From 44a51bbbefb1acd8a42134125e2e1e778a68a937 Mon Sep 17 00:00:00 2001 From: hardikl Date: Thu, 18 May 2023 13:18:20 +0530 Subject: [PATCH 1/6] feat: collection of other counters for fcvi perf object --- cmd/collectors/restperf/plugins/fcvi/fcvi.go | 71 +++++++++++++++++ cmd/collectors/restperf/restperf.go | 3 + cmd/collectors/zapiperf/plugins/fcvi/fcvi.go | 81 ++++++++++++++++++++ cmd/collectors/zapiperf/zapiperf.go | 3 + conf/restperf/9.12.0/fcvi.yaml | 28 +++++-- conf/zapiperf/cdot/9.8.0/fcvi.yaml | 12 +++ 6 files changed, 191 insertions(+), 7 deletions(-) create mode 100644 cmd/collectors/restperf/plugins/fcvi/fcvi.go create mode 100644 cmd/collectors/zapiperf/plugins/fcvi/fcvi.go diff --git a/cmd/collectors/restperf/plugins/fcvi/fcvi.go b/cmd/collectors/restperf/plugins/fcvi/fcvi.go new file mode 100644 index 000000000..5274d211c --- /dev/null +++ b/cmd/collectors/restperf/plugins/fcvi/fcvi.go @@ -0,0 +1,71 @@ +package fcvi + +import ( + "github.com/netapp/harvest/v2/cmd/poller/plugin" + "github.com/netapp/harvest/v2/cmd/tools/rest" + "github.com/netapp/harvest/v2/pkg/conf" + "github.com/netapp/harvest/v2/pkg/matrix" + "strings" + "time" +) + +type FCVI struct { + *plugin.AbstractPlugin + client *rest.Client +} + +func New(p *plugin.AbstractPlugin) plugin.Plugin { + return &FCVI{AbstractPlugin: p} +} + +func (f *FCVI) Init() error { + var err error + if err = f.InitAbc(); err != nil { + return err + } + + timeout, _ := time.ParseDuration(rest.DefaultTimeout) + if f.client, err = rest.New(conf.ZapiPoller(f.ParentParams), timeout, f.Auth); err != nil { + f.Logger.Error().Stack().Err(err).Msg("connecting") + return err + } + + if err = f.client.Init(5); err != nil { + return err + } + return nil +} + +func (f *FCVI) Run(dataMap map[string]*matrix.Matrix) ([]*matrix.Matrix, error) { + data := dataMap[f.Object] + query := "api/private/cli/metrocluster/interconnect/adapter" + fields := []string{"node", "adapter", "port_name"} + href := rest.BuildHref("", strings.Join(fields, ","), nil, "", "", "", "", query) + + records, err := rest.Fetch(f.client, href) + if err != nil { + f.Logger.Error().Err(err).Str("href", href).Msg("Failed to fetch data") + return nil, err + } + + if len(records) == 0 { + return nil, nil + } + + for _, adapterData := range records { + if !adapterData.IsObject() { + f.Logger.Warn().Str("type", adapterData.Type.String()).Msg("adapter is not object, skipping") + continue + } + node := adapterData.Get("node").String() + adapter := adapterData.Get("adapter").String() + port := adapterData.Get("port_name").String() + + // Fetch instance and add port label + if instance := data.GetInstance(node + ":" + adapter); instance != nil { + instance.SetLabel("port", port) + } + } + + return nil, nil +} diff --git a/cmd/collectors/restperf/restperf.go b/cmd/collectors/restperf/restperf.go index 1afa43806..d071872d7 100644 --- a/cmd/collectors/restperf/restperf.go +++ b/cmd/collectors/restperf/restperf.go @@ -6,6 +6,7 @@ import ( "github.com/netapp/harvest/v2/cmd/collectors/restperf/plugins/disk" "github.com/netapp/harvest/v2/cmd/collectors/restperf/plugins/fabricpool" "github.com/netapp/harvest/v2/cmd/collectors/restperf/plugins/fcp" + "github.com/netapp/harvest/v2/cmd/collectors/restperf/plugins/fcvi" "github.com/netapp/harvest/v2/cmd/collectors/restperf/plugins/headroom" "github.com/netapp/harvest/v2/cmd/collectors/restperf/plugins/nic" "github.com/netapp/harvest/v2/cmd/collectors/restperf/plugins/volume" @@ -1231,6 +1232,8 @@ func (r *RestPerf) LoadPlugin(kind string, p *plugin.AbstractPlugin) plugin.Plug return vscan.New(p) case "FabricPool": return fabricpool.New(p) + case "FCVI": + return fcvi.New(p) default: r.Logger.Info().Str("kind", kind).Msg("no Restperf plugin found") } diff --git a/cmd/collectors/zapiperf/plugins/fcvi/fcvi.go b/cmd/collectors/zapiperf/plugins/fcvi/fcvi.go new file mode 100644 index 000000000..1b7e74f3f --- /dev/null +++ b/cmd/collectors/zapiperf/plugins/fcvi/fcvi.go @@ -0,0 +1,81 @@ +package fcvi + +import ( + "github.com/netapp/harvest/v2/cmd/poller/plugin" + "github.com/netapp/harvest/v2/pkg/api/ontapi/zapi" + "github.com/netapp/harvest/v2/pkg/conf" + "github.com/netapp/harvest/v2/pkg/errs" + "github.com/netapp/harvest/v2/pkg/matrix" + "github.com/netapp/harvest/v2/pkg/tree/node" +) + +const batchSize = "500" + +type FCVI struct { + *plugin.AbstractPlugin + client *zapi.Client +} + +func New(p *plugin.AbstractPlugin) plugin.Plugin { + return &FCVI{AbstractPlugin: p} +} + +func (f *FCVI) Init() error { + var err error + if err = f.InitAbc(); err != nil { + return err + } + + if f.client, err = zapi.New(conf.ZapiPoller(f.ParentParams), f.Auth); err != nil { + f.Logger.Error().Stack().Err(err).Msg("connecting") + return err + } + if err = f.client.Init(5); err != nil { + return err + } + return nil +} + +func (f *FCVI) Run(dataMap map[string]*matrix.Matrix) ([]*matrix.Matrix, error) { + var ( + result []*node.Node + err error + ) + + adapterPortMap := make(map[string]string) + data := dataMap[f.Object] + query := "metrocluster-interconnect-adapter-get-iter" + request := node.NewXMLS(query) + request.NewChildS("max-records", batchSize) + desired := node.NewXMLS("desired-attributes") + metroclusterInterconnectAdapterAttributes := node.NewXMLS("metrocluster-interconnect-adapter") + metroclusterInterconnectAdapterAttributes.NewChildS("adapter-name", "") + metroclusterInterconnectAdapterAttributes.NewChildS("node-name", "") + metroclusterInterconnectAdapterAttributes.NewChildS("port-name", "") + desired.AddChild(metroclusterInterconnectAdapterAttributes) + request.AddChild(desired) + + if result, err = f.client.InvokeZapiCall(request); err != nil { + return nil, err + } + + if len(result) == 0 || result == nil { + return nil, errs.New(errs.ErrNoInstance, "no records found") + } + f.Logger.Info().Msgf("%d", len(result)) + + for _, adapterData := range result { + adapter := adapterData.GetChildContentS("adapter-name") + node := adapterData.GetChildContentS("node-name") + port := adapterData.GetChildContentS("port-name") + adapterPortMap[node+adapter] = port + } + + // we would not use getInstance() as key would be `sti8300mcc-215:kernel:fcvi_device_1` + for _, instance := range data.GetInstances() { + if port, ok := adapterPortMap[instance.GetLabel("node")+instance.GetLabel("fcvi")]; ok { + instance.SetLabel("port", port) + } + } + return nil, nil +} diff --git a/cmd/collectors/zapiperf/zapiperf.go b/cmd/collectors/zapiperf/zapiperf.go index 58f47869a..8e3734f9a 100644 --- a/cmd/collectors/zapiperf/zapiperf.go +++ b/cmd/collectors/zapiperf/zapiperf.go @@ -29,6 +29,7 @@ import ( "github.com/netapp/harvest/v2/cmd/collectors/zapiperf/plugins/disk" "github.com/netapp/harvest/v2/cmd/collectors/zapiperf/plugins/externalserviceoperation" "github.com/netapp/harvest/v2/cmd/collectors/zapiperf/plugins/fcp" + "github.com/netapp/harvest/v2/cmd/collectors/zapiperf/plugins/fcvi" "github.com/netapp/harvest/v2/cmd/collectors/zapiperf/plugins/headroom" "github.com/netapp/harvest/v2/cmd/collectors/zapiperf/plugins/nic" "github.com/netapp/harvest/v2/cmd/collectors/zapiperf/plugins/volume" @@ -128,6 +129,8 @@ func (z *ZapiPerf) LoadPlugin(kind string, abc *plugin.AbstractPlugin) plugin.Pl return disk.New(abc) case "ExternalServiceOperation": return externalserviceoperation.New(abc) + case "FCVI": + return fcvi.New(abc) default: z.Logger.Info().Msgf("no zapiPerf plugin found for %s", kind) } diff --git a/conf/restperf/9.12.0/fcvi.yaml b/conf/restperf/9.12.0/fcvi.yaml index 9725c3131..63f535840 100644 --- a/conf/restperf/9.12.0/fcvi.yaml +++ b/conf/restperf/9.12.0/fcvi.yaml @@ -3,14 +3,28 @@ query: api/cluster/counter/tables/fcvi object: fcvi counters: - - ^^id - - ^name => fcvi - - ^node.name => node - - rdma.write_average_latency => rdma_write_avg_latency - - rdma.write_ops => rdma_write_ops - - rdma.write_throughput => rdma_write_throughput + - ^^id => fcvi + - ^node.name => node + - firmware.invalid_crc_count => fw_invalid_crc + - firmware.invalid_transmit_word_count => fw_invalid_xmit_words + - firmware.link_failure_count => fw_link_failure + - firmware.loss_of_signal_count => fw_loss_of_signal + - firmware.loss_of_sync_count => fw_loss_of_sync + - firmware.systat.discard_frames => fw_SyStatDiscardFrames + - hard_reset_count => hard_reset_cnt + - rdma.write_average_latency => rdma_write_avg_latency + - rdma.write_ops => rdma_write_ops + - rdma.write_throughput => rdma_write_throughput + - soft_reset_count => soft_reset_cnt + +plugins: + - LabelAgent: + split: + - fcvi `:` ,fcvi + - FCVI export_options: instance_keys: - fcvi - - node \ No newline at end of file + - node + - port \ No newline at end of file diff --git a/conf/zapiperf/cdot/9.8.0/fcvi.yaml b/conf/zapiperf/cdot/9.8.0/fcvi.yaml index 7488f83d5..40b6b3e62 100644 --- a/conf/zapiperf/cdot/9.8.0/fcvi.yaml +++ b/conf/zapiperf/cdot/9.8.0/fcvi.yaml @@ -6,14 +6,26 @@ object: fcvi instance_key: uuid counters: + - fw_SyStatDiscardFrames + - fw_invalid_crc + - fw_invalid_xmit_words + - fw_link_failure + - fw_loss_of_signal + - fw_loss_of_sync + - hard_reset_cnt - instance_name => fcvi - instance_uuid - node_name => node - rdma_write_avg_latency - rdma_write_ops - rdma_write_throughput + - soft_reset_cnt + +plugins: + - FCVI export_options: instance_keys: - fcvi - node + - port From fd102c9550b88fc534922f434618af80946a73d6 Mon Sep 17 00:00:00 2001 From: hardikl Date: Fri, 19 May 2023 16:53:40 +0530 Subject: [PATCH 2/6] feat: panels for iwarp and fcvi new counters --- conf/zapiperf/cdot/9.8.0/iwarp.yaml | 1 - grafana/dashboards/cmode/mcc_cluster.json | 1433 ++++++++++++++++----- 2 files changed, 1138 insertions(+), 296 deletions(-) diff --git a/conf/zapiperf/cdot/9.8.0/iwarp.yaml b/conf/zapiperf/cdot/9.8.0/iwarp.yaml index 1f07ab9fb..5028d9f1b 100644 --- a/conf/zapiperf/cdot/9.8.0/iwarp.yaml +++ b/conf/zapiperf/cdot/9.8.0/iwarp.yaml @@ -13,7 +13,6 @@ counters: - iw_read_ops => read_ops - iw_write_ops => write_ops - node_name => node - - rdma_write_throughput export_options: instance_keys: diff --git a/grafana/dashboards/cmode/mcc_cluster.json b/grafana/dashboards/cmode/mcc_cluster.json index cfd848fa3..60ef3c978 100644 --- a/grafana/dashboards/cmode/mcc_cluster.json +++ b/grafana/dashboards/cmode/mcc_cluster.json @@ -574,295 +574,1046 @@ "type": "gauge" }, { - "datasource": "${DS_PROMETHEUS}", - "fieldConfig": { - "defaults": { - "color": { - "mode": "palette-classic" - }, - "custom": { - "axisLabel": "", - "axisPlacement": "auto", - "barAlignment": 0, - "drawStyle": "line", - "fillOpacity": 10, - "gradientMode": "none", - "hideFrom": { - "legend": false, - "tooltip": false, - "viz": false + "collapsed": true, + "datasource": "Prometheus", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 5 + }, + "id": 90, + "panels": [ + { + "datasource": "Prometheus", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "smooth", + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "µs" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 8, + "x": 0, + "y": 6 + }, + "id": 62, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom" + }, + "tooltip": { + "mode": "single" + } + }, + "pluginVersion": "8.1.8", + "targets": [ + { + "exemplar": false, + "expr": "avg by (node)(fcvi_rdma_write_avg_latency{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "interval": "", + "legendFormat": "{{node}}", + "refId": "A", + "textEditor": false + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Write Latency", + "type": "timeseries" + }, + { + "datasource": "Prometheus", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisLabel": "MB/s", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "smooth", + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "Bps" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 8, + "x": 8, + "y": 6 + }, + "id": 63, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom" + }, + "tooltip": { + "mode": "single" + } + }, + "pluginVersion": "8.1.8", + "targets": [ + { + "exemplar": false, + "expr": "avg by (node)(fcvi_rdma_write_throughput{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "interval": "", + "legendFormat": "{{node}}", + "refId": "B", + "textEditor": false + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Write Throughput", + "type": "timeseries" + }, + { + "datasource": "Prometheus", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "smooth", + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "iops" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 8, + "x": 16, + "y": 6 + }, + "id": 64, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom" + }, + "tooltip": { + "mode": "single" + } + }, + "pluginVersion": "8.1.8", + "targets": [ + { + "exemplar": false, + "expr": "avg by (node)(fcvi_rdma_write_ops{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "interval": "", + "legendFormat": "{{node}}", + "refId": "A", + "textEditor": false + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Write IOPs", + "type": "timeseries" + }, + { + "datasource": "Prometheus", + "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": "smooth", + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "locale" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 8, + "x": 0, + "y": 14 + }, + "id": 111, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom" + }, + "tooltip": { + "mode": "single" + } + }, + "pluginVersion": "8.1.8", + "targets": [ + { + "exemplar": false, + "expr": "avg by (node)(fcvi_hard_reset_cnt{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "interval": "", + "legendFormat": "{{node}}", + "refId": "A", + "textEditor": false + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Hard Reset Count", + "type": "timeseries" + }, + { + "datasource": "Prometheus", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "smooth", + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 8, + "x": 8, + "y": 14 + }, + "id": 112, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom" + }, + "tooltip": { + "mode": "single" + } + }, + "pluginVersion": "8.1.8", + "targets": [ + { + "exemplar": false, + "expr": "avg by (node)(fcvi_soft_reset_cnt{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "interval": "", + "legendFormat": "{{node}}", + "refId": "A", + "textEditor": false + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Soft Reset Count", + "type": "timeseries" + }, + { + "datasource": "Prometheus", + "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": "smooth", + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 8, + "x": 16, + "y": 14 + }, + "id": 114, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom" + }, + "tooltip": { + "mode": "single" + } + }, + "pluginVersion": "8.1.8", + "targets": [ + { + "exemplar": false, + "expr": "avg by (node)(fcvi_fw_link_failure{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "interval": "", + "legendFormat": "{{node}}", + "refId": "A", + "textEditor": false + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Link Failure Count", + "type": "timeseries" + }, + { + "datasource": "Prometheus", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "smooth", + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 8, + "x": 0, + "y": 22 + }, + "id": 110, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom" }, - "lineInterpolation": "smooth", - "lineWidth": 1, - "pointSize": 5, - "scaleDistribution": { - "type": "linear" + "tooltip": { + "mode": "single" + } + }, + "pluginVersion": "8.1.8", + "targets": [ + { + "exemplar": false, + "expr": "avg by (node)(fcvi_fw_loss_of_signal{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "interval": "", + "legendFormat": "{{node}}", + "refId": "A", + "textEditor": false + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Loss of Signal Count", + "type": "timeseries" + }, + { + "datasource": "Prometheus", + "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": "smooth", + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" }, - "showPoints": "never", - "spanNulls": true, - "stacking": { - "group": "A", - "mode": "none" + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 8, + "x": 8, + "y": 22 + }, + "id": 117, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom" }, - "thresholdsStyle": { - "mode": "off" + "tooltip": { + "mode": "single" } }, - "mappings": [], - "min": 0, - "thresholds": { - "mode": "absolute", - "steps": [ - { - "color": "green", - "value": null - }, - { - "color": "red", - "value": 80 - } - ] - }, - "unit": "µs" - }, - "overrides": [] - }, - "gridPos": { - "h": 8, - "w": 8, - "x": 0, - "y": 5 - }, - "id": 81, - "links": [], - "options": { - "legend": { - "calcs": [ - "mean", - "lastNotNull", - "max" + "pluginVersion": "8.1.8", + "targets": [ + { + "exemplar": false, + "expr": "avg by (node)(fcvi_fw_loss_of_sync{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "interval": "", + "legendFormat": "{{node}}", + "refId": "A", + "textEditor": false + } ], - "displayMode": "table", - "placement": "bottom" + "timeFrom": null, + "timeShift": null, + "title": "Loss of Sync Count", + "type": "timeseries" }, - "tooltip": { - "mode": "single" - } - }, - "pluginVersion": "8.1.8", - "targets": [ { - "exemplar": false, - "expr": "avg by(node) (fcvi_rdma_write_avg_latency{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", - "interval": "", - "legendFormat": "{{node}}", - "refId": "A", - "textEditor": false - } - ], - "timeFrom": null, - "timeShift": null, - "title": "FCVI Average Latency", - "type": "timeseries" - }, - { - "datasource": "${DS_PROMETHEUS}", - "fieldConfig": { - "defaults": { - "color": { - "mode": "palette-classic" - }, - "custom": { - "axisLabel": "MB/s", - "axisPlacement": "auto", - "barAlignment": 0, - "drawStyle": "line", - "fillOpacity": 10, - "gradientMode": "none", - "hideFrom": { - "legend": false, - "tooltip": false, - "viz": false - }, - "lineInterpolation": "smooth", - "lineWidth": 2, - "pointSize": 5, - "scaleDistribution": { - "type": "linear" + "datasource": "Prometheus", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "smooth", + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" }, - "showPoints": "never", - "spanNulls": true, - "stacking": { - "group": "A", - "mode": "none" + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 8, + "x": 16, + "y": 22 + }, + "id": 115, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom" }, - "thresholdsStyle": { - "mode": "off" + "tooltip": { + "mode": "single" } }, - "mappings": [], - "min": 0, - "thresholds": { - "mode": "absolute", - "steps": [ - { - "color": "green", - "value": null + "pluginVersion": "8.1.8", + "targets": [ + { + "exemplar": false, + "expr": "avg by (node)(fcvi_fw_SyStatDiscardFrames{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "interval": "", + "legendFormat": "{{node}}", + "refId": "A", + "textEditor": false + } + ], + "timeFrom": null, + "timeShift": null, + "title": "SyStatDiscardFrames value", + "type": "timeseries" + }, + { + "datasource": "Prometheus", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" }, - { - "color": "red", - "value": 80 - } - ] + "custom": { + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "smooth", + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] }, - "unit": "Bps" - }, - "overrides": [] - }, - "gridPos": { - "h": 8, - "w": 8, - "x": 8, - "y": 5 - }, - "id": 77, - "links": [], - "options": { - "legend": { - "calcs": [ - "mean", - "lastNotNull", - "max" + "gridPos": { + "h": 8, + "w": 8, + "x": 0, + "y": 30 + }, + "id": 116, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom" + }, + "tooltip": { + "mode": "single" + } + }, + "pluginVersion": "8.1.8", + "targets": [ + { + "exemplar": false, + "expr": "avg by (node)(fcvi_fw_invalid_crc{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "interval": "", + "legendFormat": "{{node}}", + "refId": "A", + "textEditor": false + } ], - "displayMode": "table", - "placement": "bottom" + "timeFrom": null, + "timeShift": null, + "title": "Invalid CRC Count", + "type": "timeseries" }, - "tooltip": { - "mode": "single" - } - }, - "pluginVersion": "8.1.8", - "targets": [ { - "exemplar": false, - "expr": "avg by (node) (fcvi_rdma_write_throughput{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", - "hide": false, - "interval": "", - "legendFormat": "{{node}}", - "refId": "B", - "textEditor": false - } - ], - "timeFrom": null, - "timeShift": null, - "title": "FCVI Throughput", - "type": "timeseries" - }, - { - "datasource": "${DS_PROMETHEUS}", - "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": "smooth", - "lineWidth": 2, - "pointSize": 5, - "scaleDistribution": { - "type": "linear" + "datasource": "Prometheus", + "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": "smooth", + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" }, - "showPoints": "never", - "spanNulls": true, - "stacking": { - "group": "A", - "mode": "none" + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 8, + "x": 8, + "y": 30 + }, + "id": 113, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom" }, - "thresholdsStyle": { - "mode": "off" + "tooltip": { + "mode": "single" } }, - "mappings": [], - "min": 0, - "thresholds": { - "mode": "absolute", - "steps": [ - { - "color": "green", - "value": null - }, - { - "color": "red", - "value": 80 - } - ] - }, - "unit": "iops" - }, - "overrides": [] - }, - "gridPos": { - "h": 8, - "w": 8, - "x": 16, - "y": 5 - }, - "id": 79, - "links": [], - "options": { - "legend": { - "calcs": [ - "mean", - "lastNotNull", - "max" + "pluginVersion": "8.1.8", + "targets": [ + { + "exemplar": false, + "expr": "avg by (node)(fcvi_fw_invalid_xmit_words{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "interval": "", + "legendFormat": "{{node}}", + "refId": "A", + "textEditor": false + } ], - "displayMode": "table", - "placement": "bottom" - }, - "tooltip": { - "mode": "single" - } - }, - "pluginVersion": "8.1.8", - "targets": [ - { - "exemplar": false, - "expr": "avg by(node) (fcvi_rdma_write_ops{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", - "interval": "", - "legendFormat": "{{node}}", - "refId": "A", - "textEditor": false + "timeFrom": null, + "timeShift": null, + "title": "Invalid Transmit Word Count", + "type": "timeseries" } ], - "timeFrom": null, - "timeShift": null, - "title": "FCVI IOPs", - "type": "timeseries" + "repeat": null, + "title": "MetroCluster FCVI Drilldown", + "type": "row" }, { "collapsed": true, - "datasource": "${DS_PROMETHEUS}", + "datasource": "Prometheus", "gridPos": { "h": 1, "w": 24, "x": 0, - "y": 13 + "y": 38 }, - "id": 90, + "id": 107, "panels": [ { - "datasource": "${DS_PROMETHEUS}", + "datasource": "Prometheus", "fieldConfig": { "defaults": { "color": { @@ -911,7 +1662,7 @@ } ] }, - "unit": "µs" + "unit": "iops" }, "overrides": [] }, @@ -919,9 +1670,9 @@ "h": 8, "w": 8, "x": 0, - "y": 14 + "y": 39 }, - "id": 62, + "id": 104, "links": [], "options": { "legend": { @@ -941,27 +1692,27 @@ "targets": [ { "exemplar": false, - "expr": "avg (fcvi_rdma_write_avg_latency{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "expr": "avg by (node)(iw_ops{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", "interval": "", - "legendFormat": "Write", - "refId": "A", + "legendFormat": "{{node}}", + "refId": "B", "textEditor": false } ], "timeFrom": null, "timeShift": null, - "title": "FCVI Latency", + "title": "IOPs", "type": "timeseries" }, { - "datasource": "${DS_PROMETHEUS}", + "datasource": null, "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { - "axisLabel": "MB/s", + "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "drawStyle": "line", @@ -1003,7 +1754,7 @@ } ] }, - "unit": "Bps" + "unit": "iops" }, "overrides": [] }, @@ -1011,9 +1762,9 @@ "h": 8, "w": 8, "x": 8, - "y": 14 + "y": 39 }, - "id": 63, + "id": 108, "links": [], "options": { "legend": { @@ -1033,20 +1784,20 @@ "targets": [ { "exemplar": false, - "expr": "avg(fcvi_rdma_write_throughput{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "expr": "avg by (node)(iw_read_ops{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", "interval": "", - "legendFormat": "Write", - "refId": "B", + "legendFormat": "{{node}}", + "refId": "A", "textEditor": false } ], "timeFrom": null, "timeShift": null, - "title": "FCVI Throughput", + "title": "Read IOPs", "type": "timeseries" }, { - "datasource": "${DS_PROMETHEUS}", + "datasource": null, "fieldConfig": { "defaults": { "color": { @@ -1103,9 +1854,101 @@ "h": 8, "w": 8, "x": 16, - "y": 14 + "y": 39 }, - "id": 64, + "id": 109, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom" + }, + "tooltip": { + "mode": "single" + } + }, + "pluginVersion": "8.1.8", + "targets": [ + { + "exemplar": false, + "expr": "avg by (node)(iw_write_ops{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "interval": "", + "legendFormat": "{{node}}", + "refId": "A", + "textEditor": false + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Write IOPs", + "type": "timeseries" + }, + { + "datasource": null, + "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": "smooth", + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "µs" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 8, + "x": 0, + "y": 47 + }, + "id": 103, "links": [], "options": { "legend": { @@ -1125,21 +1968,21 @@ "targets": [ { "exemplar": false, - "expr": "avg(fcvi_rdma_write_ops{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "expr": "avg by (node)(iw_avg_latency{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", "interval": "", - "legendFormat": "Write", + "legendFormat": "{{node}}", "refId": "A", "textEditor": false } ], "timeFrom": null, "timeShift": null, - "title": "FCVI Write IOPs", + "title": "Average Latency", "type": "timeseries" } ], "repeat": null, - "title": "MetroCluster FCVI Drilldown", + "title": "MetroCluster Iwarp Drilldown", "type": "row" }, { @@ -1149,7 +1992,7 @@ "h": 1, "w": 24, "x": 0, - "y": 14 + "y": 55 }, "id": 91, "panels": [ @@ -1216,7 +2059,7 @@ "h": 8, "w": 12, "x": 0, - "y": 15 + "y": 56 }, "id": 17, "links": [], @@ -1321,7 +2164,7 @@ "h": 8, "w": 12, "x": 12, - "y": 15 + "y": 56 }, "id": 95, "options": { @@ -1422,7 +2265,7 @@ "h": 8, "w": 12, "x": 0, - "y": 23 + "y": 64 }, "id": 73, "links": [], @@ -1517,7 +2360,7 @@ "h": 8, "w": 12, "x": 12, - "y": 23 + "y": 64 }, "id": 74, "links": [], @@ -1609,7 +2452,7 @@ "h": 8, "w": 12, "x": 0, - "y": 31 + "y": 72 }, "id": 71, "links": [], @@ -1699,7 +2542,7 @@ "h": 8, "w": 12, "x": 12, - "y": 31 + "y": 72 }, "id": 69, "links": [], @@ -1746,7 +2589,7 @@ "h": 1, "w": 24, "x": 0, - "y": 15 + "y": 80 }, "id": 92, "panels": [ @@ -1808,7 +2651,7 @@ "h": 8, "w": 12, "x": 0, - "y": 16 + "y": 81 }, "id": 75, "links": [], @@ -1901,7 +2744,7 @@ "h": 8, "w": 12, "x": 12, - "y": 16 + "y": 81 }, "id": 76, "links": [], @@ -1948,7 +2791,7 @@ "h": 1, "w": 24, "x": 0, - "y": 16 + "y": 89 }, "id": 93, "panels": [ @@ -2010,7 +2853,7 @@ "h": 8, "w": 8, "x": 0, - "y": 17 + "y": 90 }, "id": 86, "links": [], @@ -2102,7 +2945,7 @@ "h": 8, "w": 8, "x": 8, - "y": 17 + "y": 90 }, "id": 100, "links": [], @@ -2194,7 +3037,7 @@ "h": 8, "w": 8, "x": 16, - "y": 17 + "y": 90 }, "id": 97, "links": [], @@ -2286,7 +3129,7 @@ "h": 8, "w": 8, "x": 0, - "y": 25 + "y": 98 }, "id": 98, "links": [], @@ -2378,7 +3221,7 @@ "h": 8, "w": 8, "x": 8, - "y": 25 + "y": 98 }, "id": 96, "links": [], @@ -2470,7 +3313,7 @@ "h": 8, "w": 8, "x": 16, - "y": 25 + "y": 98 }, "id": 99, "links": [], From af839f8866619a9428850e132bb00f1d47582116 Mon Sep 17 00:00:00 2001 From: hardikl Date: Mon, 22 May 2023 16:13:20 +0530 Subject: [PATCH 3/6] feat: added iw counters in exclude list --- integration/test/dashboard_json_test.go | 1 + 1 file changed, 1 insertion(+) diff --git a/integration/test/dashboard_json_test.go b/integration/test/dashboard_json_test.go index 9791ea3cb..e8e26d8a3 100644 --- a/integration/test/dashboard_json_test.go +++ b/integration/test/dashboard_json_test.go @@ -61,6 +61,7 @@ var excludeCounters = []string{ "flashcache_", "flashpool", "health_", + "iw", "logical_used", "metadata_exporter_count", "metadata_target_ping", From e752399e12b53c5034c192529143938af872d40a Mon Sep 17 00:00:00 2001 From: hardikl Date: Tue, 23 May 2023 14:58:43 +0530 Subject: [PATCH 4/6] feat: handle review comments --- conf/restperf/9.12.0/fcvi.yaml | 16 ++++++++-------- conf/zapiperf/cdot/9.8.0/fcvi.yaml | 16 ++++++++-------- grafana/dashboards/cmode/mcc_cluster.json | 16 ++++++++-------- 3 files changed, 24 insertions(+), 24 deletions(-) diff --git a/conf/restperf/9.12.0/fcvi.yaml b/conf/restperf/9.12.0/fcvi.yaml index 63f535840..00a21222a 100644 --- a/conf/restperf/9.12.0/fcvi.yaml +++ b/conf/restperf/9.12.0/fcvi.yaml @@ -5,17 +5,17 @@ object: fcvi counters: - ^^id => fcvi - ^node.name => node - - firmware.invalid_crc_count => fw_invalid_crc - - firmware.invalid_transmit_word_count => fw_invalid_xmit_words - - firmware.link_failure_count => fw_link_failure - - firmware.loss_of_signal_count => fw_loss_of_signal - - firmware.loss_of_sync_count => fw_loss_of_sync - - firmware.systat.discard_frames => fw_SyStatDiscardFrames - - hard_reset_count => hard_reset_cnt + - firmware.invalid_crc_count => firmware_invalid_crc_count + - firmware.invalid_transmit_word_count => firmware_invalid_transmit_word_count + - firmware.link_failure_count => firmware_link_failure_count + - firmware.loss_of_signal_count => firmware_loss_of_signal_count + - firmware.loss_of_sync_count => firmware_loss_of_sync_count + - firmware.systat.discard_frames => firmware_systat_discard_frames + - hard_reset_count => hard_reset_count - rdma.write_average_latency => rdma_write_avg_latency - rdma.write_ops => rdma_write_ops - rdma.write_throughput => rdma_write_throughput - - soft_reset_count => soft_reset_cnt + - soft_reset_count => soft_reset_count plugins: - LabelAgent: diff --git a/conf/zapiperf/cdot/9.8.0/fcvi.yaml b/conf/zapiperf/cdot/9.8.0/fcvi.yaml index 40b6b3e62..db9c97b19 100644 --- a/conf/zapiperf/cdot/9.8.0/fcvi.yaml +++ b/conf/zapiperf/cdot/9.8.0/fcvi.yaml @@ -6,20 +6,20 @@ object: fcvi instance_key: uuid counters: - - fw_SyStatDiscardFrames - - fw_invalid_crc - - fw_invalid_xmit_words - - fw_link_failure - - fw_loss_of_signal - - fw_loss_of_sync - - hard_reset_cnt + - fw_SyStatDiscardFrames => firmwares_systat_discard_frames + - fw_invalid_crc => firmware_invalid_crc_count + - fw_invalid_xmit_words => firmware_invalid_transmit_word_count + - fw_link_failure => firmware_link_failure_count + - fw_loss_of_signal => firmware_loss_of_signal_count + - fw_loss_of_sync => firmware_loss_of_sync_count + - hard_reset_cnt => hard_reset_count - instance_name => fcvi - instance_uuid - node_name => node - rdma_write_avg_latency - rdma_write_ops - rdma_write_throughput - - soft_reset_cnt + - soft_reset_cnt => soft_reset_count plugins: - FCVI diff --git a/grafana/dashboards/cmode/mcc_cluster.json b/grafana/dashboards/cmode/mcc_cluster.json index 60ef3c978..9ef410c38 100644 --- a/grafana/dashboards/cmode/mcc_cluster.json +++ b/grafana/dashboards/cmode/mcc_cluster.json @@ -940,7 +940,7 @@ "targets": [ { "exemplar": false, - "expr": "avg by (node)(fcvi_hard_reset_cnt{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "expr": "avg by (node)(fcvi_hard_reset_count{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", "interval": "", "legendFormat": "{{node}}", "refId": "A", @@ -1032,7 +1032,7 @@ "targets": [ { "exemplar": false, - "expr": "avg by (node)(fcvi_soft_reset_cnt{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "expr": "avg by (node)(fcvi_soft_reset_count{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", "interval": "", "legendFormat": "{{node}}", "refId": "A", @@ -1124,7 +1124,7 @@ "targets": [ { "exemplar": false, - "expr": "avg by (node)(fcvi_fw_link_failure{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "expr": "avg by (node)(fcvi_firmware_link_failure_count{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", "interval": "", "legendFormat": "{{node}}", "refId": "A", @@ -1216,7 +1216,7 @@ "targets": [ { "exemplar": false, - "expr": "avg by (node)(fcvi_fw_loss_of_signal{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "expr": "avg by (node)(fcvi_firmware_loss_of_signal_count{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", "interval": "", "legendFormat": "{{node}}", "refId": "A", @@ -1308,7 +1308,7 @@ "targets": [ { "exemplar": false, - "expr": "avg by (node)(fcvi_fw_loss_of_sync{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "expr": "avg by (node)(fcvi_firmware_loss_of_sync_count{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", "interval": "", "legendFormat": "{{node}}", "refId": "A", @@ -1400,7 +1400,7 @@ "targets": [ { "exemplar": false, - "expr": "avg by (node)(fcvi_fw_SyStatDiscardFrames{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "expr": "avg by (node)(fcvi_firmwares_systat_discard_frames{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", "interval": "", "legendFormat": "{{node}}", "refId": "A", @@ -1492,7 +1492,7 @@ "targets": [ { "exemplar": false, - "expr": "avg by (node)(fcvi_fw_invalid_crc{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "expr": "avg by (node)(fcvi_firmware_invalid_crc_count{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", "interval": "", "legendFormat": "{{node}}", "refId": "A", @@ -1584,7 +1584,7 @@ "targets": [ { "exemplar": false, - "expr": "avg by (node)(fcvi_fw_invalid_xmit_words{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "expr": "avg by (node)(fcvi_firmware_invalid_transmit_word_count{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", "interval": "", "legendFormat": "{{node}}", "refId": "A", From d9184e976f654bfa5373fc9a9e0ecfd165b8a8b3 Mon Sep 17 00:00:00 2001 From: hardikl Date: Tue, 23 May 2023 18:33:14 +0530 Subject: [PATCH 5/6] feat: added panel decription for new panels --- grafana/dashboards/cmode/mcc_cluster.json | 67 ++++++++++++++--------- 1 file changed, 41 insertions(+), 26 deletions(-) diff --git a/grafana/dashboards/cmode/mcc_cluster.json b/grafana/dashboards/cmode/mcc_cluster.json index 9ef410c38..d27a30a7b 100644 --- a/grafana/dashboards/cmode/mcc_cluster.json +++ b/grafana/dashboards/cmode/mcc_cluster.json @@ -575,7 +575,7 @@ }, { "collapsed": true, - "datasource": "Prometheus", + "datasource": "${DS_PROMETHEUS}", "gridPos": { "h": 1, "w": 24, @@ -585,7 +585,8 @@ "id": 90, "panels": [ { - "datasource": "Prometheus", + "datasource": "${DS_PROMETHEUS}", + "description": "Average RDMA write I/O latency per node", "fieldConfig": { "defaults": { "color": { @@ -677,7 +678,8 @@ "type": "timeseries" }, { - "datasource": "Prometheus", + "datasource": "${DS_PROMETHEUS}", + "description": "Average RDMA write throughput in bytes per second per node", "fieldConfig": { "defaults": { "color": { @@ -769,7 +771,8 @@ "type": "timeseries" }, { - "datasource": "Prometheus", + "datasource": "${DS_PROMETHEUS}", + "description": "Average Number of RDMA write I/Os issued per second per node", "fieldConfig": { "defaults": { "color": { @@ -861,7 +864,8 @@ "type": "timeseries" }, { - "datasource": "Prometheus", + "datasource": "${DS_PROMETHEUS}", + "description": "Total Number of times hard reset of FCVI adapter got issued per node", "fieldConfig": { "defaults": { "color": { @@ -940,7 +944,7 @@ "targets": [ { "exemplar": false, - "expr": "avg by (node)(fcvi_hard_reset_count{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "expr": "sum by (node)(fcvi_hard_reset_count{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", "interval": "", "legendFormat": "{{node}}", "refId": "A", @@ -953,7 +957,8 @@ "type": "timeseries" }, { - "datasource": "Prometheus", + "datasource": "${DS_PROMETHEUS}", + "description": "Total Number of times soft reset of FCVI adapter got issued per node", "fieldConfig": { "defaults": { "color": { @@ -1032,7 +1037,7 @@ "targets": [ { "exemplar": false, - "expr": "avg by (node)(fcvi_soft_reset_count{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "expr": "sum by (node)(fcvi_soft_reset_count{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", "interval": "", "legendFormat": "{{node}}", "refId": "A", @@ -1045,7 +1050,8 @@ "type": "timeseries" }, { - "datasource": "Prometheus", + "datasource": "${DS_PROMETHEUS}", + "description": "Total Number of times Firmware reported link failure count per node", "fieldConfig": { "defaults": { "color": { @@ -1124,7 +1130,7 @@ "targets": [ { "exemplar": false, - "expr": "avg by (node)(fcvi_firmware_link_failure_count{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "expr": "sum by (node)(fcvi_firmware_link_failure_count{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", "interval": "", "legendFormat": "{{node}}", "refId": "A", @@ -1137,7 +1143,8 @@ "type": "timeseries" }, { - "datasource": "Prometheus", + "datasource": "${DS_PROMETHEUS}", + "description": "Total Number of times Firmware reported loss of signal count per node", "fieldConfig": { "defaults": { "color": { @@ -1216,7 +1223,7 @@ "targets": [ { "exemplar": false, - "expr": "avg by (node)(fcvi_firmware_loss_of_signal_count{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "expr": "sum by (node)(fcvi_firmware_loss_of_signal_count{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", "interval": "", "legendFormat": "{{node}}", "refId": "A", @@ -1229,7 +1236,8 @@ "type": "timeseries" }, { - "datasource": "Prometheus", + "datasource": "${DS_PROMETHEUS}", + "description": "Total Number of times Firmware reported loss of sync count per node", "fieldConfig": { "defaults": { "color": { @@ -1308,7 +1316,7 @@ "targets": [ { "exemplar": false, - "expr": "avg by (node)(fcvi_firmware_loss_of_sync_count{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "expr": "sum by (node)(fcvi_firmware_loss_of_sync_count{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", "interval": "", "legendFormat": "{{node}}", "refId": "A", @@ -1321,7 +1329,8 @@ "type": "timeseries" }, { - "datasource": "Prometheus", + "datasource": "${DS_PROMETHEUS}", + "description": "Total Number of times Firmware reported SyStatDiscardFrames value per node", "fieldConfig": { "defaults": { "color": { @@ -1400,7 +1409,7 @@ "targets": [ { "exemplar": false, - "expr": "avg by (node)(fcvi_firmwares_systat_discard_frames{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "expr": "sum by (node)(fcvi_firmwares_systat_discard_frames{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", "interval": "", "legendFormat": "{{node}}", "refId": "A", @@ -1409,11 +1418,12 @@ ], "timeFrom": null, "timeShift": null, - "title": "SyStatDiscardFrames value", + "title": "SyStatDiscardFrames Value", "type": "timeseries" }, { - "datasource": "Prometheus", + "datasource": "${DS_PROMETHEUS}", + "description": "Total Number of times Firmware reported invalid crc count per node", "fieldConfig": { "defaults": { "color": { @@ -1492,7 +1502,7 @@ "targets": [ { "exemplar": false, - "expr": "avg by (node)(fcvi_firmware_invalid_crc_count{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "expr": "sum by (node)(fcvi_firmware_invalid_crc_count{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", "interval": "", "legendFormat": "{{node}}", "refId": "A", @@ -1505,7 +1515,8 @@ "type": "timeseries" }, { - "datasource": "Prometheus", + "datasource": "${DS_PROMETHEUS}", + "description": "Total Number of times Firmware reported invalid transmit word count per node", "fieldConfig": { "defaults": { "color": { @@ -1584,7 +1595,7 @@ "targets": [ { "exemplar": false, - "expr": "avg by (node)(fcvi_firmware_invalid_transmit_word_count{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "expr": "sum by (node)(fcvi_firmware_invalid_transmit_word_count{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", "interval": "", "legendFormat": "{{node}}", "refId": "A", @@ -1603,7 +1614,7 @@ }, { "collapsed": true, - "datasource": "Prometheus", + "datasource": "${DS_PROMETHEUS}", "gridPos": { "h": 1, "w": 24, @@ -1613,7 +1624,8 @@ "id": 107, "panels": [ { - "datasource": "Prometheus", + "datasource": "${DS_PROMETHEUS}", + "description": "Average Number of RDMA I/Os issued per node", "fieldConfig": { "defaults": { "color": { @@ -1705,7 +1717,8 @@ "type": "timeseries" }, { - "datasource": null, + "datasource": "${DS_PROMETHEUS}", + "description": "Average Number of RDMA read I/Os issued per node", "fieldConfig": { "defaults": { "color": { @@ -1797,7 +1810,8 @@ "type": "timeseries" }, { - "datasource": null, + "datasource": "${DS_PROMETHEUS}", + "description": "Average Number of RDMA write I/Os issued per node", "fieldConfig": { "defaults": { "color": { @@ -1889,7 +1903,8 @@ "type": "timeseries" }, { - "datasource": null, + "datasource": "${DS_PROMETHEUS}", + "description": "Average RDMA I/O latency per node", "fieldConfig": { "defaults": { "color": { From 8c0e45932ab2a388128405cf0df893b5a5969a4a Mon Sep 17 00:00:00 2001 From: hardikl Date: Tue, 23 May 2023 20:35:12 +0530 Subject: [PATCH 6/6] feat: typo changes --- grafana/dashboards/cmode/mcc_cluster.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/grafana/dashboards/cmode/mcc_cluster.json b/grafana/dashboards/cmode/mcc_cluster.json index d27a30a7b..7a5cd7f42 100644 --- a/grafana/dashboards/cmode/mcc_cluster.json +++ b/grafana/dashboards/cmode/mcc_cluster.json @@ -1409,7 +1409,7 @@ "targets": [ { "exemplar": false, - "expr": "sum by (node)(fcvi_firmwares_systat_discard_frames{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", + "expr": "sum by (node)(fcvi_firmware_systat_discard_frames{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"})", "interval": "", "legendFormat": "{{node}}", "refId": "A",