This is an automated email from the ASF dual-hosted git repository.
nicholasjiang pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/celeborn.git
The following commit(s) were added to refs/heads/main by this push:
new c587f33aa [CELEBORN-1793] Add netty pinned memory metrics
c587f33aa is described below
commit c587f33aafccc62ffb80438ea81812582e612cbb
Author: Wang, Fei <[email protected]>
AuthorDate: Fri Jul 25 17:09:42 2025 +0800
[CELEBORN-1793] Add netty pinned memory metrics
### What changes were proposed in this pull request?
Add netty pinned memory metrics
### Why are the changes needed?
We can know more accurately the memory actually allocated from PoolArena.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Existing uts.
Closes #3019 from leixm/CELEBORN-1793.
Lead-authored-by: Wang, Fei <[email protected]>
Co-authored-by: Xianming Lei <[email protected]>
Signed-off-by: SteNicholas <[email protected]>
---
assets/grafana/celeborn-dashboard.json | 522 +++++++++++++++++++++
.../common/network/util/NettyMemoryMetrics.java | 8 +
2 files changed, 530 insertions(+)
diff --git a/assets/grafana/celeborn-dashboard.json
b/assets/grafana/celeborn-dashboard.json
index 6c66edc59..85e4af319 100644
--- a/assets/grafana/celeborn-dashboard.json
+++ b/assets/grafana/celeborn-dashboard.json
@@ -9260,6 +9260,180 @@
"title": "metrics_push_chunkSize_Value",
"type": "timeseries"
},
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "auto",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ }
+ ]
+ },
+ "unit": "decbytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 12,
+ "y": 63
+ },
+ "id": 254,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "editorMode": "code",
+ "expr":
"metrics_push_pinnedHeapMemory_Value{instance=~\"${instance}\"}",
+ "legendFormat": "${baseLegend}",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "metrics_push_pinnedHeapMemory_Value",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "auto",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ }
+ ]
+ },
+ "unit": "decbytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 0,
+ "y": 71
+ },
+ "id": 255,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "editorMode": "code",
+ "expr":
"metrics_push_pinnedDirectMemory_Value{instance=~\"${instance}\"}",
+ "legendFormat": "${baseLegend}",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "metrics_push_pinnedDirectMemory_Value",
+ "type": "timeseries"
+ },
{
"datasource": {
"type": "prometheus",
@@ -10053,6 +10227,180 @@
"title": "metrics_fetch_chunkSize_Value",
"type": "timeseries"
},
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "auto",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ }
+ ]
+ },
+ "unit": "decbytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 0,
+ "y": 111
+ },
+ "id": 256,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "editorMode": "code",
+ "expr":
"metrics_fetch_pinnedHeapMemory_Value{instance=~\"${instance}\"}",
+ "legendFormat": "${baseLegend}",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "metrics_fetch_pinnedHeapMemory_Value",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "auto",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ }
+ ]
+ },
+ "unit": "decbytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 12,
+ "y": 111
+ },
+ "id": 257,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "editorMode": "code",
+ "expr":
"metrics_fetch_pinnedDirectMemory_Value{instance=~\"${instance}\"}",
+ "legendFormat": "${baseLegend}",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "metrics_fetch_pinnedDirectMemory_Value",
+ "type": "timeseries"
+ },
{
"datasource": {
"type": "prometheus",
@@ -10846,6 +11194,180 @@
"title": "metrics_replicate_chunkSize_Value",
"type": "timeseries"
},
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "auto",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ }
+ ]
+ },
+ "unit": "decbytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 12,
+ "y": 151
+ },
+ "id": 258,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "editorMode": "code",
+ "expr":
"metrics_replicate_pinnedHeapMemory_Value{instance=~\"${instance}\"}",
+ "legendFormat": "${baseLegend}",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "metrics_replicate_pinnedHeapMemory_Value",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "auto",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ }
+ ]
+ },
+ "unit": "decbytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 0,
+ "y": 159
+ },
+ "id": 259,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "editorMode": "code",
+ "expr":
"metrics_replicate_pinnedDirectMemory_Value{instance=~\"${instance}\"}",
+ "legendFormat": "${baseLegend}",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "metrics_replicate_pinnedDirectMemory_Value",
+ "type": "timeseries"
+ },
{
"datasource": {
"type": "prometheus",
diff --git
a/common/src/main/java/org/apache/celeborn/common/network/util/NettyMemoryMetrics.java
b/common/src/main/java/org/apache/celeborn/common/network/util/NettyMemoryMetrics.java
index 59bba341b..26b4ab57e 100644
---
a/common/src/main/java/org/apache/celeborn/common/network/util/NettyMemoryMetrics.java
+++
b/common/src/main/java/org/apache/celeborn/common/network/util/NettyMemoryMetrics.java
@@ -136,6 +136,14 @@ public class NettyMemoryMetrics {
MetricRegistry.name(metricPrefix, "chunkSize"),
labels,
pooledAllocatorMetric::chunkSize);
+ source.addGauge(
+ MetricRegistry.name(metricPrefix, "pinnedHeapMemory"),
+ labels,
+ () -> ((PooledByteBufAllocator) allocator).pinnedHeapMemory());
+ source.addGauge(
+ MetricRegistry.name(metricPrefix, "pinnedDirectMemory"),
+ labels,
+ () -> ((PooledByteBufAllocator) allocator).pinnedDirectMemory());
if (verboseMetricsEnabled) {
int directArenaIndex = 0;
for (PoolArenaMetric metric : pooledAllocatorMetric.directArenas()) {
