"type": "grafana",
"id": "grafana",
"name": "Grafana",
- "version": "5.0.4"
+ "version": "5.0.0"
},
{
"type": "panel",
"gnetId": null,
"graphTooltip": 0,
"id": null,
- "iteration": 1524726965851,
+ "iteration": 1530165442642,
"links": [],
"panels": [
{
"fill": 1,
"gridPos": {
"h": 7,
- "w": 6,
+ "w": 8,
"x": 0,
"y": 1
},
- "id": 4,
+ "id": 29,
"legend": {
"avg": false,
"current": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
- "stack": true,
+ "stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "sum by(ceph_daemon) (rate(ceph_rgw_req[30s]))",
+ "expr": "avg(rate(ceph_rgw_get_initial_lat_sum[30s]) / rate(ceph_rgw_get_initial_lat_count[30s]))",
"format": "time_series",
"intervalFactor": 1,
- "legendFormat": "{{ceph_daemon}}",
+ "legendFormat": "GET AVG",
"refId": "A"
+ },
+ {
+ "expr": "avg(rate(ceph_rgw_put_initial_lat_sum[30s]) / rate(ceph_rgw_put_initial_lat_count[30s]))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "PUT AVG",
+ "refId": "B"
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
- "title": "Total Requests/sec by RGW Instance",
+ "title": "Average GET/PUT Latencies",
"tooltip": {
"shared": true,
"sort": 0,
},
"yaxes": [
{
- "decimals": 0,
- "format": "none",
+ "format": "s",
"label": null,
"logBase": 1,
"max": null,
"logBase": 1,
"max": null,
"min": null,
- "show": true
+ "show": false
}
]
},
"dashLength": 10,
"dashes": false,
"datasource": null,
- "description": "Total bytes transferred in/out of all radosgw instances within the cluster",
"fill": 1,
"gridPos": {
"h": 7,
- "w": 6,
- "x": 6,
+ "w": 7,
+ "x": 8,
"y": 1
},
- "id": 6,
+ "id": 4,
"legend": {
"avg": false,
"current": false,
"steppedLine": false,
"targets": [
{
- "expr": "sum(rate(ceph_rgw_get_b[30s]))",
+ "expr": "sum by(rgw_host) (label_replace(rate(ceph_rgw_req[30s]), \"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\"))",
"format": "time_series",
"intervalFactor": 1,
- "legendFormat": "GETs",
+ "legendFormat": "{{rgw_host}}",
"refId": "A"
- },
- {
- "expr": "sum(rate(ceph_rgw_put_b[30s]))",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "PUTs",
- "refId": "B"
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
- "title": "Bandwidth Consumed by Type",
+ "title": "Total Requests/sec by RGW Instance",
"tooltip": {
"shared": true,
"sort": 0,
},
"yaxes": [
{
- "format": "bytes",
+ "decimals": 0,
+ "format": "none",
"label": null,
"logBase": 1,
"max": null,
"dashLength": 10,
"dashes": false,
"datasource": null,
- "description": "Total bytes transferred in/out through get/put operations, by radosgw instance",
+ "description": "Latencies are shown stacked, without a yaxis to provide a visual indication of GET latency imbalance across RGW hosts",
"fill": 1,
"gridPos": {
"h": 7,
"w": 6,
- "x": 12,
+ "x": 15,
"y": 1
},
- "id": 9,
+ "id": 31,
"legend": {
"avg": false,
"current": false,
"steppedLine": false,
"targets": [
{
- "expr": "sum by(ceph_daemon) \n (rate(ceph_rgw_get_b[30s]) + rate(ceph_rgw_put_b[30s]))",
+ "expr": "label_replace(rate(ceph_rgw_get_initial_lat_sum[30s]),\"rgw_host\",\"$1\",\"ceph_daemon\",\"rgw.(.*)\") / \nlabel_replace(rate(ceph_rgw_get_initial_lat_count[30s]),\"rgw_host\",\"$1\",\"ceph_daemon\",\"rgw.(.*)\")",
"format": "time_series",
"intervalFactor": 1,
- "legendFormat": "{{ceph_daemon}}",
+ "legendFormat": "{{rgw_host}}",
"refId": "A"
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
- "title": "Bandwidth by RGW Instance",
+ "title": "GET Latencies by RGW Instance",
"tooltip": {
"shared": true,
"sort": 0,
},
"yaxes": [
{
- "format": "bytes",
+ "decimals": null,
+ "format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": "0",
- "show": true
+ "show": false
},
{
"format": "short",
"logBase": 1,
"max": null,
"min": null,
- "show": true
+ "show": false
}
]
},
"gridPos": {
"h": 7,
"w": 3,
- "x": 18,
+ "x": 21,
"y": 1
},
"id": 8,
"valueName": "avg"
},
{
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
"datasource": null,
- "decimals": 0,
- "format": "none",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
+ "description": "Total bytes transferred in/out of all radosgw instances within the cluster",
+ "fill": 1,
"gridPos": {
- "h": 7,
- "w": 3,
- "x": 21,
- "y": 1
+ "h": 6,
+ "w": 8,
+ "x": 0,
+ "y": 8
},
- "id": 10,
- "interval": null,
+ "id": 6,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
"links": [],
- "mappingType": 1,
- "mappingTypes": [
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
{
- "name": "value to text",
- "value": 1
+ "expr": "sum(rate(ceph_rgw_get_b[30s]))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "GETs",
+ "refId": "A"
},
{
- "name": "range to text",
- "value": 2
+ "expr": "sum(rate(ceph_rgw_put_b[30s]))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "PUTs",
+ "refId": "B"
}
],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
+ "thresholds": [],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Bandwidth Consumed by Type",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
{
- "from": "null",
- "text": "N/A",
- "to": "null"
+ "format": "bytes",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
}
- ],
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": true
+ ]
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": null,
+ "description": "Total bytes transferred in/out through get/put operations, by radosgw instance",
+ "fill": 1,
+ "gridPos": {
+ "h": 6,
+ "w": 7,
+ "x": 8,
+ "y": 8
},
- "tableColumn": "",
+ "id": 9,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
"targets": [
{
- "expr": "sum(ceph_rgw_failed_req)",
+ "expr": "sum by(rgw_host) (\n (label_replace(rate(ceph_rgw_get_b[30s]), \"rgw_host\",\"$1\",\"ceph_daemon\",\"rgw.(.*)\")) + \n (label_replace(rate(ceph_rgw_put_b[30s]), \"rgw_host\",\"$1\",\"ceph_daemon\",\"rgw.(.*)\"))\n)",
"format": "time_series",
"intervalFactor": 1,
+ "legendFormat": "{{rgw_host}}",
"refId": "A"
}
],
- "thresholds": "",
- "title": "Failed HTTP Requests",
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
+ "thresholds": [],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Bandwidth by RGW Instance",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
{
- "op": "=",
- "text": "N/A",
- "value": "null"
+ "format": "bytes",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
}
- ],
- "valueName": "current"
+ ]
},
{
- "collapsed": true,
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": null,
+ "description": "Latencies are shown stacked, without a yaxis to provide a visual indication of PUT latency imbalance across RGW hosts",
+ "fill": 1,
"gridPos": {
- "h": 1,
- "w": 24,
- "x": 0,
+ "h": 6,
+ "w": 6,
+ "x": 15,
"y": 8
},
- "id": 12,
- "panels": [
- {
- "aliasColors": {
- "GETs": "#7eb26d",
- "Other": "#447ebc",
- "PUTs": "#eab839",
- "Requests": "#3f2b5b",
- "Requests Failed": "#bf1b00"
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": null,
- "fill": 1,
- "gridPos": {
+ "id": 32,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "label_replace(rate(ceph_rgw_put_initial_lat_sum[30s]),\"rgw_host\",\"$1\",\"ceph_daemon\",\"rgw.(.*)\") / \nlabel_replace(rate(ceph_rgw_put_initial_lat_count[30s]),\"rgw_host\",\"$1\",\"ceph_daemon\",\"rgw.(.*)\")",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{rgw_host}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "PUT Latencies by RGW Instance",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "decimals": null,
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": "0",
+ "show": false
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
+ }
+ ]
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": null,
+ "description": "Failed HTTP Requests by RGW instance",
+ "fill": 1,
+ "gridPos": {
+ "h": 6,
+ "w": 3,
+ "x": 21,
+ "y": 8
+ },
+ "id": 41,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "label_replace(ceph_rgw_failed_req, \"rgw_host\",\"$1\",\"ceph_daemon\",\"rgw.(.*)\")",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{rgw_host}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Failed Requests",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": false,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "none",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": "0",
+ "show": false
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
+ {
+ "collapsed": true,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 14
+ },
+ "id": 12,
+ "panels": [
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": null,
+ "fill": 1,
+ "gridPos": {
"h": 8,
- "w": 9,
+ "w": 6,
"x": 0,
- "y": 9
+ "y": 15
},
- "id": 14,
+ "id": 34,
"legend": {
"avg": false,
"current": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
+ "scopedVars": {
+ "rgw_servers": {
+ "selected": false,
+ "text": "rgw.rhs-srv-01",
+ "value": "rgw.rhs-srv-01"
+ }
+ },
"seriesOverrides": [],
"spaceLength": 10,
- "stack": true,
+ "stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "rate(ceph_rgw_failed_req{ceph_daemon=~\"[[rgw_servers]]\"}[30s])",
+ "expr": "rate(ceph_rgw_get_initial_lat_sum{ceph_daemon=~\"($rgw_servers)\"}[30s]) / rate(ceph_rgw_get_initial_lat_count{ceph_daemon=~\"($rgw_servers)\"}[30s])",
"format": "time_series",
"intervalFactor": 1,
- "legendFormat": "Requests Failed",
- "refId": "B"
- },
- {
- "expr": "rate(ceph_rgw_get{ceph_daemon=~\"[[rgw_servers]]\"}[30s])",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "GETs",
- "refId": "C"
- },
- {
- "expr": "rate(ceph_rgw_put{ceph_daemon=~\"[[rgw_servers]]\"}[30s])",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "PUTs",
- "refId": "D"
+ "legendFormat": "GET",
+ "refId": "A"
},
{
- "expr": "rate(ceph_rgw_req{ceph_daemon=~\"[[rgw_servers]]\"}[30s]) -\n (rate(ceph_rgw_get{ceph_daemon=~\"[[rgw_servers]]\"}[30s]) +\n rate(ceph_rgw_put{ceph_daemon=~\"[[rgw_servers]]\"}[30s]))",
+ "expr": "rate(ceph_rgw_put_initial_lat_sum{ceph_daemon=~\"($rgw_servers)\"}[30s]) / rate(ceph_rgw_put_initial_lat_count{ceph_daemon=~\"($rgw_servers)\"}[30s])",
"format": "time_series",
"intervalFactor": 1,
- "legendFormat": "Other",
- "refId": "A"
+ "legendFormat": "PUT",
+ "refId": "B"
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
- "title": "HTTP Request Breakdown",
+ "title": "$rgw_servers GET/PUT Latencies",
"tooltip": {
"shared": true,
"sort": 0,
},
"yaxes": [
{
- "format": "short",
+ "format": "s",
"label": null,
"logBase": 1,
"max": null,
- "min": null,
+ "min": "0",
"show": true
},
{
"logBase": 1,
"max": null,
"min": null,
- "show": true
+ "show": false
}
]
},
"fill": 1,
"gridPos": {
"h": 8,
- "w": 8,
- "x": 9,
- "y": 9
+ "w": 7,
+ "x": 6,
+ "y": 15
},
"id": 18,
"legend": {
"pointradius": 5,
"points": false,
"renderer": "flot",
+ "scopedVars": {
+ "rgw_servers": {
+ "selected": false,
+ "text": "rgw.rhs-srv-01",
+ "value": "rgw.rhs-srv-01"
+ }
+ },
"seriesOverrides": [],
"spaceLength": 10,
"stack": true,
}
]
},
+ {
+ "aliasColors": {
+ "GETs": "#7eb26d",
+ "Other": "#447ebc",
+ "PUTs": "#eab839",
+ "Requests": "#3f2b5b",
+ "Requests Failed": "#bf1b00"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": null,
+ "fill": 1,
+ "gridPos": {
+ "h": 8,
+ "w": 7,
+ "x": 13,
+ "y": 15
+ },
+ "id": 14,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "scopedVars": {
+ "rgw_servers": {
+ "selected": false,
+ "text": "rgw.rhs-srv-01",
+ "value": "rgw.rhs-srv-01"
+ }
+ },
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "rate(ceph_rgw_failed_req{ceph_daemon=~\"[[rgw_servers]]\"}[30s])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Requests Failed",
+ "refId": "B"
+ },
+ {
+ "expr": "rate(ceph_rgw_get{ceph_daemon=~\"[[rgw_servers]]\"}[30s])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "GETs",
+ "refId": "C"
+ },
+ {
+ "expr": "rate(ceph_rgw_put{ceph_daemon=~\"[[rgw_servers]]\"}[30s])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "PUTs",
+ "refId": "D"
+ },
+ {
+ "expr": "rate(ceph_rgw_req{ceph_daemon=~\"[[rgw_servers]]\"}[30s]) -\n (rate(ceph_rgw_get{ceph_daemon=~\"[[rgw_servers]]\"}[30s]) +\n rate(ceph_rgw_put{ceph_daemon=~\"[[rgw_servers]]\"}[30s]))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Other",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "HTTP Request Breakdown",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
{
"aliasColors": {
"Failures": "#bf1b00",
"format": "none",
"gridPos": {
"h": 8,
- "w": 7,
- "x": 17,
- "y": 9
+ "w": 4,
+ "x": 20,
+ "y": 15
},
"id": 23,
"interval": null,
"maxDataPoints": 3,
"nullPointMode": "connected",
"pieType": "pie",
+ "scopedVars": {
+ "rgw_servers": {
+ "selected": false,
+ "text": "rgw.rhs-srv-01",
+ "value": "rgw.rhs-srv-01"
+ }
+ },
"strokeWidth": 1,
"targets": [
{
},
"timezone": "",
"title": "Ceph RGW Workload",
- "version": 15
+ "version": 26
}