hidden topk var removal from Grafana dashboards

[rahulguptajss]

TopK

• Remove pending hidden topk vars as mentioned here and replace panel queries with @ modifier

[rahulguptajss]

Below are the pending ones after #2881 . Most are now from external_service_op.json and storage grid.

grafana/dashboards/cmode/external_service_op.json:          "query": "query_result(topk($TopResources, avg by (key) (avg_over_time(external_service_op_request_latency{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",svm=~\"$SVM\",service_name=~\"$ServiceName\",operation=~\"$Operation\"}[3h]))))",
grafana/dashboards/cmode/external_service_op.json:          "query": "query_result(topk($TopResources, sum by (key) (avg_over_time(external_service_op_num_not_found_responses{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",svm=~\"$SVM\",service_name=~\"$ServiceName\",operation=~\"$Operation\"}[3h]))))",
grafana/dashboards/cmode/external_service_op.json:          "query": "query_result(topk($TopResources, sum by (key) (avg_over_time(external_service_op_num_request_failures{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",svm=~\"$SVM\",service_name=~\"$ServiceName\",operation=~\"$Operation\"}[3h]))))",
grafana/dashboards/cmode/external_service_op.json:          "query": "query_result(topk($TopResources, sum by (key) (avg_over_time(external_service_op_num_requests_sent{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",svm=~\"$SVM\",service_name=~\"$ServiceName\",operation=~\"$Operation\"}[3h]))))",
grafana/dashboards/cmode/external_service_op.json:          "query": "query_result(topk($TopResources, sum by (key) (avg_over_time(external_service_op_num_responses_received{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",svm=~\"$SVM\",service_name=~\"$ServiceName\",operation=~\"$Operation\"}[3h]))))",
grafana/dashboards/cmode/external_service_op.json:          "query": "query_result(topk($TopResources, sum by (key) (avg_over_time(external_service_op_num_successful_responses{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",svm=~\"$SVM\",service_name=~\"$ServiceName\",operation=~\"$Operation\"}[3h]))))",
grafana/dashboards/cmode/external_service_op.json:          "query": "query_result(topk($TopResources, sum by (key) (avg_over_time(external_service_op_num_timeouts{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",svm=~\"$SVM\",service_name=~\"$ServiceName\",operation=~\"$Operation\"}[3h]))))",
grafana/dashboards/cmode/external_service_op.json:        "definition": "query_result(topk($TopResources, avg by (key) (avg_over_time(external_service_op_request_latency{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",svm=~\"$SVM\",service_name=~\"$ServiceName\",operation=~\"$Operation\"}[3h]))))",
grafana/dashboards/cmode/external_service_op.json:        "definition": "query_result(topk($TopResources, sum by (key) (avg_over_time(external_service_op_num_not_found_responses{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",svm=~\"$SVM\",service_name=~\"$ServiceName\",operation=~\"$Operation\"}[3h]))))",
grafana/dashboards/cmode/external_service_op.json:        "definition": "query_result(topk($TopResources, sum by (key) (avg_over_time(external_service_op_num_request_failures{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",svm=~\"$SVM\",service_name=~\"$ServiceName\",operation=~\"$Operation\"}[3h]))))",
grafana/dashboards/cmode/external_service_op.json:        "definition": "query_result(topk($TopResources, sum by (key) (avg_over_time(external_service_op_num_requests_sent{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",svm=~\"$SVM\",service_name=~\"$ServiceName\",operation=~\"$Operation\"}[3h]))))",
grafana/dashboards/cmode/external_service_op.json:        "definition": "query_result(topk($TopResources, sum by (key) (avg_over_time(external_service_op_num_responses_received{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",svm=~\"$SVM\",service_name=~\"$ServiceName\",operation=~\"$Operation\"}[3h]))))",
grafana/dashboards/cmode/external_service_op.json:        "definition": "query_result(topk($TopResources, sum by (key) (avg_over_time(external_service_op_num_successful_responses{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",svm=~\"$SVM\",service_name=~\"$ServiceName\",operation=~\"$Operation\"}[3h]))))",
grafana/dashboards/cmode/external_service_op.json:        "definition": "query_result(topk($TopResources, sum by (key) (avg_over_time(external_service_op_num_timeouts{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",svm=~\"$SVM\",service_name=~\"$ServiceName\",operation=~\"$Operation\"}[3h]))))",
grafana/dashboards/cmode/node.json:          "query": "query_result(topk($TopResources, avg_over_time(fcp_read_data{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"}[3h])+avg_over_time(fcp_write_data{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"}[3h])+avg_over_time(fcp_nvmf_read_data{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"}[3h])+avg_over_time(fcp_nvmf_write_data{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"}[3h])))",
grafana/dashboards/cmode/node.json:          "query": "query_result(topk($TopResources, avg_over_time(nic_rx_bytes{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"}[3h])+avg_over_time(nic_tx_bytes{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"}[3h])))",
grafana/dashboards/cmode/node.json:        "definition": "query_result(topk($TopResources, avg_over_time(fcp_read_data{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"}[3h])+avg_over_time(fcp_write_data{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"}[3h])+avg_over_time(fcp_nvmf_read_data{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"}[3h])+avg_over_time(fcp_nvmf_write_data{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"}[3h])))",
grafana/dashboards/cmode/node.json:        "definition": "query_result(topk($TopResources, avg_over_time(nic_rx_bytes{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"}[3h])+avg_over_time(nic_tx_bytes{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\"}[3h])))",
grafana/dashboards/cmode/power.json:          "query": "query_result(topk($TopResources, avg_over_time(aggr_power{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\"}[${__range}])))",
grafana/dashboards/cmode/power.json:        "definition": "query_result(topk($TopResources, avg_over_time(aggr_power{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\"}[${__range}])))",
grafana/dashboards/cmode/snapmirror.json:          "query": "query_result(topk($TopResources, avg_over_time(snapmirror_last_transfer_size{source_cluster=~\"$SourceCluster\",source_volume=~\"$SourceVolume\",destination_volume=~\"$DestinationVolume\",source_vserver=~\"$SourceSVM\",destination_vserver=~\"$DestinationSVM\"}[3h])))",
grafana/dashboards/cmode/snapmirror.json:        "definition": "query_result(topk($TopResources, avg_over_time(snapmirror_last_transfer_size{source_cluster=~\"$SourceCluster\",source_volume=~\"$SourceVolume\",destination_volume=~\"$DestinationVolume\",source_vserver=~\"$SourceSVM\",destination_vserver=~\"$DestinationSVM\"}[3h])))",
grafana/dashboards/storagegrid/fabricpool.json:          "query": "query_result(topk($TopResources, avg_over_time(storagegrid_private_load_balancer_storage_request_count{cluster=~\"$SGCluster\",policy=~\"$Policy\"}[${__range}])))",
grafana/dashboards/storagegrid/fabricpool.json:          "query": "query_result(topk($TopResources, avg_over_time(storagegrid_private_load_balancer_storage_rx_bytes{cluster=~\"$SGCluster\",policy=~\"$Policy\"}[${__range}])))",
grafana/dashboards/storagegrid/fabricpool.json:          "query": "query_result(topk($TopResources, avg_over_time(storagegrid_private_load_balancer_storage_tx_bytes{cluster=~\"$SGCluster\",policy=~\"$Policy\"}[${__range}])))",
grafana/dashboards/storagegrid/fabricpool.json:        "definition": "query_result(topk($TopResources, avg_over_time(storagegrid_private_load_balancer_storage_request_count{cluster=~\"$SGCluster\",policy=~\"$Policy\"}[${__range}])))",
grafana/dashboards/storagegrid/fabricpool.json:        "definition": "query_result(topk($TopResources, avg_over_time(storagegrid_private_load_balancer_storage_rx_bytes{cluster=~\"$SGCluster\",policy=~\"$Policy\"}[${__range}])))",
grafana/dashboards/storagegrid/fabricpool.json:        "definition": "query_result(topk($TopResources, avg_over_time(storagegrid_private_load_balancer_storage_tx_bytes{cluster=~\"$SGCluster\",policy=~\"$Policy\"}[${__range}])))",
grafana/dashboards/storagegrid/overview.json:          "query": "query_result(topk($TopResources, avg by(tenant,datacenter)(avg_over_time(storagegrid_tenant_usage_data_bytes{cluster=~\"$Cluster\"}[3h]))))",
grafana/dashboards/storagegrid/overview.json:          "query": "query_result(topk($TopResources, avg by(tenant,datacenter)(avg_over_time(storagegrid_tenant_usage_data_bytes{cluster=~\"$Cluster\"}[3h])/avg_over_time(storagegrid_tenant_usage_quota_bytes{cluster=~\"$Cluster\"}[3h]))))",
grafana/dashboards/storagegrid/overview.json:          "query": "query_result(topk($TopResources, avg_over_time(storagegrid_private_load_balancer_storage_request_count{cluster=~\"$Cluster\",policy=~\"$Policy\"}[3h])))",
grafana/dashboards/storagegrid/overview.json:          "query": "query_result(topk($TopResources, avg_over_time(storagegrid_private_load_balancer_storage_request_time{cluster=~\"$Cluster\",policy=~\"$Policy\"}[3h])))",
grafana/dashboards/storagegrid/overview.json:          "query": "query_result(topk($TopResources, avg_over_time(storagegrid_private_load_balancer_storage_rx_bytes{cluster=~\"$Cluster\",policy=~\"$Policy\"}[3h])))",
grafana/dashboards/storagegrid/overview.json:          "query": "query_result(topk($TopResources, avg_over_time(storagegrid_private_load_balancer_storage_tx_bytes{cluster=~\"$Cluster\",policy=~\"$Policy\"}[3h])))",
grafana/dashboards/storagegrid/overview.json:          "query": "query_result(topk($TopResources,(avg_over_time(storagegrid_node_cpu_utilization_percentage{cluster=~\"$Cluster\"}[3h]))))",
grafana/dashboards/storagegrid/overview.json:          "query": "query_result(topk($TopResources,(avg_over_time(storagegrid_storage_utilization_data_bytes{cluster=~\"$Cluster\"}[3h]))))",
grafana/dashboards/storagegrid/overview.json:        "definition": "query_result(topk($TopResources, avg by(tenant,datacenter)(avg_over_time(storagegrid_tenant_usage_data_bytes{cluster=~\"$Cluster\"}[3h]))))",
grafana/dashboards/storagegrid/overview.json:        "definition": "query_result(topk($TopResources, avg by(tenant,datacenter)(avg_over_time(storagegrid_tenant_usage_data_bytes{cluster=~\"$Cluster\"}[3h])/avg_over_time(storagegrid_tenant_usage_quota_bytes{cluster=~\"$Cluster\"}[3h]))))",
grafana/dashboards/storagegrid/overview.json:        "definition": "query_result(topk($TopResources, avg_over_time(storagegrid_private_load_balancer_storage_request_count{cluster=~\"$Cluster\",policy=~\"$Policy\"}[3h])))",
grafana/dashboards/storagegrid/overview.json:        "definition": "query_result(topk($TopResources, avg_over_time(storagegrid_private_load_balancer_storage_request_time{cluster=~\"$Cluster\",policy=~\"$Policy\"}[3h])))",
grafana/dashboards/storagegrid/overview.json:        "definition": "query_result(topk($TopResources, avg_over_time(storagegrid_private_load_balancer_storage_rx_bytes{cluster=~\"$Cluster\",policy=~\"$Policy\"}[3h])))",
grafana/dashboards/storagegrid/overview.json:        "definition": "query_result(topk($TopResources, avg_over_time(storagegrid_private_load_balancer_storage_tx_bytes{cluster=~\"$Cluster\",policy=~\"$Policy\"}[3h])))",
grafana/dashboards/storagegrid/overview.json:        "definition": "query_result(topk($TopResources,(avg_over_time(storagegrid_node_cpu_utilization_percentage{cluster=~\"$Cluster\"}[3h]))))",
grafana/dashboards/storagegrid/overview.json:        "definition": "query_result(topk($TopResources,(avg_over_time(storagegrid_storage_utilization_data_bytes{cluster=~\"$Cluster\"}[3h]))))",

[rahulguptajss]

Only SG dashboards will remain after PR #2889

[cgrinds]

Was TopDiskBusy missed in the aggregate dashboard?
Everything else looks good.

harvest/grafana/dashboards/cmode/aggregate.json

Line 3288 in 74dcf38

"expr": "avg by (node, aggr) (aggr_disk_busy{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\",aggr=~\"$TopDiskBusy\"})",

and

harvest/grafana/dashboards/cmode/aggregate.json

Line 3397 in 74dcf38

"expr": "avg by (node, aggr) (aggr_disk_busy{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\",aggr=~\"$TopDiskBusy\"})",

[rahulguptajss]

Was TopDiskBusy missed in the aggregate dashboard? Everything else looks good.

harvest/grafana/dashboards/cmode/aggregate.json

Line 3288 in 74dcf38

"expr": "avg by (node, aggr) (aggr_disk_busy{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\",aggr=~\"$TopDiskBusy\"})",

and

harvest/grafana/dashboards/cmode/aggregate.json

Line 3397 in 74dcf38

"expr": "avg by (node, aggr) (aggr_disk_busy{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$Node\",aggr=~\"$TopDiskBusy\"})",

I have removed this and added topk to two panels where it was used, as part of issue #2900.

[cgrinds]

Verified on 24.05.0 commit 6617960
All dashboards except for SG ones are fixed #2890