From 7bade4a618b29bf44723800be03b4ad576e7c9d8 Mon Sep 17 00:00:00 2001 From: rahulguptajss Date: Tue, 10 Dec 2024 13:59:09 +0530 Subject: [PATCH 1/3] feat: add Disk and Tape Drives Throughput by Host Adapter --- grafana/dashboards/cmode/disk.json | 216 +++++++++++++++++++++-------- 1 file changed, 158 insertions(+), 58 deletions(-) diff --git a/grafana/dashboards/cmode/disk.json b/grafana/dashboards/cmode/disk.json index b1673ade9..d5a1d4422 100644 --- a/grafana/dashboards/cmode/disk.json +++ b/grafana/dashboards/cmode/disk.json @@ -65,7 +65,7 @@ "gnetId": null, "graphTooltip": 1, "id": null, - "iteration": 1715672476697, + "iteration": 1733818694570, "links": [ { "asDropdown": true, @@ -2410,7 +2410,7 @@ "h": 9, "w": 8, "x": 0, - "y": 48 + "y": 32 }, "id": 32, "options": { @@ -2508,7 +2508,7 @@ "h": 9, "w": 8, "x": 8, - "y": 48 + "y": 32 }, "id": 34, "options": { @@ -2544,13 +2544,13 @@ ], "timeFrom": null, "timeShift": null, - "title": "Disk and Tape Drives Throughput", + "title": "Disk and Tape Drives Throughput by Node", "transformations": [], "type": "timeseries" }, { "datasource": "${DS_PROMETHEUS}", - "description": "This panel displays detail of array of counts of different types of Consistency Points (CP) and average latency in microseconds for the WAFL filesystem to process write request to the volume.", + "description": "This panel displays detail of bytes written/read through a host adapter.", "fieldConfig": { "defaults": { "color": { @@ -2598,58 +2598,17 @@ } ] }, - "unit": "µs" + "unit": "binBps" }, - "overrides": [ - { - "matcher": { - "id": "byFrameRefID", - "options": "A" - }, - "properties": [ - { - "id": "custom.axisPlacement", - "value": "right" - }, - { - "id": "custom.axisLabel", - "value": "Back to Back CP Count" - }, - { - "id": "unit", - "value": "locale" - } - ] - }, - { - "matcher": { - "id": "byFrameRefID", - "options": "B" - }, - "properties": [ - { - "id": "custom.axisPlacement", - "value": "left" - }, - { - "id": "custom.axisLabel", - "value": "Write Latency" - }, - { - "id": "unit", - "value": "µs" - } - ] - } - ] + "overrides": [] }, "gridPos": { "h": 9, "w": 8, "x": 16, - "y": 48 + "y": 32 }, - "id": 40, + "id": 62, "options": { "legend": { "calcs": [ @@ -2667,23 +2626,25 @@ "pluginVersion": "8.1.8", "targets": [ { - "expr": "sum(wafl_cp_count{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\",metric=~\"back_to_back_CP|deferred_back_to_back_CP\"})", + "exemplar": false, + "expr": "(\n sum by (datacenter,cluster,node,hostadapter) (hostadapter_bytes_written{datacenter=~\"$Datacenter\", cluster=~\"$Cluster\",node=~\"$Node\"})\n)\nand on(datacenter,cluster,node,hostadapter)\ntopk(\n $TopResources,\n sum by (datacenter,cluster,node,hostadapter) (\n avg_over_time(hostadapter_bytes_written{datacenter=~\"$Datacenter\", cluster=~\"$Cluster\",node=~\"$Node\"}[3h])\n )\n)", "hide": false, "interval": "", - "legendFormat": "Back-to-back CP Count", + "legendFormat": "{{node}} - {{hostadapter}} - WRITE", "refId": "A" }, { - "expr": "node_vol_write_latency{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"}", + "exemplar": false, + "expr": "(\n sum by (datacenter,cluster,node,hostadapter) (hostadapter_bytes_read{datacenter=~\"$Datacenter\", cluster=~\"$Cluster\",node=~\"$Node\"})\n)\nand on(datacenter,cluster,node,hostadapter)\ntopk(\n $TopResources,\n sum by (datacenter,cluster,node,hostadapter) (\n avg_over_time(hostadapter_bytes_read{datacenter=~\"$Datacenter\", cluster=~\"$Cluster\",node=~\"$Node\"}[3h])\n )\n)", "hide": false, "interval": "", - "legendFormat": "Write Latency {{node}}", + "legendFormat": "{{node}} - {{hostadapter}} - READ", "refId": "B" } ], "timeFrom": null, "timeShift": null, - "title": "CP (Consistency Points) Counts", + "title": "Top $TopResources Disk and Tape Drives Throughput by Host Adapter", "transformations": [], "type": "timeseries" }, @@ -2777,7 +2738,7 @@ "h": 9, "w": 8, "x": 0, - "y": 57 + "y": 41 }, "id": 36, "options": { @@ -2907,7 +2868,7 @@ "h": 9, "w": 8, "x": 8, - "y": 57 + "y": 41 }, "id": 38, "options": { @@ -2946,6 +2907,145 @@ "title": "Flash Pool", "transformations": [], "type": "timeseries" + }, + { + "datasource": "${DS_PROMETHEUS}", + "description": "This panel displays detail of array of counts of different types of Consistency Points (CP) and average latency in microseconds for the WAFL filesystem to process write request to the volume.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "µs" + }, + "overrides": [ + { + "matcher": { + "id": "byFrameRefID", + "options": "A" + }, + "properties": [ + { + "id": "custom.axisPlacement", + "value": "right" + }, + { + "id": "custom.axisLabel", + "value": "Back to Back CP Count" + }, + { + "id": "unit", + "value": "locale" + } + ] + }, + { + "matcher": { + "id": "byFrameRefID", + "options": "B" + }, + "properties": [ + { + "id": "custom.axisPlacement", + "value": "left" + }, + { + "id": "custom.axisLabel", + "value": "Write Latency" + }, + { + "id": "unit", + "value": "µs" + } + ] + } + ] + }, + "gridPos": { + "h": 9, + "w": 8, + "x": 16, + "y": 41 + }, + "id": 40, + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom" + }, + "tooltip": { + "mode": "single" + } + }, + "pluginVersion": "8.1.8", + "targets": [ + { + "expr": "sum(wafl_cp_count{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\",metric=~\"back_to_back_CP|deferred_back_to_back_CP\"})", + "hide": false, + "interval": "", + "legendFormat": "Back-to-back CP Count", + "refId": "A" + }, + { + "expr": "node_vol_write_latency{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"}", + "hide": false, + "interval": "", + "legendFormat": "Write Latency {{node}}", + "refId": "B" + } + ], + "timeFrom": null, + "timeShift": null, + "title": "CP (Consistency Points) Counts", + "transformations": [], + "type": "timeseries" } ], "title": "Disk Utilization: Node-level Overview", @@ -3251,5 +3351,5 @@ "timezone": "", "title": "ONTAP: Disk", "uid": "cdot-disk", - "version": 32 + "version": 33 } From f8c830c28570682530808f60b1b76006bf3a5af5 Mon Sep 17 00:00:00 2001 From: rahulguptajss Date: Tue, 10 Dec 2024 15:23:20 +0530 Subject: [PATCH 2/3] feat: add Disk and Tape Drives Throughput by Host Adapter --- grafana/dashboards/cmode/disk.json | 33 +++++++++++++++++++++++++----- 1 file changed, 28 insertions(+), 5 deletions(-) diff --git a/grafana/dashboards/cmode/disk.json b/grafana/dashboards/cmode/disk.json index d5a1d4422..96d1762d3 100644 --- a/grafana/dashboards/cmode/disk.json +++ b/grafana/dashboards/cmode/disk.json @@ -65,7 +65,7 @@ "gnetId": null, "graphTooltip": 1, "id": null, - "iteration": 1733818694570, + "iteration": 1733818694587, "links": [ { "asDropdown": true, @@ -2627,7 +2627,7 @@ "targets": [ { "exemplar": false, - "expr": "(\n sum by (datacenter,cluster,node,hostadapter) (hostadapter_bytes_written{datacenter=~\"$Datacenter\", cluster=~\"$Cluster\",node=~\"$Node\"})\n)\nand on(datacenter,cluster,node,hostadapter)\ntopk(\n $TopResources,\n sum by (datacenter,cluster,node,hostadapter) (\n avg_over_time(hostadapter_bytes_written{datacenter=~\"$Datacenter\", cluster=~\"$Cluster\",node=~\"$Node\"}[3h])\n )\n)", + "expr": "(\n sum by (datacenter,cluster,node,hostadapter) (hostadapter_bytes_written{datacenter=~\"$Datacenter\", cluster=~\"$Cluster\",node=~\"$Node\",hostadapter=~\"$HostAdapter\"})\n)\nand on(datacenter,cluster,node,hostadapter)\ntopk(\n $TopResources,\n sum by (datacenter,cluster,node,hostadapter) (\n avg_over_time(hostadapter_bytes_written{datacenter=~\"$Datacenter\", cluster=~\"$Cluster\",node=~\"$Node\",hostadapter=~\"$HostAdapter\"}[3h])\n )\n)", "hide": false, "interval": "", "legendFormat": "{{node}} - {{hostadapter}} - WRITE", @@ -2635,7 +2635,7 @@ }, { "exemplar": false, - "expr": "(\n sum by (datacenter,cluster,node,hostadapter) (hostadapter_bytes_read{datacenter=~\"$Datacenter\", cluster=~\"$Cluster\",node=~\"$Node\"})\n)\nand on(datacenter,cluster,node,hostadapter)\ntopk(\n $TopResources,\n sum by (datacenter,cluster,node,hostadapter) (\n avg_over_time(hostadapter_bytes_read{datacenter=~\"$Datacenter\", cluster=~\"$Cluster\",node=~\"$Node\"}[3h])\n )\n)", + "expr": "(\n sum by (datacenter,cluster,node,hostadapter) (hostadapter_bytes_read{datacenter=~\"$Datacenter\", cluster=~\"$Cluster\",node=~\"$Node\",hostadapter=~\"$HostAdapter\"})\n)\nand on(datacenter,cluster,node,hostadapter)\ntopk(\n $TopResources,\n sum by (datacenter,cluster,node,hostadapter) (\n avg_over_time(hostadapter_bytes_read{datacenter=~\"$Datacenter\", cluster=~\"$Cluster\",node=~\"$Node\",hostadapter=~\"$HostAdapter\"}[3h])\n )\n)", "hide": false, "interval": "", "legendFormat": "{{node}} - {{hostadapter}} - READ", @@ -3149,7 +3149,7 @@ "options": [], "query": { "query": "label_values(disk_labels{system_type!=\"7mode\",cluster=~\"$Cluster\"}, node)", - "refId": "Prometheus-Node-Variable-Query" + "refId": "StandardVariableQuery" }, "refresh": 2, "regex": "", @@ -3175,7 +3175,7 @@ "options": [], "query": { "query": "label_values(aggr_disk_busy{cluster=~\"$Cluster\",node=~\"$Node\"}, aggr)", - "refId": "Prometheus-Aggregate-Variable-Query" + "refId": "StandardVariableQuery" }, "refresh": 2, "regex": "", @@ -3238,6 +3238,29 @@ "type": "query", "useTags": false }, + { + "allValue": null, + "current": {}, + "datasource": "${DS_PROMETHEUS}", + "definition": "label_values(hostadapter_bytes_read{system_type!=\"7mode\",cluster=~\"$Cluster\",node=~\"$Node\"}, hostadapter)", + "description": null, + "error": null, + "hide": 0, + "includeAll": true, + "label": null, + "multi": true, + "name": "HostAdapter", + "options": [], + "query": { + "query": "label_values(hostadapter_bytes_read{system_type!=\"7mode\",cluster=~\"$Cluster\",node=~\"$Node\"}, hostadapter)", + "refId": "StandardVariableQuery" + }, + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "type": "query" + }, { "allValue": null, "current": { From 9badc0fd62c39da5f51e9c79eb4ed6b4002e5e34 Mon Sep 17 00:00:00 2001 From: rahulguptajss Date: Wed, 11 Dec 2024 16:55:23 +0530 Subject: [PATCH 3/3] feat: add Disk and Tape Drives Throughput by Host Adapter --- grafana/dashboards/cmode/disk.json | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/grafana/dashboards/cmode/disk.json b/grafana/dashboards/cmode/disk.json index 96d1762d3..94e813261 100644 --- a/grafana/dashboards/cmode/disk.json +++ b/grafana/dashboards/cmode/disk.json @@ -65,7 +65,7 @@ "gnetId": null, "graphTooltip": 1, "id": null, - "iteration": 1733818694587, + "iteration": 1733915992490, "links": [ { "asDropdown": true, @@ -2446,7 +2446,7 @@ ], "timeFrom": null, "timeShift": null, - "title": "Disk Throughput", + "title": "Disk Throughput by Node", "transformations": [], "type": "timeseries" }, @@ -3027,6 +3027,7 @@ "pluginVersion": "8.1.8", "targets": [ { + "exemplar": false, "expr": "sum(wafl_cp_count{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\",metric=~\"back_to_back_CP|deferred_back_to_back_CP\"})", "hide": false, "interval": "", @@ -3048,7 +3049,7 @@ "type": "timeseries" } ], - "title": "Disk Utilization: Node-level Overview", + "title": "Disk Utilization", "type": "row" } ], @@ -3374,5 +3375,5 @@ "timezone": "", "title": "ONTAP: Disk", "uid": "cdot-disk", - "version": 33 + "version": 15 }