistency 2. update grafana dashboard to add following panel: - compaction input/output bytes - bulk insert handle elasped time in frontend and region worker
2025-12-26 16:10:02 +00:00 · 2025-05-20 20:05:54 +08:00
parent 7ae0e150e5
commit eaf7b4b9dd
8 changed files with 8524 additions and 7550 deletions
--- a/grafana/dashboards/metrics/cluster/dashboard.json
+++ b/grafana/dashboards/metrics/cluster/dashboard.json
--- a/grafana/dashboards/metrics/cluster/dashboard.md
+++ b/grafana/dashboards/metrics/cluster/dashboard.md
@@ -46,6 +46,7 @@
 | Ingest Rows per Instance | `sum by(instance, pod)(rate(greptime_table_operator_ingest_rows{instance=~"$frontend"}[$__rate_interval]))` | `timeseries` | Ingestion rate by row as in each frontend | `prometheus` | `rowsps` | `[{{instance}}]-[{{pod}}]` |
 | Region Call QPS per Instance | `sum by(instance, pod, request_type) (rate(greptime_grpc_region_request_count{instance=~"$frontend"}[$__rate_interval]))` | `timeseries` | Region Call QPS per Instance. | `prometheus` | `ops` | `[{{instance}}]-[{{pod}}]-[{{request_type}}]` |
 | Region Call P99 per Instance | `histogram_quantile(0.99, sum by(instance, pod, le, request_type) (rate(greptime_grpc_region_request_bucket{instance=~"$frontend"}[$__rate_interval])))` | `timeseries` | Region Call P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{request_type}}]` |
+| Frontend Handle Bulk Insert Elapsed Time  | `sum by(instance, pod, stage) (rate(greptime_table_operator_handle_bulk_insert_sum[$__rate_interval]))/sum by(instance, pod, stage) (rate(greptime_table_operator_handle_bulk_insert_count[$__rate_interval]))`<br/>`histogram_quantile(0.99, sum by(instance, pod, stage, le) (rate(greptime_table_operator_handle_bulk_insert_bucket[$__rate_interval])))` | `timeseries` | Per-stage time for frontend to handle bulk insert requests | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{stage}}]-AVG` |
 # Mito Engine
 | Title | Query | Type | Description | Datasource | Unit | Legend Format |
 | --- | --- | --- | --- | --- | --- | --- |
@@ -67,6 +68,8 @@
 | WAL sync duration seconds | `histogram_quantile(0.99, sum by(le, type, node, instance, pod) (rate(raft_engine_sync_log_duration_seconds_bucket[$__rate_interval])))` | `timeseries` | Raft engine (local disk) log store sync latency, p99 | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-p99` |
 | Log Store op duration seconds | `histogram_quantile(0.99, sum by(le,logstore,optype,instance, pod) (rate(greptime_logstore_op_elapsed_bucket[$__rate_interval])))` | `timeseries` | Write-ahead log operations latency at p99 | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{logstore}}]-[{{optype}}]-p99` |
 | Inflight Flush | `greptime_mito_inflight_flush_count` | `timeseries` | Ongoing flush task count | `prometheus` | `none` | `[{{instance}}]-[{{pod}}]` |
+| Compaction Input/Output Bytes | `sum by(instance, pod) (greptime_mito_compaction_input_bytes)`<br/>`sum by(instance, pod) (greptime_mito_compaction_output_bytes)` | `timeseries` | Compaction oinput output bytes | `prometheus` | `bytes` | `[{{instance}}]-[{{pod}}]-input` |
+| Region Worker Handle Bulk Insert Requests | `histogram_quantile(0.95, sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_bucket[$__rate_interval])))`<br/>`sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_sum[$__rate_interval]))/sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_count[$__rate_interval]))` | `timeseries` | Per-stage elapsed time for region worker to handle bulk insert region requests. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{stage}}]-P95` |
 # OpenDAL
 | Title | Query | Type | Description | Datasource | Unit | Legend Format |
 | --- | --- | --- | --- | --- | --- | --- |
--- a/grafana/dashboards/metrics/cluster/dashboard.yaml
+++ b/grafana/dashboards/metrics/cluster/dashboard.yaml
@@ -371,6 +371,21 @@ groups:
                type: prometheus
                uid: ${metrics}
              legendFormat: '[{{instance}}]-[{{pod}}]-[{{request_type}}]'
+        - title: 'Frontend Handle Bulk Insert Elapsed Time '
+          type: timeseries
+          description: Per-stage time for frontend to handle bulk insert requests
+          unit: s
+          queries:
+            - expr: sum by(instance, pod, stage) (rate(greptime_table_operator_handle_bulk_insert_sum[$__rate_interval]))/sum by(instance, pod, stage) (rate(greptime_table_operator_handle_bulk_insert_count[$__rate_interval]))
+              datasource:
+                type: prometheus
+                uid: ${metrics}
+              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-AVG'
+            - expr: histogram_quantile(0.99, sum by(instance, pod, stage, le) (rate(greptime_table_operator_handle_bulk_insert_bucket[$__rate_interval])))
+              datasource:
+                type: prometheus
+                uid: ${metrics}
+              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-P95'
    - title: Mito Engine
      panels:
        - title: Request OPS per Instance
@@ -562,6 +577,36 @@ groups:
                type: prometheus
                uid: ${metrics}
              legendFormat: '[{{instance}}]-[{{pod}}]'
+        - title: Compaction Input/Output Bytes
+          type: timeseries
+          description: Compaction oinput output bytes
+          unit: bytes
+          queries:
+            - expr: sum by(instance, pod) (greptime_mito_compaction_input_bytes)
+              datasource:
+                type: prometheus
+                uid: ${metrics}
+              legendFormat: '[{{instance}}]-[{{pod}}]-input'
+            - expr: sum by(instance, pod) (greptime_mito_compaction_output_bytes)
+              datasource:
+                type: prometheus
+                uid: ${metrics}
+              legendFormat: '[{{instance}}]-[{{pod}}]-output'
+        - title: Region Worker Handle Bulk Insert Requests
+          type: timeseries
+          description: Per-stage elapsed time for region worker to handle bulk insert region requests.
+          unit: s
+          queries:
+            - expr: histogram_quantile(0.95, sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_bucket[$__rate_interval])))
+              datasource:
+                type: prometheus
+                uid: ${metrics}
+              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-P95'
+            - expr: sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_sum[$__rate_interval]))/sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_count[$__rate_interval]))
+              datasource:
+                type: prometheus
+                uid: ${metrics}
+              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-AVG'
    - title: OpenDAL
      panels:
        - title: QPS per Instance
--- a/grafana/dashboards/metrics/standalone/dashboard.json
+++ b/grafana/dashboards/metrics/standalone/dashboard.json
--- a/grafana/dashboards/metrics/standalone/dashboard.md
+++ b/grafana/dashboards/metrics/standalone/dashboard.md
@@ -46,6 +46,7 @@
 | Ingest Rows per Instance | `sum by(instance, pod)(rate(greptime_table_operator_ingest_rows{}[$__rate_interval]))` | `timeseries` | Ingestion rate by row as in each frontend | `prometheus` | `rowsps` | `[{{instance}}]-[{{pod}}]` |
 | Region Call QPS per Instance | `sum by(instance, pod, request_type) (rate(greptime_grpc_region_request_count{}[$__rate_interval]))` | `timeseries` | Region Call QPS per Instance. | `prometheus` | `ops` | `[{{instance}}]-[{{pod}}]-[{{request_type}}]` |
 | Region Call P99 per Instance | `histogram_quantile(0.99, sum by(instance, pod, le, request_type) (rate(greptime_grpc_region_request_bucket{}[$__rate_interval])))` | `timeseries` | Region Call P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{request_type}}]` |
+| Frontend Handle Bulk Insert Elapsed Time  | `sum by(instance, pod, stage) (rate(greptime_table_operator_handle_bulk_insert_sum[$__rate_interval]))/sum by(instance, pod, stage) (rate(greptime_table_operator_handle_bulk_insert_count[$__rate_interval]))`<br/>`histogram_quantile(0.99, sum by(instance, pod, stage, le) (rate(greptime_table_operator_handle_bulk_insert_bucket[$__rate_interval])))` | `timeseries` | Per-stage time for frontend to handle bulk insert requests | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{stage}}]-AVG` |
 # Mito Engine
 | Title | Query | Type | Description | Datasource | Unit | Legend Format |
 | --- | --- | --- | --- | --- | --- | --- |
@@ -67,6 +68,8 @@
 | WAL sync duration seconds | `histogram_quantile(0.99, sum by(le, type, node, instance, pod) (rate(raft_engine_sync_log_duration_seconds_bucket[$__rate_interval])))` | `timeseries` | Raft engine (local disk) log store sync latency, p99 | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-p99` |
 | Log Store op duration seconds | `histogram_quantile(0.99, sum by(le,logstore,optype,instance, pod) (rate(greptime_logstore_op_elapsed_bucket[$__rate_interval])))` | `timeseries` | Write-ahead log operations latency at p99 | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{logstore}}]-[{{optype}}]-p99` |
 | Inflight Flush | `greptime_mito_inflight_flush_count` | `timeseries` | Ongoing flush task count | `prometheus` | `none` | `[{{instance}}]-[{{pod}}]` |
+| Compaction Input/Output Bytes | `sum by(instance, pod) (greptime_mito_compaction_input_bytes)`<br/>`sum by(instance, pod) (greptime_mito_compaction_output_bytes)` | `timeseries` | Compaction oinput output bytes | `prometheus` | `bytes` | `[{{instance}}]-[{{pod}}]-input` |
+| Region Worker Handle Bulk Insert Requests | `histogram_quantile(0.95, sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_bucket[$__rate_interval])))`<br/>`sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_sum[$__rate_interval]))/sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_count[$__rate_interval]))` | `timeseries` | Per-stage elapsed time for region worker to handle bulk insert region requests. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{stage}}]-P95` |
 # OpenDAL
 | Title | Query | Type | Description | Datasource | Unit | Legend Format |
 | --- | --- | --- | --- | --- | --- | --- |
--- a/grafana/dashboards/metrics/standalone/dashboard.yaml
+++ b/grafana/dashboards/metrics/standalone/dashboard.yaml
@@ -371,6 +371,21 @@ groups:
                type: prometheus
                uid: ${metrics}
              legendFormat: '[{{instance}}]-[{{pod}}]-[{{request_type}}]'
+        - title: 'Frontend Handle Bulk Insert Elapsed Time '
+          type: timeseries
+          description: Per-stage time for frontend to handle bulk insert requests
+          unit: s
+          queries:
+            - expr: sum by(instance, pod, stage) (rate(greptime_table_operator_handle_bulk_insert_sum[$__rate_interval]))/sum by(instance, pod, stage) (rate(greptime_table_operator_handle_bulk_insert_count[$__rate_interval]))
+              datasource:
+                type: prometheus
+                uid: ${metrics}
+              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-AVG'
+            - expr: histogram_quantile(0.99, sum by(instance, pod, stage, le) (rate(greptime_table_operator_handle_bulk_insert_bucket[$__rate_interval])))
+              datasource:
+                type: prometheus
+                uid: ${metrics}
+              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-P95'
    - title: Mito Engine
      panels:
        - title: Request OPS per Instance
@@ -562,6 +577,36 @@ groups:
                type: prometheus
                uid: ${metrics}
              legendFormat: '[{{instance}}]-[{{pod}}]'
+        - title: Compaction Input/Output Bytes
+          type: timeseries
+          description: Compaction oinput output bytes
+          unit: bytes
+          queries:
+            - expr: sum by(instance, pod) (greptime_mito_compaction_input_bytes)
+              datasource:
+                type: prometheus
+                uid: ${metrics}
+              legendFormat: '[{{instance}}]-[{{pod}}]-input'
+            - expr: sum by(instance, pod) (greptime_mito_compaction_output_bytes)
+              datasource:
+                type: prometheus
+                uid: ${metrics}
+              legendFormat: '[{{instance}}]-[{{pod}}]-output'
+        - title: Region Worker Handle Bulk Insert Requests
+          type: timeseries
+          description: Per-stage elapsed time for region worker to handle bulk insert region requests.
+          unit: s
+          queries:
+            - expr: histogram_quantile(0.95, sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_bucket[$__rate_interval])))
+              datasource:
+                type: prometheus
+                uid: ${metrics}
+              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-P95'
+            - expr: sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_sum[$__rate_interval]))/sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_count[$__rate_interval]))
+              datasource:
+                type: prometheus
+                uid: ${metrics}
+              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-AVG'
    - title: OpenDAL
      panels:
        - title: QPS per Instance
--- a/src/mito2/src/flush.rs
+++ b/src/mito2/src/flush.rs
@@ -33,7 +33,7 @@ use crate::error::{
 };
 use crate::manifest::action::{RegionEdit, RegionMetaAction, RegionMetaActionList};
 use crate::metrics::{
-    FLUSH_BYTES_TOTAL, FLUSH_ELAPSED, FLUSH_ERRORS_TOTAL, FLUSH_REQUESTS_TOTAL,
+    FLUSH_BYTES_TOTAL, FLUSH_ELAPSED, FLUSH_FAILURE_TOTAL, FLUSH_REQUESTS_TOTAL,
    INFLIGHT_FLUSH_COUNT,
 };
 use crate::read::Source;
@@ -601,7 +601,7 @@ impl FlushScheduler {
    pub(crate) fn on_flush_failed(&mut self, region_id: RegionId, err: Arc<Error>) {
        error!(err; "Region {} failed to flush, cancel all pending tasks", region_id);

-        FLUSH_ERRORS_TOTAL.inc();
+        FLUSH_FAILURE_TOTAL.inc();

        // Remove this region.
        let Some(flush_status) = self.region_status.remove(&region_id) else {
--- a/src/mito2/src/metrics.rs
+++ b/src/mito2/src/metrics.rs
@@ -70,8 +70,8 @@ lazy_static! {
        )
        .unwrap();
    /// Counter of scheduled failed flush jobs.
-    pub static ref FLUSH_ERRORS_TOTAL: IntCounter =
-        register_int_counter!("greptime_mito_flush_errors_total", "mito flush errors total").unwrap();
+    pub static ref FLUSH_FAILURE_TOTAL: IntCounter =
+        register_int_counter!("greptime_mito_flush_failure_total", "mito flush failure total").unwrap();
    /// Elapsed time of a flush job.
    pub static ref FLUSH_ELAPSED: HistogramVec = register_histogram_vec!(
            "greptime_mito_flush_elapsed",