From 22843dde4ff4831e3253d20aabb641dc015a0882 Mon Sep 17 00:00:00 2001 From: Max Kotliar Date: Tue, 28 Jul 2026 18:09:07 +0300 Subject: [PATCH 1/6] dashboards: Add Fsync avg duration panel to Troubleshooting section The commit https://github.com/VictoriaMetrics/VictoriaMetrics/commit/dd2d6807e4d6444aa41fceb6d54c3a0dc5409f9d added the following metrics to VictoriaMetrics: - vm_filestream_fsync_duration_seconds_total - it measures the summary duration for [fsync()](https://man7.org/linux/man-pages/man2/fsync.2.html) calls during background merges at VictoriaMetrics. - vm_filestream_fsync_calls_total - it counts the number of fsync() calls. This commit adds a `Fsync avg duration ($instance)` panel to the `Troubleshooting` section of the `VictoriaLogs - single-node`, `VictoriaLogs - cluster`, and `vlagent` dashboards. Follow-up on https://github.com/VictoriaMetrics/VictoriaMetrics/pull/11079 --- dashboards/victorialogs-cluster.json | 104 ++++++++++++++++++++++++ dashboards/victorialogs.json | 104 ++++++++++++++++++++++++ dashboards/vlagent.json | 104 ++++++++++++++++++++++++ dashboards/vm/victorialogs-cluster.json | 104 ++++++++++++++++++++++++ dashboards/vm/victorialogs.json | 104 ++++++++++++++++++++++++ dashboards/vm/vlagent.json | 104 ++++++++++++++++++++++++ 6 files changed, 624 insertions(+) diff --git a/dashboards/victorialogs-cluster.json b/dashboards/victorialogs-cluster.json index 7126244be3..2cdb2eb3a7 100644 --- a/dashboards/victorialogs-cluster.json +++ b/dashboards/victorialogs-cluster.json @@ -4422,6 +4422,110 @@ ], "title": "Streams churn rate 24h", "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$DS_PROMETHEUS" + }, + "description": "Average duration of fsync system calls. Spikes or high latency indicates that storage I/O cannot keep up with the write rate, which may slow down data ingestion.\n\nIf this value is elevated:\n- Check disk-related metrics.\n- If using cloud storage, check IOPS and throughput limits.\n- If using NFS, check network performance, server resource usage, and any errors on the NFS server side.\n- Check for known bugs in the filesystem or kernel version being used.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "axisSoftMin": 0, + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 124 + }, + "id": 159, + "options": { + "legend": { + "calcs": [ + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": true, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "12.4.3", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "rate(vm_filestream_fsync_duration_seconds_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) / rate(vm_filestream_fsync_calls_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", + "format": "time_series", + "instant": false, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "title": "Fsync avg duration ($instance)", + "type": "timeseries" } ], "title": "Troubleshooting", diff --git a/dashboards/victorialogs.json b/dashboards/victorialogs.json index 028b9c7164..29e864081e 100644 --- a/dashboards/victorialogs.json +++ b/dashboards/victorialogs.json @@ -4236,6 +4236,110 @@ ], "title": "Logs dropped for last 1h", "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$DS_PROMETHEUS" + }, + "description": "Average duration of fsync system calls. Spikes or high latency indicates that storage I/O cannot keep up with the write rate, which may slow down data ingestion.\n\nIf this value is elevated:\n- Check disk-related metrics.\n- If using cloud storage, check IOPS and throughput limits.\n- If using NFS, check network performance, server resource usage, and any errors on the NFS server side.\n- Check for known bugs in the filesystem or kernel version being used.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "axisSoftMin": 0, + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 124 + }, + "id": 159, + "options": { + "legend": { + "calcs": [ + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": true, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "12.4.3", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "rate(vm_filestream_fsync_duration_seconds_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) / rate(vm_filestream_fsync_calls_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", + "format": "time_series", + "instant": false, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "title": "Fsync avg duration ($instance)", + "type": "timeseries" } ], "title": "Troubleshooting", diff --git a/dashboards/vlagent.json b/dashboards/vlagent.json index 1d83fdd160..8677ad2d83 100644 --- a/dashboards/vlagent.json +++ b/dashboards/vlagent.json @@ -3808,6 +3808,110 @@ ], "title": "Restarts ($job)", "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$DS_PROMETHEUS" + }, + "description": "Average duration of fsync system calls. Spikes or high latency indicates that storage I/O cannot keep up with the write rate, which may slow down data ingestion.\n\nIf this value is elevated:\n- Check disk-related metrics.\n- If using cloud storage, check IOPS and throughput limits.\n- If using NFS, check network performance, server resource usage, and any errors on the NFS server side.\n- Check for known bugs in the filesystem or kernel version being used.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "axisSoftMin": 0, + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 124 + }, + "id": 159, + "options": { + "legend": { + "calcs": [ + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": true, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "12.4.3", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "rate(vm_filestream_fsync_duration_seconds_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) / rate(vm_filestream_fsync_calls_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", + "format": "time_series", + "instant": false, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "title": "Fsync avg duration ($instance)", + "type": "timeseries" } ], "title": "Troubleshooting", diff --git a/dashboards/vm/victorialogs-cluster.json b/dashboards/vm/victorialogs-cluster.json index e80ab535a1..e835312602 100644 --- a/dashboards/vm/victorialogs-cluster.json +++ b/dashboards/vm/victorialogs-cluster.json @@ -4423,6 +4423,110 @@ ], "title": "Streams churn rate 24h", "type": "timeseries" + }, + { + "datasource": { + "type": "victoriametrics-metrics-datasource", + "uid": "$DS_PROMETHEUS" + }, + "description": "Average duration of fsync system calls. Spikes or high latency indicates that storage I/O cannot keep up with the write rate, which may slow down data ingestion.\n\nIf this value is elevated:\n- Check disk-related metrics.\n- If using cloud storage, check IOPS and throughput limits.\n- If using NFS, check network performance, server resource usage, and any errors on the NFS server side.\n- Check for known bugs in the filesystem or kernel version being used.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "axisSoftMin": 0, + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 124 + }, + "id": 159, + "options": { + "legend": { + "calcs": [ + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": true, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "12.4.3", + "targets": [ + { + "datasource": { + "type": "victoriametrics-metrics-datasource", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "rate(vm_filestream_fsync_duration_seconds_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) / rate(vm_filestream_fsync_calls_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", + "format": "time_series", + "instant": false, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "title": "Fsync avg duration ($instance)", + "type": "timeseries" } ], "title": "Troubleshooting", diff --git a/dashboards/vm/victorialogs.json b/dashboards/vm/victorialogs.json index 1c3d79595a..64b789344a 100644 --- a/dashboards/vm/victorialogs.json +++ b/dashboards/vm/victorialogs.json @@ -4237,6 +4237,110 @@ ], "title": "Logs dropped for last 1h", "type": "timeseries" + }, + { + "datasource": { + "type": "victoriametrics-metrics-datasource", + "uid": "$DS_PROMETHEUS" + }, + "description": "Average duration of fsync system calls. Spikes or high latency indicates that storage I/O cannot keep up with the write rate, which may slow down data ingestion.\n\nIf this value is elevated:\n- Check disk-related metrics.\n- If using cloud storage, check IOPS and throughput limits.\n- If using NFS, check network performance, server resource usage, and any errors on the NFS server side.\n- Check for known bugs in the filesystem or kernel version being used.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "axisSoftMin": 0, + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 124 + }, + "id": 159, + "options": { + "legend": { + "calcs": [ + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": true, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "12.4.3", + "targets": [ + { + "datasource": { + "type": "victoriametrics-metrics-datasource", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "rate(vm_filestream_fsync_duration_seconds_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) / rate(vm_filestream_fsync_calls_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", + "format": "time_series", + "instant": false, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "title": "Fsync avg duration ($instance)", + "type": "timeseries" } ], "title": "Troubleshooting", diff --git a/dashboards/vm/vlagent.json b/dashboards/vm/vlagent.json index 8314f3b9b3..bebea01c48 100644 --- a/dashboards/vm/vlagent.json +++ b/dashboards/vm/vlagent.json @@ -3809,6 +3809,110 @@ ], "title": "Restarts ($job)", "type": "timeseries" + }, + { + "datasource": { + "type": "victoriametrics-metrics-datasource", + "uid": "$DS_PROMETHEUS" + }, + "description": "Average duration of fsync system calls. Spikes or high latency indicates that storage I/O cannot keep up with the write rate, which may slow down data ingestion.\n\nIf this value is elevated:\n- Check disk-related metrics.\n- If using cloud storage, check IOPS and throughput limits.\n- If using NFS, check network performance, server resource usage, and any errors on the NFS server side.\n- Check for known bugs in the filesystem or kernel version being used.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "axisSoftMin": 0, + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 124 + }, + "id": 159, + "options": { + "legend": { + "calcs": [ + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": true, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "12.4.3", + "targets": [ + { + "datasource": { + "type": "victoriametrics-metrics-datasource", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "rate(vm_filestream_fsync_duration_seconds_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) / rate(vm_filestream_fsync_calls_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", + "format": "time_series", + "instant": false, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "title": "Fsync avg duration ($instance)", + "type": "timeseries" } ], "title": "Troubleshooting", From a3659d33dc9ed1df11851f0457cb6145821709e8 Mon Sep 17 00:00:00 2001 From: Max Kotliar Date: Tue, 28 Jul 2026 18:31:39 +0300 Subject: [PATCH 2/6] add changelog --- docs/victorialogs/CHANGELOG.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/docs/victorialogs/CHANGELOG.md b/docs/victorialogs/CHANGELOG.md index 41e90b6874..7f5b33025b 100644 --- a/docs/victorialogs/CHANGELOG.md +++ b/docs/victorialogs/CHANGELOG.md @@ -22,6 +22,8 @@ according to the following docs: ## tip +* FEATURE: [dashboards/cluster](https://grafana.com/grafana/dashboards/23274), [dashboards/single](https://grafana.com/grafana/dashboards/22084), and [dashboards/vlagent](https://grafana.com/grafana/dashboards/24513): add `Fsync avg duration` panel to the Troubleshooting section of the single-node, cluster, and vlagent dashboards. This panel surfaces degradation of IO operation for faster incident triage. See [VictoriaMetrics#10432](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10432). + * BUGFIX: [cluster version](https://docs.victoriametrics.com/victorialogs/cluster/): evenly spread rerouted data across available `vlstorage` nodes. Previously, healthy nodes adjacent to unavailable nodes in the `-storageNode` list could receive much more data, resulting in uneven resource usage. See [#1548](https://github.com/VictoriaMetrics/VictoriaLogs/issues/1548). * BUGFIX: [data ingestion](https://docs.victoriametrics.com/victorialogs/data-ingestion/) and [querying](https://docs.victoriametrics.com/victorialogs/querying/): properly handle logs containing duplicate [stream field](https://docs.victoriametrics.com/victorialogs/keyconcepts/#stream-fields) names. Previously, [v1.52.0](https://github.com/VictoriaMetrics/VictoriaLogs/releases/tag/v1.52.0) could panic when ingesting such logs in single-node VictoriaLogs, drop them during ingestion in VictoriaLogs cluster, or panic when querying such data written by earlier releases. See [#1603](https://github.com/VictoriaMetrics/VictoriaLogs/issues/1603) and [#1604](https://github.com/VictoriaMetrics/VictoriaLogs/issues/1604). From c57cae7bb3c441c637c827b25ec9039ce77a0bd0 Mon Sep 17 00:00:00 2001 From: Max Kotliar Date: Tue, 28 Jul 2026 18:33:55 +0300 Subject: [PATCH 3/6] fix datasource --- dashboards/vlagent.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/dashboards/vlagent.json b/dashboards/vlagent.json index 8677ad2d83..dce682c6d9 100644 --- a/dashboards/vlagent.json +++ b/dashboards/vlagent.json @@ -3900,7 +3900,7 @@ { "datasource": { "type": "prometheus", - "uid": "$ds" + "uid": "$DS_PROMETHEUS" }, "editorMode": "code", "expr": "rate(vm_filestream_fsync_duration_seconds_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) / rate(vm_filestream_fsync_calls_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", From 249f64d33d263e18d6bf91385533fbf2328018a5 Mon Sep 17 00:00:00 2001 From: Max Kotliar Date: Tue, 28 Jul 2026 18:35:31 +0300 Subject: [PATCH 4/6] fix datasource --- dashboards/victorialogs.json | 2 +- dashboards/vm/victorialogs.json | 2 +- dashboards/vm/vlagent.json | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/dashboards/victorialogs.json b/dashboards/victorialogs.json index 29e864081e..35083edf7e 100644 --- a/dashboards/victorialogs.json +++ b/dashboards/victorialogs.json @@ -4328,7 +4328,7 @@ { "datasource": { "type": "prometheus", - "uid": "$ds" + "uid": "$DS_PROMETHEUS" }, "editorMode": "code", "expr": "rate(vm_filestream_fsync_duration_seconds_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) / rate(vm_filestream_fsync_calls_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", diff --git a/dashboards/vm/victorialogs.json b/dashboards/vm/victorialogs.json index 64b789344a..94d0884396 100644 --- a/dashboards/vm/victorialogs.json +++ b/dashboards/vm/victorialogs.json @@ -4329,7 +4329,7 @@ { "datasource": { "type": "victoriametrics-metrics-datasource", - "uid": "$ds" + "uid": "$DS_PROMETHEUS" }, "editorMode": "code", "expr": "rate(vm_filestream_fsync_duration_seconds_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) / rate(vm_filestream_fsync_calls_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", diff --git a/dashboards/vm/vlagent.json b/dashboards/vm/vlagent.json index bebea01c48..46abd41bc8 100644 --- a/dashboards/vm/vlagent.json +++ b/dashboards/vm/vlagent.json @@ -3901,7 +3901,7 @@ { "datasource": { "type": "victoriametrics-metrics-datasource", - "uid": "$ds" + "uid": "$DS_PROMETHEUS" }, "editorMode": "code", "expr": "rate(vm_filestream_fsync_duration_seconds_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) / rate(vm_filestream_fsync_calls_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", From 6840a7f7968e7d6e9ad9cbf44c592db709434e8c Mon Sep 17 00:00:00 2001 From: func25 Date: Wed, 29 Jul 2026 14:50:55 +0700 Subject: [PATCH 5/6] update --- dashboards/victorialogs-cluster.json | 6 +++--- dashboards/victorialogs.json | 2 +- dashboards/vlagent.json | 4 ++-- dashboards/vm/victorialogs-cluster.json | 6 +++--- dashboards/vm/victorialogs.json | 2 +- dashboards/vm/vlagent.json | 4 ++-- 6 files changed, 12 insertions(+), 12 deletions(-) diff --git a/dashboards/victorialogs-cluster.json b/dashboards/victorialogs-cluster.json index 2cdb2eb3a7..6e57148cdd 100644 --- a/dashboards/victorialogs-cluster.json +++ b/dashboards/victorialogs-cluster.json @@ -4428,7 +4428,7 @@ "type": "prometheus", "uid": "$DS_PROMETHEUS" }, - "description": "Average duration of fsync system calls. Spikes or high latency indicates that storage I/O cannot keep up with the write rate, which may slow down data ingestion.\n\nIf this value is elevated:\n- Check disk-related metrics.\n- If using cloud storage, check IOPS and throughput limits.\n- If using NFS, check network performance, server resource usage, and any errors on the NFS server side.\n- Check for known bugs in the filesystem or kernel version being used.", + "description": "Average duration of fsync system calls. Spikes or consistently high values indicate slow storage writes and may reduce data ingestion performance.\n\nIf this value is high:\n- Check disk latency and utilization.\n- For cloud storage, check IOPS and throughput limits.\n- For NFS, check network latency and NFS server resource usage.\n- Check for known filesystem or kernel issues.", "fieldConfig": { "defaults": { "color": { @@ -4514,10 +4514,10 @@ { "datasource": { "type": "prometheus", - "uid": "$ds" + "uid": "$DS_PROMETHEUS" }, "editorMode": "code", - "expr": "rate(vm_filestream_fsync_duration_seconds_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) / rate(vm_filestream_fsync_calls_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", + "expr": "rate(vm_filestream_fsync_duration_seconds_total{job=~\"$job_cluster\", instance=~\"$instance\"}[$__rate_interval]) / rate(vm_filestream_fsync_calls_total{job=~\"$job_cluster\", instance=~\"$instance\"}[$__rate_interval])", "format": "time_series", "instant": false, "legendFormat": "{{instance}}", diff --git a/dashboards/victorialogs.json b/dashboards/victorialogs.json index 35083edf7e..54d14f24d6 100644 --- a/dashboards/victorialogs.json +++ b/dashboards/victorialogs.json @@ -4242,7 +4242,7 @@ "type": "prometheus", "uid": "$DS_PROMETHEUS" }, - "description": "Average duration of fsync system calls. Spikes or high latency indicates that storage I/O cannot keep up with the write rate, which may slow down data ingestion.\n\nIf this value is elevated:\n- Check disk-related metrics.\n- If using cloud storage, check IOPS and throughput limits.\n- If using NFS, check network performance, server resource usage, and any errors on the NFS server side.\n- Check for known bugs in the filesystem or kernel version being used.", + "description": "Average duration of fsync system calls. Spikes or consistently high values indicate slow storage writes and may reduce data ingestion performance.\n\nIf this value is high:\n- Check disk latency and utilization.\n- For cloud storage, check IOPS and throughput limits.\n- For NFS, check network latency and NFS server resource usage.\n- Check for known filesystem or kernel issues.", "fieldConfig": { "defaults": { "color": { diff --git a/dashboards/vlagent.json b/dashboards/vlagent.json index dce682c6d9..9763e8f7bf 100644 --- a/dashboards/vlagent.json +++ b/dashboards/vlagent.json @@ -3814,7 +3814,7 @@ "type": "prometheus", "uid": "$DS_PROMETHEUS" }, - "description": "Average duration of fsync system calls. Spikes or high latency indicates that storage I/O cannot keep up with the write rate, which may slow down data ingestion.\n\nIf this value is elevated:\n- Check disk-related metrics.\n- If using cloud storage, check IOPS and throughput limits.\n- If using NFS, check network performance, server resource usage, and any errors on the NFS server side.\n- Check for known bugs in the filesystem or kernel version being used.", + "description": "Average duration of fsync system calls. Spikes or consistently high values indicate slow storage writes and may reduce data ingestion performance.\n\nIf this value is high:\n- Check disk latency and utilization.\n- For cloud storage, check IOPS and throughput limits.\n- For NFS, check network latency and NFS server resource usage.\n- Check for known filesystem or kernel issues.", "fieldConfig": { "defaults": { "color": { @@ -3876,7 +3876,7 @@ "x": 0, "y": 124 }, - "id": 159, + "id": 167, "options": { "legend": { "calcs": [ diff --git a/dashboards/vm/victorialogs-cluster.json b/dashboards/vm/victorialogs-cluster.json index e835312602..62b6ecc9ec 100644 --- a/dashboards/vm/victorialogs-cluster.json +++ b/dashboards/vm/victorialogs-cluster.json @@ -4429,7 +4429,7 @@ "type": "victoriametrics-metrics-datasource", "uid": "$DS_PROMETHEUS" }, - "description": "Average duration of fsync system calls. Spikes or high latency indicates that storage I/O cannot keep up with the write rate, which may slow down data ingestion.\n\nIf this value is elevated:\n- Check disk-related metrics.\n- If using cloud storage, check IOPS and throughput limits.\n- If using NFS, check network performance, server resource usage, and any errors on the NFS server side.\n- Check for known bugs in the filesystem or kernel version being used.", + "description": "Average duration of fsync system calls. Spikes or consistently high values indicate slow storage writes and may reduce data ingestion performance.\n\nIf this value is high:\n- Check disk latency and utilization.\n- For cloud storage, check IOPS and throughput limits.\n- For NFS, check network latency and NFS server resource usage.\n- Check for known filesystem or kernel issues.", "fieldConfig": { "defaults": { "color": { @@ -4515,10 +4515,10 @@ { "datasource": { "type": "victoriametrics-metrics-datasource", - "uid": "$ds" + "uid": "$DS_PROMETHEUS" }, "editorMode": "code", - "expr": "rate(vm_filestream_fsync_duration_seconds_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) / rate(vm_filestream_fsync_calls_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", + "expr": "rate(vm_filestream_fsync_duration_seconds_total{job=~\"$job_cluster\", instance=~\"$instance\"}[$__rate_interval]) / rate(vm_filestream_fsync_calls_total{job=~\"$job_cluster\", instance=~\"$instance\"}[$__rate_interval])", "format": "time_series", "instant": false, "legendFormat": "{{instance}}", diff --git a/dashboards/vm/victorialogs.json b/dashboards/vm/victorialogs.json index 94d0884396..c1954ca6c1 100644 --- a/dashboards/vm/victorialogs.json +++ b/dashboards/vm/victorialogs.json @@ -4243,7 +4243,7 @@ "type": "victoriametrics-metrics-datasource", "uid": "$DS_PROMETHEUS" }, - "description": "Average duration of fsync system calls. Spikes or high latency indicates that storage I/O cannot keep up with the write rate, which may slow down data ingestion.\n\nIf this value is elevated:\n- Check disk-related metrics.\n- If using cloud storage, check IOPS and throughput limits.\n- If using NFS, check network performance, server resource usage, and any errors on the NFS server side.\n- Check for known bugs in the filesystem or kernel version being used.", + "description": "Average duration of fsync system calls. Spikes or consistently high values indicate slow storage writes and may reduce data ingestion performance.\n\nIf this value is high:\n- Check disk latency and utilization.\n- For cloud storage, check IOPS and throughput limits.\n- For NFS, check network latency and NFS server resource usage.\n- Check for known filesystem or kernel issues.", "fieldConfig": { "defaults": { "color": { diff --git a/dashboards/vm/vlagent.json b/dashboards/vm/vlagent.json index 46abd41bc8..0cb71848ad 100644 --- a/dashboards/vm/vlagent.json +++ b/dashboards/vm/vlagent.json @@ -3815,7 +3815,7 @@ "type": "victoriametrics-metrics-datasource", "uid": "$DS_PROMETHEUS" }, - "description": "Average duration of fsync system calls. Spikes or high latency indicates that storage I/O cannot keep up with the write rate, which may slow down data ingestion.\n\nIf this value is elevated:\n- Check disk-related metrics.\n- If using cloud storage, check IOPS and throughput limits.\n- If using NFS, check network performance, server resource usage, and any errors on the NFS server side.\n- Check for known bugs in the filesystem or kernel version being used.", + "description": "Average duration of fsync system calls. Spikes or consistently high values indicate slow storage writes and may reduce data ingestion performance.\n\nIf this value is high:\n- Check disk latency and utilization.\n- For cloud storage, check IOPS and throughput limits.\n- For NFS, check network latency and NFS server resource usage.\n- Check for known filesystem or kernel issues.", "fieldConfig": { "defaults": { "color": { @@ -3877,7 +3877,7 @@ "x": 0, "y": 124 }, - "id": 159, + "id": 167, "options": { "legend": { "calcs": [ From 623cce35663b9f1f0417aebf1fbc44399094740c Mon Sep 17 00:00:00 2001 From: func25 Date: Wed, 29 Jul 2026 15:38:44 +0700 Subject: [PATCH 6/6] update --- docs/victorialogs/CHANGELOG.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/victorialogs/CHANGELOG.md b/docs/victorialogs/CHANGELOG.md index 7f5b33025b..57eb71d2cb 100644 --- a/docs/victorialogs/CHANGELOG.md +++ b/docs/victorialogs/CHANGELOG.md @@ -22,7 +22,7 @@ according to the following docs: ## tip -* FEATURE: [dashboards/cluster](https://grafana.com/grafana/dashboards/23274), [dashboards/single](https://grafana.com/grafana/dashboards/22084), and [dashboards/vlagent](https://grafana.com/grafana/dashboards/24513): add `Fsync avg duration` panel to the Troubleshooting section of the single-node, cluster, and vlagent dashboards. This panel surfaces degradation of IO operation for faster incident triage. See [VictoriaMetrics#10432](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10432). +* FEATURE: [dashboards/cluster](https://grafana.com/grafana/dashboards/23274), [dashboards/single](https://grafana.com/grafana/dashboards/22084), and [dashboards/vlagent](https://grafana.com/grafana/dashboards/24513): add `Fsync avg duration` panel to the Troubleshooting section of the single-node, cluster, and vlagent dashboards. This panel shows average `fsync` latency to help identify slow storage persistence. See [VictoriaMetrics#10432](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10432). * BUGFIX: [cluster version](https://docs.victoriametrics.com/victorialogs/cluster/): evenly spread rerouted data across available `vlstorage` nodes. Previously, healthy nodes adjacent to unavailable nodes in the `-storageNode` list could receive much more data, resulting in uneven resource usage. See [#1548](https://github.com/VictoriaMetrics/VictoriaLogs/issues/1548). * BUGFIX: [data ingestion](https://docs.victoriametrics.com/victorialogs/data-ingestion/) and [querying](https://docs.victoriametrics.com/victorialogs/querying/): properly handle logs containing duplicate [stream field](https://docs.victoriametrics.com/victorialogs/keyconcepts/#stream-fields) names. Previously, [v1.52.0](https://github.com/VictoriaMetrics/VictoriaLogs/releases/tag/v1.52.0) could panic when ingesting such logs in single-node VictoriaLogs, drop them during ingestion in VictoriaLogs cluster, or panic when querying such data written by earlier releases. See [#1603](https://github.com/VictoriaMetrics/VictoriaLogs/issues/1603) and [#1604](https://github.com/VictoriaMetrics/VictoriaLogs/issues/1604).