chore: merge Release/25.05.1

CHANGELOG.md

@@ -1,6 +1,18 @@
 # Change Log
 ## [Releases](https://github.com/NetApp/harvest/releases)
 
+## 25.05.1 / 2025-06-10 Release
+:pushpin: This release is identical to 25.05.0, if you are using the Cisco collector, we recommend upgrading to version 25.05.1 to reduce cardinality issues caused by storing a switch's uptime as a label instead of a metric value.
+
+This release also includes:
+
+1. Introduced a new `ONTAP: Switch` dashboard that provides detailed information about switches connected to ONTAP.
+2. Enhanced functionality to parse the Cisco version when the RCF is missing.
+3. Updated to Golang 1.23.4, which includes several security vulnerability fixes (CVEs).
+4. MetroCluster internal SVMs and volumes are no longer exported when they are offline.
+
+---
+
 ## 25.05.0 / 2025-05-19 Release
 pushpin: Highlights of this major release include:
 ## :star: New Features

cmd/collectors/cisco/rest/client.go

@@ -158,7 +158,7 @@ func (c *Client) callWithAuthRetry(command string, callType apiType) (gjson.Resu
 	//  }
 	// }
 	code := result.Get("output.code")
-	if code.Exists() {
+	if code.Exists() && code.Int() != 200 {
 		errMsg := result.Get("output.msg").String()
 		if errMsg == "" {
 			errMsg = "unknown error"

cmd/tools/grafana/dashboard_test.go

@@ -1007,16 +1007,17 @@ func ensureLookBack(text string) string {
 
 func TestOnlyHighlightsExpanded(t *testing.T) {
 	exceptions := map[string]int{
-		"cmode/shelf.json":              2,
-		"cmode/fsa.json":                2,
+		"cmode/auditlog.json":           2,
 		"cmode/flexcache.json":          2,
-		"cmode/workload.json":           2,
-		"cmode/smb.json":                2,
+		"cmode/fsa.json":                2,
 		"cmode/health.json":             2,
+		"cmode/nfsTroubleshooting.json": 3,
 		"cmode/power.json":              2,
+		"cmode/shelf.json":              2,
+		"cmode/smb.json":                2,
+		"cmode/switch.json":             2,
+		"cmode/workload.json":           2,
 		"storagegrid/fabricpool.json":   2,
-		"cmode/auditlog.json":           2,
-		"cmode/nfsTroubleshooting.json": 3,
 	}
 	// count the number of expanded sections in the dashboard and ensure num expanded = 1
 	VisitDashboards(

docs/ontap-metrics.md

@@ -7,7 +7,7 @@ These can be generated on demand by running `bin/harvest grafana metrics`. See
 - More information about ONTAP REST performance counters can be found [here](https://docs.netapp.com/us-en/ontap-pcmap-9121/index.html).
 
 ```
-Creation Date : 2025-May-29
+Creation Date : 2025-Jun-09
 ONTAP Version: 9.16.1
 ```
 ## Understanding the structure

docs/resources/power-algorithm.md

@@ -2,7 +2,7 @@
 Gathering power metrics requires a cluster with:
 
 * ONTAP versions 9.6+
-* [REST enabled](../prepare-cdot-clusters.md), even when using the ZAPI collector. After granting REST permissions, restart Harvest.
+* [REST enabled](../prepare-cdot-clusters.md#rest-least-privilege-role), even when using the ZAPI collector. After granting REST permissions, restart Harvest.
 
 REST is required because it is the only way to collect chassis field-replaceable-unit (FRU) information via the
 REST API `/api/private/cli/system/chassis/fru`.

grafana/dashboards/cmode/network.json

@@ -71,7 +71,7 @@
   "gnetId": null,
   "graphTooltip": 1,
   "id": null,
-  "iteration": 1723188904112,
+  "iteration": 1749475358867,
   "links": [
     {
       "asDropdown": true,
@@ -564,7 +564,7 @@
       "panels": [
         {
           "datasource": "${DS_PROMETHEUS}",
-          "description": "Ethernet port details.",
+          "description": "Displays a collection of ports (physical, VLAN and LAG) for an entire cluster.",
           "fieldConfig": {
             "defaults": {
               "custom": {
@@ -762,6 +762,18 @@
                     "value": "Mbits"
                   }
                 ]
+              },
+              {
+                "matcher": {
+                  "id": "byName",
+                  "options": "MTU"
+                },
+                "properties": [
+                  {
+                    "id": "unit",
+                    "value": "string"
+                  }
+                ]
               }
             ]
           },
@@ -893,7 +905,7 @@
         },
         {
           "datasource": "${DS_PROMETHEUS}",
-          "description": "NIC port details.",
+          "description": "This table tracks hardware network traffic performance and errors for all supported network interface cards (NIC), such as Intel Niantic, Qlogic, and CNA.",
           "fieldConfig": {
             "defaults": {
               "custom": {
@@ -1614,7 +1626,7 @@
               "exemplar": false,
               "expr": "nic_util_percent{cluster=~\"$Cluster\",datacenter=~\"$Datacenter\",nic=~\"$Eth\",node=~\"$Node\"}\nand\n  topk(\n    $TopResources,\n    avg_over_time(\n      nic_util_percent{cluster=~\"$Cluster\",datacenter=~\"$Datacenter\",nic=~\"$Eth\",node=~\"$Node\"}[3h] @ end()\n    )\n  )",
               "interval": "",
-              "legendFormat": "{{node}} {{nic}}",
+              "legendFormat": "{{node}} - {{nic}}",
               "refId": "A"
             }
           ],
@@ -1703,15 +1715,17 @@
           "pluginVersion": "8.1.8",
           "targets": [
             {
+              "exemplar": false,
               "expr": "sum by (cluster) (\n  nic_tx_total_errors{cluster=~\"$Cluster\",datacenter=~\"$Datacenter\",nic=~\"$Eth\",node=~\"$Node\"}\n)",
               "interval": "",
-              "legendFormat": "TOTAL",
+              "legendFormat": "TOTAL - {{cluster}}",
               "refId": "A"
             },
             {
+              "exemplar": false,
               "expr": "sum by (cluster) (\n  nic_tx_hw_errors{cluster=~\"$Cluster\",datacenter=~\"$Datacenter\",nic=~\"$Eth\",node=~\"$Node\"}\n)",
               "interval": "",
-              "legendFormat": "HW",
+              "legendFormat": "HW - {{cluster}}",
               "refId": "D"
             }
           ],
@@ -1800,27 +1814,31 @@
           "pluginVersion": "8.1.8",
           "targets": [
             {
+              "exemplar": false,
               "expr": "sum by (cluster) (\n  nic_rx_total_errors{cluster=~\"$Cluster\",datacenter=~\"$Datacenter\",nic=~\"$Eth\",node=~\"$Node\"}\n)",
               "interval": "",
-              "legendFormat": "TOTAL",
+              "legendFormat": "TOTAL- {{cluster}}",
               "refId": "A"
             },
             {
+              "exemplar": false,
               "expr": "sum by (cluster) (\n  nic_rx_alignment_errors{cluster=~\"$Cluster\",datacenter=~\"$Datacenter\",nic=~\"$Eth\",node=~\"$Node\"}\n)",
               "interval": "",
-              "legendFormat": "ALIGNMENT",
+              "legendFormat": "ALIGNMENT- {{cluster}}",
               "refId": "B"
             },
             {
+              "exemplar": false,
               "expr": "sum by (cluster) (\n  nic_rx_crc_errors{cluster=~\"$Cluster\",datacenter=~\"$Datacenter\",nic=~\"$Eth\",node=~\"$Node\"}\n)",
               "interval": "",
-              "legendFormat": "CRC",
+              "legendFormat": "CRC- {{cluster}}",
               "refId": "C"
             },
             {
+              "exemplar": false,
               "expr": "sum by (cluster) (\n  nic_rx_length_errors{cluster=~\"$Cluster\",datacenter=~\"$Datacenter\",nic=~\"$Eth\",node=~\"$Node\"}\n)",
               "interval": "",
-              "legendFormat": "LENGTH",
+              "legendFormat": "LENGTH- {{cluster}}",
               "refId": "D"
             }
           ],
@@ -2145,8 +2163,8 @@
                   "Value #F": 8,
                   "cluster": 1,
                   "datacenter": 0,
-                  "nic": 2,
-                  "node": 3
+                  "nic": 3,
+                  "node": 2
                 },
                 "renameByName": {
                   "Value #A": "",
@@ -5179,5 +5197,5 @@
   "timezone": "",
   "title": "ONTAP: Network",
   "uid": "cdot-network",
-  "version": 12
+  "version": 13
 }