perf(ecstore): improve erasure write diagnostics and single-block performance (#3280)

* docs(object-capacity): add localized crate docs

* fix(ecstore): improve quorum and transport diagnostics

* perf(ecstore): add safe single-block write fast path

* refactor(ecstore): collapse layered small write paths

* chore(docs): keep issue 662 design note tracked

* fix(docs): restore issue 662 design note

* chore(docs): keep issue 662 design local only

* feat(obs): add internode reliability metrics and dashboard

* feat(obs): extend internode diagnostics and service logging

* fix(docs): use AGENTS guide filename

* perf(ecstore): reuse owned buffer in small encode

* fix(ecstore): tighten small write diagnostics

---------

Co-authored-by: cxymds <Cxymds@qq.com>
This commit is contained in:
houseme
2026-06-08 17:45:56 +08:00
committed by GitHub
parent ddd35badad
commit ed73952cb6
16 changed files with 2455 additions and 123 deletions
@@ -9627,6 +9627,416 @@
],
"title": "Cluster Config / API Rejected (All)",
"type": "timeseries"
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 262
},
"id": 507,
"panels": [],
"title": "Internode Reliability",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": true,
"axisColorMode": "text",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "smooth",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
}
]
},
"unit": "ops"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 263
},
"id": 508,
"options": {
"legend": {
"calcs": [
"lastNotNull",
"max"
],
"displayMode": "table",
"placement": "right",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "12.3.2",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum by (operation, classification) (rate(rustfs_system_network_internode_operation_classified_errors_total{job=~\"$job\", operation=~\"put_file_stream|walk_dir|read_file_stream\"}[$__rate_interval]))",
"legendFormat": "{{operation}} | {{classification}}",
"range": true,
"refId": "A"
}
],
"title": "Internode Classified Errors",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": true,
"axisColorMode": "text",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "smooth",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
}
]
},
"unit": "ops"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 263
},
"id": 509,
"options": {
"legend": {
"calcs": [
"lastNotNull",
"max"
],
"displayMode": "table",
"placement": "right",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "12.3.2",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum by (operation, classification) (rate(rustfs_system_network_internode_operation_retries_total{job=~\"$job\", operation=\"put_file_stream\"}[$__rate_interval]))",
"legendFormat": "retry | {{classification}}",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum by (operation, classification) (rate(rustfs_system_network_internode_operation_retry_successes_total{job=~\"$job\", operation=\"put_file_stream\"}[$__rate_interval]))",
"legendFormat": "retry success | {{classification}}",
"range": true,
"refId": "B"
}
],
"title": "Internode Open Write Retries",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "smooth",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"max": 1,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "yellow",
"value": 0.25
},
{
"color": "red",
"value": 0.5
}
]
},
"unit": "percentunit"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 271
},
"id": 510,
"options": {
"legend": {
"calcs": [
"lastNotNull",
"max"
],
"displayMode": "table",
"placement": "right",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "12.3.2",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum by (classification) (rate(rustfs_system_network_internode_operation_retry_successes_total{job=~\"$job\", operation=\"put_file_stream\"}[$__rate_interval])) / clamp_min(sum by (classification) (rate(rustfs_system_network_internode_operation_retries_total{job=~\"$job\", operation=\"put_file_stream\"}[$__rate_interval])), 1e-9)",
"legendFormat": "{{classification}}",
"range": true,
"refId": "A"
}
],
"title": "Internode Retry Success Ratio",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": true,
"axisColorMode": "text",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "smooth",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
}
]
},
"unit": "ops"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 271
},
"id": 511,
"options": {
"legend": {
"calcs": [
"lastNotNull",
"max"
],
"displayMode": "table",
"placement": "right",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "12.3.2",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum by (stage, dominant_error) (rate(rustfs_system_storage_erasure_write_quorum_failures_total{job=~\"$job\"}[$__rate_interval]))",
"legendFormat": "{{stage}} | {{dominant_error}}",
"range": true,
"refId": "A"
}
],
"title": "Erasure Write Quorum Failures",
"type": "timeseries"
}
],
"preload": false,