mirror of
https://github.com/ceph/ceph
synced 2026-08-02 07:03:18 +00:00
mgr/dashboard: introduce HAProxy metrics for RGW
Fixes: https://tracker.ceph.com/issues/53311 Signed-off-by: Avan Thakkar <athakkar@redhat.com>
This commit is contained in:
Avan Thakkar
parent
961bfc8e45
commit
8d83126e51
@ -3,8 +3,8 @@ local g = import 'grafana.libsonnet';
|
||||
local dashboardSchema(title, description, uid, time_from, refresh, schemaVersion, tags, timezone, timepicker) =
|
||||
g.dashboard.new(title=title, description=description, uid=uid, time_from=time_from, refresh=refresh, schemaVersion=schemaVersion, tags=tags, timezone=timezone, timepicker=timepicker);
|
||||
|
||||
local graphPanelSchema(aliasColors, title, description, nullPointMode, stack, formatY1, formatY2, labelY1, labelY2, min, fill, datasource) =
|
||||
g.graphPanel.new(aliasColors=aliasColors, title=title, description=description, nullPointMode=nullPointMode, stack=stack, formatY1=formatY1, formatY2=formatY2, labelY1=labelY1, labelY2=labelY2, min=min, fill=fill, datasource=datasource);
|
||||
local graphPanelSchema(aliasColors, title, description, nullPointMode, stack, formatY1, formatY2, labelY1, labelY2, min, fill, datasource, legend_alignAsTable=false, legend_avg=false, legend_min=false, legend_max=false, legend_current=false, legend_values=false) =
|
||||
g.graphPanel.new(aliasColors=aliasColors, title=title, description=description, nullPointMode=nullPointMode, stack=stack, formatY1=formatY1, formatY2=formatY2, labelY1=labelY1, labelY2=labelY2, min=min, fill=fill, datasource=datasource, legend_alignAsTable=legend_alignAsTable, legend_avg=legend_avg, legend_min=legend_min, legend_max=legend_max, legend_current=legend_current, legend_values=legend_values);
|
||||
|
||||
local addTargetSchema(expr, intervalFactor, format, legendFormat) =
|
||||
g.prometheus.target(expr=expr, intervalFactor=intervalFactor, format=format, legendFormat=legendFormat);
|
||||
@ -250,8 +250,8 @@ local addStyle(alias, colorMode, colors, dateFormat, decimals, mappingType, patt
|
||||
}
|
||||
{
|
||||
"radosgw-overview.json":
|
||||
local RgwOverviewPanel(title, description, formatY1, formatY2, expr1, legendFormat1, x, y, w, h) =
|
||||
graphPanelSchema({}, title, description, 'null', false, formatY1, formatY2, null, null, 0, 1, '$datasource')
|
||||
local RgwOverviewPanel(title, description, formatY1, formatY2, expr1, legendFormat1, x, y, w, h, datasource='$datasource', legend_alignAsTable=false, legend_avg=false, legend_min=false, legend_max=false, legend_current=false, legend_values=false) =
|
||||
graphPanelSchema({}, title, description, 'null', false, formatY1, formatY2, null, null, 0, 1, datasource, legend_alignAsTable, legend_avg, legend_min, legend_max, legend_current, legend_values)
|
||||
.addTargets(
|
||||
[addTargetSchema(expr1, 1, 'time_series', legendFormat1)]) + {gridPos: {x: x, y: y, w: w, h: h}};
|
||||
|
||||
@ -271,6 +271,12 @@ local addStyle(alias, colorMode, colors, dateFormat, decimals, mappingType, patt
|
||||
.addTemplate(
|
||||
addTemplateSchema('rgw_servers', '$datasource', 'label_values(ceph_rgw_req, ceph_daemon)', 1, true, 1, '', '')
|
||||
)
|
||||
.addTemplate(
|
||||
addTemplateSchema('code', '$datasource', 'label_values(haproxy_server_http_responses_total{instance=~"$ingress_service"}, code)', 1, true, 1, 'HTTP Code', '')
|
||||
)
|
||||
.addTemplate(
|
||||
addTemplateSchema('ingress_service', '$datasource', 'label_values(haproxy_server_status, instance)', 1, true, 1, 'Ingress Service', '')
|
||||
)
|
||||
.addTemplate(
|
||||
g.template.datasource('datasource', 'prometheus', 'default', label='Data Source')
|
||||
)
|
||||
@ -289,8 +295,72 @@ local addStyle(alias, colorMode, colors, dateFormat, decimals, mappingType, patt
|
||||
RgwOverviewPanel(
|
||||
'Bandwidth by RGW Instance', 'Total bytes transferred in/out through get/put operations, by radosgw instance', 'bytes', 'short', '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)', '{{rgw_host}}', 8, 8, 7, 6),
|
||||
RgwOverviewPanel(
|
||||
'PUT Latencies by RGW Instance', 'Latencies are shown stacked, without a yaxis to provide a visual indication of PUT latency imbalance across RGW hosts', 's', 'short', '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.(.*)\")', '{{rgw_host}}', 15, 8, 6, 6)
|
||||
])
|
||||
'PUT Latencies by RGW Instance', 'Latencies are shown stacked, without a yaxis to provide a visual indication of PUT latency imbalance across RGW hosts', 's', 'short', '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\",\"$1\",\"ceph_daemon\",\"rgw.(.*)\")', '{{rgw_host}}', 15, 8, 6, 6),
|
||||
|
||||
addRowSchema(false, true, 'RGW Overview - HAProxy Metrics') + {gridPos: {x: 0, y: 12, w: 9, h: 12}},
|
||||
RgwOverviewPanel(
|
||||
'Total responses by HTTP code', '', 'short', 'short', 'sum(irate(haproxy_frontend_http_responses_total{code=~"$code",instance=~"$ingress_service",proxy=~"frontend"}[5m])) by (code)', 'Frontend {{ code }}', 0, 12, 5, 12, '$datasource', true, true, true, true, true, true)
|
||||
.addTargets(
|
||||
[addTargetSchema('sum(irate(haproxy_backend_http_responses_total{code=~"$code",instance=~"$ingress_service",proxy=~"backend"}[5m])) by (code)', 1, 'time_series', 'Backend {{ code }}')])
|
||||
.addSeriesOverride([
|
||||
{ "alias": "/.*Back.*/",
|
||||
"transform": "negative-Y" },
|
||||
{ "alias": "/.*1.*/" },
|
||||
{ "alias": "/.*2.*/" },
|
||||
{ "alias": "/.*3.*/" },
|
||||
{ "alias": "/.*4.*/" },
|
||||
{ "alias": "/.*5.*/" },
|
||||
{ "alias": "/.*other.*/" }
|
||||
]),
|
||||
RgwOverviewPanel(
|
||||
'Total requests / responses', '', 'short', 'short',
|
||||
'sum(irate(haproxy_frontend_http_requests_total{proxy=~"frontend",instance=~"$ingress_service"}[5m])) by (instance)', 'Requests', 5, 12, 5, 12, '$datasource', true, true, true, true, true, true)
|
||||
.addTargets(
|
||||
[addTargetSchema('sum(irate(haproxy_backend_response_errors_total{proxy=~"backend",instance=~"$ingress_service"}[5m])) by (instance)', 2, 'time_series', 'Response errors'),
|
||||
addTargetSchema('sum(irate(haproxy_frontend_request_errors_total{proxy=~"frontend",instance=~"$ingress_service"}[5m])) by (instance)', 1, 'time_series', 'Requests errors'),
|
||||
addTargetSchema('sum(irate(haproxy_backend_redispatch_warnings_total{proxy=~"backend",instance=~"$ingress_service"}[5m])) by (instance)', 2, 'time_series', 'Backend redispatch'),
|
||||
addTargetSchema('sum(irate(haproxy_backend_retry_warnings_total{proxy=~"backend",instance=~"$ingress_service"}[5m])) by (instance)', 2, 'time_series', 'Backend retry'),
|
||||
addTargetSchema('sum(irate(haproxy_frontend_requests_denied_total{proxy=~"frontend",instance=~"$ingress_service"}[5m])) by (instance)', 2, 'time_series', 'Request denied'),
|
||||
addTargetSchema('sum(haproxy_backend_current_queue{proxy=~"backend",instance=~"$ingress_service"}) by (instance)', 2, 'time_series', 'Backend Queued'),
|
||||
])
|
||||
.addSeriesOverride([
|
||||
{
|
||||
"alias": "/.*Response.*/",
|
||||
"transform": "negative-Y"
|
||||
},
|
||||
{
|
||||
"alias": "/.*Backend.*/",
|
||||
"transform": "negative-Y"
|
||||
}
|
||||
]),
|
||||
RgwOverviewPanel(
|
||||
'Total number of connections', '', 'short', 'short',
|
||||
'sum(irate(haproxy_frontend_connections_total{proxy=~"frontend",instance=~"$ingress_service"}[5m])) by (instance)', 'Front', 10, 12, 5, 12, '$datasource', true, true, true, true, true, true)
|
||||
.addTargets(
|
||||
[addTargetSchema('sum(irate(haproxy_backend_connection_attempts_total{proxy=~"backend",instance=~"$ingress_service"}[5m])) by (instance)', 1, 'time_series', 'Back'),
|
||||
addTargetSchema('sum(irate(haproxy_backend_connection_errors_total{proxy=~"backend",instance=~"$ingress_service"}[5m])) by (instance)', 1, 'time_series', 'Back errors'),
|
||||
])
|
||||
.addSeriesOverride([
|
||||
{
|
||||
"alias": "/.*Back.*/",
|
||||
"transform": "negative-Y"
|
||||
}
|
||||
]),
|
||||
RgwOverviewPanel(
|
||||
'Current total of incoming / outgoing bytes', '', 'short', 'short',
|
||||
'sum(irate(haproxy_frontend_bytes_in_total{proxy=~"frontend",instance=~"$ingress_service"}[5m])*8) by (instance)', 'IN Front', 15, 12, 6, 12, '$datasource', true, true, true, true, true, true)
|
||||
.addTargets(
|
||||
[addTargetSchema('sum(irate(haproxy_frontend_bytes_out_total{proxy=~"frontend",instance=~"$ingress_service"}[5m])*8) by (instance)', 2, 'time_series', 'OUT Front'),
|
||||
addTargetSchema('sum(irate(haproxy_backend_bytes_in_total{proxy=~"backend",instance=~"$ingress_service"}[5m])*8) by (instance)', 2, 'time_series', 'IN Back'),
|
||||
addTargetSchema('sum(irate(haproxy_backend_bytes_out_total{proxy=~"backend",instance=~"$ingress_service"}[5m])*8) by (instance)', 2, 'time_series', 'OUT Back')
|
||||
])
|
||||
.addSeriesOverride([
|
||||
{
|
||||
"alias": "/.*OUT.*/",
|
||||
"transform": "negative-Y"
|
||||
}
|
||||
])
|
||||
])
|
||||
}
|
||||
{
|
||||
"radosgw-detail.json":
|
||||
|
||||
@ -579,6 +579,499 @@
|
||||
"show": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"collapse": false,
|
||||
"collapsed": false,
|
||||
"gridPos": {
|
||||
"h": 12,
|
||||
"w": 9,
|
||||
"x": 0,
|
||||
"y": 12
|
||||
},
|
||||
"id": 9,
|
||||
"panels": [ ],
|
||||
"repeat": null,
|
||||
"repeatIteration": null,
|
||||
"repeatRowId": null,
|
||||
"showTitle": true,
|
||||
"title": "RGW Overview - HAProxy Metrics",
|
||||
"titleSize": "h6",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"aliasColors": { },
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"description": "",
|
||||
"fill": 1,
|
||||
"gridPos": {
|
||||
"h": 12,
|
||||
"w": 5,
|
||||
"x": 0,
|
||||
"y": 12
|
||||
},
|
||||
"id": 10,
|
||||
"legend": {
|
||||
"alignAsTable": true,
|
||||
"avg": true,
|
||||
"current": true,
|
||||
"max": true,
|
||||
"min": true,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 1,
|
||||
"links": [ ],
|
||||
"nullPointMode": "null",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"repeat": null,
|
||||
"seriesOverrides": [
|
||||
[
|
||||
{
|
||||
"alias": "/.*Back.*/",
|
||||
"transform": "negative-Y"
|
||||
},
|
||||
{
|
||||
"alias": "/.*1.*/"
|
||||
},
|
||||
{
|
||||
"alias": "/.*2.*/"
|
||||
},
|
||||
{
|
||||
"alias": "/.*3.*/"
|
||||
},
|
||||
{
|
||||
"alias": "/.*4.*/"
|
||||
},
|
||||
{
|
||||
"alias": "/.*5.*/"
|
||||
},
|
||||
{
|
||||
"alias": "/.*other.*/"
|
||||
}
|
||||
]
|
||||
],
|
||||
"spaceLength": 10,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(irate(haproxy_frontend_http_responses_total{code=~\"$code\",instance=~\"$ingress_service\",proxy=~\"frontend\"}[5m])) by (code)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 1,
|
||||
"legendFormat": "Frontend {{ code }}",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "sum(irate(haproxy_backend_http_responses_total{code=~\"$code\",instance=~\"$ingress_service\",proxy=~\"backend\"}[5m])) by (code)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 1,
|
||||
"legendFormat": "Backend {{ code }}",
|
||||
"refId": "B"
|
||||
}
|
||||
],
|
||||
"thresholds": [ ],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Total responses by HTTP code",
|
||||
"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": 0,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"aliasColors": { },
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"description": "",
|
||||
"fill": 1,
|
||||
"gridPos": {
|
||||
"h": 12,
|
||||
"w": 5,
|
||||
"x": 5,
|
||||
"y": 12
|
||||
},
|
||||
"id": 11,
|
||||
"legend": {
|
||||
"alignAsTable": true,
|
||||
"avg": true,
|
||||
"current": true,
|
||||
"max": true,
|
||||
"min": true,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 1,
|
||||
"links": [ ],
|
||||
"nullPointMode": "null",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"repeat": null,
|
||||
"seriesOverrides": [
|
||||
[
|
||||
{
|
||||
"alias": "/.*Response.*/",
|
||||
"transform": "negative-Y"
|
||||
},
|
||||
{
|
||||
"alias": "/.*Backend.*/",
|
||||
"transform": "negative-Y"
|
||||
}
|
||||
]
|
||||
],
|
||||
"spaceLength": 10,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(irate(haproxy_frontend_http_requests_total{proxy=~\"frontend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 1,
|
||||
"legendFormat": "Requests",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "sum(irate(haproxy_backend_response_errors_total{proxy=~\"backend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Response errors",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(irate(haproxy_frontend_request_errors_total{proxy=~\"frontend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 1,
|
||||
"legendFormat": "Requests errors",
|
||||
"refId": "C"
|
||||
},
|
||||
{
|
||||
"expr": "sum(irate(haproxy_backend_redispatch_warnings_total{proxy=~\"backend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Backend redispatch",
|
||||
"refId": "D"
|
||||
},
|
||||
{
|
||||
"expr": "sum(irate(haproxy_backend_retry_warnings_total{proxy=~\"backend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Backend retry",
|
||||
"refId": "E"
|
||||
},
|
||||
{
|
||||
"expr": "sum(irate(haproxy_frontend_requests_denied_total{proxy=~\"frontend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Request denied",
|
||||
"refId": "F"
|
||||
},
|
||||
{
|
||||
"expr": "sum(haproxy_backend_current_queue{proxy=~\"backend\",instance=~\"$ingress_service\"}) by (instance)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "Backend Queued",
|
||||
"refId": "G"
|
||||
}
|
||||
],
|
||||
"thresholds": [ ],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Total requests / responses",
|
||||
"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": 0,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"aliasColors": { },
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"description": "",
|
||||
"fill": 1,
|
||||
"gridPos": {
|
||||
"h": 12,
|
||||
"w": 5,
|
||||
"x": 10,
|
||||
"y": 12
|
||||
},
|
||||
"id": 12,
|
||||
"legend": {
|
||||
"alignAsTable": true,
|
||||
"avg": true,
|
||||
"current": true,
|
||||
"max": true,
|
||||
"min": true,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 1,
|
||||
"links": [ ],
|
||||
"nullPointMode": "null",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"repeat": null,
|
||||
"seriesOverrides": [
|
||||
[
|
||||
{
|
||||
"alias": "/.*Back.*/",
|
||||
"transform": "negative-Y"
|
||||
}
|
||||
]
|
||||
],
|
||||
"spaceLength": 10,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(irate(haproxy_frontend_connections_total{proxy=~\"frontend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 1,
|
||||
"legendFormat": "Front",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "sum(irate(haproxy_backend_connection_attempts_total{proxy=~\"backend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 1,
|
||||
"legendFormat": "Back",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(irate(haproxy_backend_connection_errors_total{proxy=~\"backend\",instance=~\"$ingress_service\"}[5m])) by (instance)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 1,
|
||||
"legendFormat": "Back errors",
|
||||
"refId": "C"
|
||||
}
|
||||
],
|
||||
"thresholds": [ ],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Total number of connections",
|
||||
"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": 0,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"aliasColors": { },
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"description": "",
|
||||
"fill": 1,
|
||||
"gridPos": {
|
||||
"h": 12,
|
||||
"w": 6,
|
||||
"x": 15,
|
||||
"y": 12
|
||||
},
|
||||
"id": 13,
|
||||
"legend": {
|
||||
"alignAsTable": true,
|
||||
"avg": true,
|
||||
"current": true,
|
||||
"max": true,
|
||||
"min": true,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 1,
|
||||
"links": [ ],
|
||||
"nullPointMode": "null",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"repeat": null,
|
||||
"seriesOverrides": [
|
||||
[
|
||||
{
|
||||
"alias": "/.*OUT.*/",
|
||||
"transform": "negative-Y"
|
||||
}
|
||||
]
|
||||
],
|
||||
"spaceLength": 10,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(irate(haproxy_frontend_bytes_in_total{proxy=~\"frontend\",instance=~\"$ingress_service\"}[5m])*8) by (instance)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 1,
|
||||
"legendFormat": "IN Front",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "sum(irate(haproxy_frontend_bytes_out_total{proxy=~\"frontend\",instance=~\"$ingress_service\"}[5m])*8) by (instance)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "OUT Front",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(irate(haproxy_backend_bytes_in_total{proxy=~\"backend\",instance=~\"$ingress_service\"}[5m])*8) by (instance)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "IN Back",
|
||||
"refId": "C"
|
||||
},
|
||||
{
|
||||
"expr": "sum(irate(haproxy_backend_bytes_out_total{proxy=~\"backend\",instance=~\"$ingress_service\"}[5m])*8) by (instance)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "OUT Back",
|
||||
"refId": "D"
|
||||
}
|
||||
],
|
||||
"thresholds": [ ],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Current total of incoming / outgoing bytes",
|
||||
"tooltip": {
|
||||
"shared": true,
|
||||
"sort": 0,
|
||||
"value_type": "individual"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"buckets": null,
|
||||
"mode": "time",
|
||||
"name": null,
|
||||
"show": true,
|
||||
"values": [ ]
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"refresh": "15s",
|
||||
@ -610,6 +1103,46 @@
|
||||
"type": "query",
|
||||
"useTags": false
|
||||
},
|
||||
{
|
||||
"allValue": null,
|
||||
"current": { },
|
||||
"datasource": "$datasource",
|
||||
"hide": 0,
|
||||
"includeAll": true,
|
||||
"label": "HTTP Code",
|
||||
"multi": false,
|
||||
"name": "code",
|
||||
"options": [ ],
|
||||
"query": "label_values(haproxy_server_http_responses_total{instance=~\"$ingress_service\"}, code)",
|
||||
"refresh": 1,
|
||||
"regex": "",
|
||||
"sort": 1,
|
||||
"tagValuesQuery": "",
|
||||
"tags": [ ],
|
||||
"tagsQuery": "",
|
||||
"type": "query",
|
||||
"useTags": false
|
||||
},
|
||||
{
|
||||
"allValue": null,
|
||||
"current": { },
|
||||
"datasource": "$datasource",
|
||||
"hide": 0,
|
||||
"includeAll": true,
|
||||
"label": "Ingress Service",
|
||||
"multi": false,
|
||||
"name": "ingress_service",
|
||||
"options": [ ],
|
||||
"query": "label_values(haproxy_server_status, instance)",
|
||||
"refresh": 1,
|
||||
"regex": "",
|
||||
"sort": 1,
|
||||
"tagValuesQuery": "",
|
||||
"tags": [ ],
|
||||
"tagsQuery": "",
|
||||
"type": "query",
|
||||
"useTags": false
|
||||
},
|
||||
{
|
||||
"current": {
|
||||
"text": "default",
|
||||
|
||||
@ -0,0 +1,212 @@
|
||||
Feature: RGW Overview Dashboard
|
||||
|
||||
Scenario: "Test Average GET Latencies"
|
||||
Given the following series:
|
||||
| metrics | values |
|
||||
| ceph_rgw_get_initial_lat_sum{ceph_daemon="rgw.foo",instance="127.0.0.1", job="ceph"} | 10 50 100 |
|
||||
| ceph_rgw_get_initial_lat_count{ceph_daemon="rgw.foo", instance="127.0.0.1", job="ceph"} | 20 60 80 |
|
||||
When interval is `30s`
|
||||
Then Grafana panel `Average GET/PUT Latencies` with legend `GET AVG` shows:
|
||||
| metrics | values |
|
||||
| {ceph_daemon="rgw.foo",instance="127.0.0.1", job="ceph"} | 2.5000000000000004 |
|
||||
|
||||
Scenario: "Test Average PUT Latencies"
|
||||
Given the following series:
|
||||
| metrics | values |
|
||||
| ceph_rgw_put_initial_lat_sum{ceph_daemon="rgw.foo",instance="127.0.0.1", job="ceph"} | 15 35 55 |
|
||||
| ceph_rgw_put_initial_lat_count{ceph_daemon="rgw.foo", instance="127.0.0.1", job="ceph"} | 10 30 50 |
|
||||
When interval is `30s`
|
||||
Then Grafana panel `Average GET/PUT Latencies` with legend `PUT AVG` shows:
|
||||
| metrics | values |
|
||||
| {ceph_daemon="rgw.foo",instance="127.0.0.1", job="ceph"} | 1 |
|
||||
|
||||
Scenario: "Test Total Requests/sec by RGW Instance"
|
||||
Given the following series:
|
||||
| metrics | values |
|
||||
| ceph_rgw_req{ceph_daemon="rgw.1",instance="127.0.0.1",job="ceph"} | 10 50 100 |
|
||||
When interval is `30s`
|
||||
Then Grafana panel `Total Requests/sec by RGW Instance` with legend `{{rgw_host}}` shows:
|
||||
| metrics | values |
|
||||
| {rgw_host="1"} | 1.6666666666666667 |
|
||||
|
||||
Scenario: "Test Bandwidth Consumed by Type- GET"
|
||||
Given the following series:
|
||||
| metrics | values |
|
||||
| ceph_rgw_get_b{ceph_daemon="rgw.1",instance="127.0.0.1",job="ceph"} | 10 50 100 |
|
||||
When evaluation time is `1m`
|
||||
And interval is `30s`
|
||||
Then Grafana panel `Bandwidth Consumed by Type` with legend `GETs` shows:
|
||||
| metrics | values |
|
||||
| {} | 1.6666666666666667 |
|
||||
|
||||
Scenario: "Test Bandwidth Consumed by Type- PUT"
|
||||
Given the following series:
|
||||
| metrics | values |
|
||||
| ceph_rgw_put_b{ceph_daemon="rgw.1",instance="127.0.0.1",job="ceph"} | 5 20 50 |
|
||||
When evaluation time is `1m`
|
||||
And interval is `30s`
|
||||
Then Grafana panel `Bandwidth Consumed by Type` with legend `PUTs` shows:
|
||||
| metrics | values |
|
||||
| {} | 1 |
|
||||
|
||||
Scenario: "Test Total backend responses by HTTP code"
|
||||
Given the following series:
|
||||
| metrics | values |
|
||||
| haproxy_backend_http_responses_total{code="200",instance="ingress.rgw.1",proxy="backend"} | 10 100 |
|
||||
| haproxy_backend_http_responses_total{code="404",instance="ingress.rgw.1",proxy="backend"} | 20 200 |
|
||||
When variable `ingress_service` is `ingress.rgw.1`
|
||||
When variable `code` is `200`
|
||||
Then Grafana panel `Total responses by HTTP code` with legend `Backend {{ code }}` shows:
|
||||
| metrics | values |
|
||||
| {code="200"} | 1.5 |
|
||||
|
||||
Scenario: "Test Total frontend responses by HTTP code"
|
||||
Given the following series:
|
||||
| metrics | values |
|
||||
| haproxy_frontend_http_responses_total{code="200",instance="ingress.rgw.1",proxy="frontend"} | 10 100 |
|
||||
| haproxy_frontend_http_responses_total{code="404",instance="ingress.rgw.1",proxy="frontend"} | 20 200 |
|
||||
When variable `ingress_service` is `ingress.rgw.1`
|
||||
When variable `code` is `200`
|
||||
Then Grafana panel `Total responses by HTTP code` with legend `Frontend {{ code }}` shows:
|
||||
| metrics | values |
|
||||
| {code="200"} | 1.5 |
|
||||
|
||||
Scenario: "Test Total http frontend requests by instance"
|
||||
Given the following series:
|
||||
| metrics | values |
|
||||
| haproxy_frontend_http_requests_total{proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
|
||||
| haproxy_frontend_http_requests_total{proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
|
||||
When variable `ingress_service` is `ingress.rgw.1`
|
||||
Then Grafana panel `Total requests / responses` with legend `Requests` shows:
|
||||
| metrics | values |
|
||||
| {instance="ingress.rgw.1"} | 3 |
|
||||
|
||||
Scenario: "Test Total backend response errors by instance"
|
||||
Given the following series:
|
||||
| metrics | values |
|
||||
| haproxy_backend_response_errors_total{proxy="backend",instance="ingress.rgw.1"} | 10 100 |
|
||||
| haproxy_backend_response_errors_total{proxy="backend",instance="ingress.rgw.1"} | 20 200 |
|
||||
When variable `ingress_service` is `ingress.rgw.1`
|
||||
Then Grafana panel `Total requests / responses` with legend `Response errors` shows:
|
||||
| metrics | values |
|
||||
| {instance="ingress.rgw.1"} | 3 |
|
||||
|
||||
Scenario: "Test Total frontend requests errors by instance"
|
||||
Given the following series:
|
||||
| metrics | values |
|
||||
| haproxy_frontend_request_errors_total{proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
|
||||
| haproxy_frontend_request_errors_total{proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
|
||||
When variable `ingress_service` is `ingress.rgw.1`
|
||||
Then Grafana panel `Total requests / responses` with legend `Requests errors` shows:
|
||||
| metrics | values |
|
||||
| {instance="ingress.rgw.1"} | 3 |
|
||||
|
||||
Scenario: "Test Total backend redispatch warnings by instance"
|
||||
Given the following series:
|
||||
| metrics | values |
|
||||
| haproxy_backend_redispatch_warnings_total{proxy="backend",instance="ingress.rgw.1"} | 10 100 |
|
||||
| haproxy_backend_redispatch_warnings_total{proxy="backend",instance="ingress.rgw.1"} | 20 200 |
|
||||
When variable `ingress_service` is `ingress.rgw.1`
|
||||
Then Grafana panel `Total requests / responses` with legend `Backend redispatch` shows:
|
||||
| metrics | values |
|
||||
| {instance="ingress.rgw.1"} | 3 |
|
||||
|
||||
Scenario: "Test Total backend retry warnings by instance"
|
||||
Given the following series:
|
||||
| metrics | values |
|
||||
| haproxy_backend_retry_warnings_total{proxy="backend",instance="ingress.rgw.1"} | 10 100 |
|
||||
| haproxy_backend_retry_warnings_total{proxy="backend",instance="ingress.rgw.1"} | 20 200 |
|
||||
When variable `ingress_service` is `ingress.rgw.1`
|
||||
Then Grafana panel `Total requests / responses` with legend `Backend retry` shows:
|
||||
| metrics | values |
|
||||
| {instance="ingress.rgw.1"} | 3 |
|
||||
|
||||
Scenario: "Test Total frontend requests denied by instance"
|
||||
Given the following series:
|
||||
| metrics | values |
|
||||
| haproxy_frontend_requests_denied_total{proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
|
||||
| haproxy_frontend_requests_denied_total{proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
|
||||
When variable `ingress_service` is `ingress.rgw.1`
|
||||
Then Grafana panel `Total requests / responses` with legend `Request denied` shows:
|
||||
| metrics | values |
|
||||
| {instance="ingress.rgw.1"} | 3 |
|
||||
|
||||
Scenario: "Test Total backend current queue by instance"
|
||||
Given the following series:
|
||||
| metrics | values |
|
||||
| haproxy_backend_current_queue{proxy="backend",instance="ingress.rgw.1"} | 10 100 |
|
||||
| haproxy_backend_current_queue{proxy="backend",instance="ingress.rgw.1"} | 20 200 |
|
||||
When variable `ingress_service` is `ingress.rgw.1`
|
||||
Then Grafana panel `Total requests / responses` with legend `Backend Queued` shows:
|
||||
| metrics | values |
|
||||
| {instance="ingress.rgw.1"} | 200 |
|
||||
|
||||
Scenario: "Test Total frontend connections by instance"
|
||||
Given the following series:
|
||||
| metrics | values |
|
||||
| haproxy_frontend_connections_total{proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
|
||||
| haproxy_frontend_connections_total{proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
|
||||
When variable `ingress_service` is `ingress.rgw.1`
|
||||
Then Grafana panel `Total number of connections` with legend `Front` shows:
|
||||
| metrics | values |
|
||||
| {instance="ingress.rgw.1"} | 3 |
|
||||
|
||||
Scenario: "Test Total backend connections attempts by instance"
|
||||
Given the following series:
|
||||
| metrics | values |
|
||||
| haproxy_backend_connection_attempts_total{proxy="backend",instance="ingress.rgw.1"} | 10 100 |
|
||||
| haproxy_backend_connection_attempts_total{proxy="backend",instance="ingress.rgw.1"} | 20 200 |
|
||||
When variable `ingress_service` is `ingress.rgw.1`
|
||||
Then Grafana panel `Total number of connections` with legend `Back` shows:
|
||||
| metrics | values |
|
||||
| {instance="ingress.rgw.1"} | 3 |
|
||||
|
||||
Scenario: "Test Total backend connections error by instance"
|
||||
Given the following series:
|
||||
| metrics | values |
|
||||
| haproxy_backend_connection_errors_total{proxy="backend",instance="ingress.rgw.1"} | 10 100 |
|
||||
| haproxy_backend_connection_errors_total{proxy="backend",instance="ingress.rgw.1"} | 20 200 |
|
||||
When variable `ingress_service` is `ingress.rgw.1`
|
||||
Then Grafana panel `Total number of connections` with legend `Back errors` shows:
|
||||
| metrics | values |
|
||||
| {instance="ingress.rgw.1"} | 3 |
|
||||
|
||||
Scenario: "Test Total frontend bytes incoming by instance"
|
||||
Given the following series:
|
||||
| metrics | values |
|
||||
| haproxy_frontend_bytes_in_total{proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
|
||||
| haproxy_frontend_bytes_in_total{proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
|
||||
When variable `ingress_service` is `ingress.rgw.1`
|
||||
Then Grafana panel `Current total of incoming / outgoing bytes` with legend `IN Front` shows:
|
||||
| metrics | values |
|
||||
| {instance="ingress.rgw.1"} | 24 |
|
||||
|
||||
Scenario: "Test Total frontend bytes outgoing by instance"
|
||||
Given the following series:
|
||||
| metrics | values |
|
||||
| haproxy_frontend_bytes_out_total{proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
|
||||
| haproxy_frontend_bytes_out_total{proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
|
||||
When variable `ingress_service` is `ingress.rgw.1`
|
||||
Then Grafana panel `Current total of incoming / outgoing bytes` with legend `OUT Front` shows:
|
||||
| metrics | values |
|
||||
| {instance="ingress.rgw.1"} | 24 |
|
||||
|
||||
Scenario: "Test Total backend bytes incoming by instance"
|
||||
Given the following series:
|
||||
| metrics | values |
|
||||
| haproxy_backend_bytes_in_total{proxy="backend",instance="ingress.rgw.1"} | 10 100 |
|
||||
| haproxy_backend_bytes_in_total{proxy="backend",instance="ingress.rgw.1"} | 20 200 |
|
||||
When variable `ingress_service` is `ingress.rgw.1`
|
||||
Then Grafana panel `Current total of incoming / outgoing bytes` with legend `IN Back` shows:
|
||||
| metrics | values |
|
||||
| {instance="ingress.rgw.1"} | 24 |
|
||||
|
||||
Scenario: "Test Total backend bytes outgoing by instance"
|
||||
Given the following series:
|
||||
| metrics | values |
|
||||
| haproxy_backend_bytes_out_total{proxy="backend",instance="ingress.rgw.1"} | 10 100 |
|
||||
| haproxy_backend_bytes_out_total{proxy="backend",instance="ingress.rgw.1"} | 20 200 |
|
||||
When variable `ingress_service` is `ingress.rgw.1`
|
||||
Then Grafana panel `Current total of incoming / outgoing bytes` with legend `OUT Back` shows:
|
||||
| metrics | values |
|
||||
| {instance="ingress.rgw.1"} | 24 |
|
||||
Loading…
Reference in New Issue
Block a user
