Merge branch 'master' into update-mountstats

.circleci/config.yml

@@ -46,7 +46,7 @@ jobs:
     parallelism: 3
     steps:
       - prometheus/setup_environment
-      - run: docker run --privileged linuxkit/binfmt:v0.8
+      - run: docker run --privileged linuxkit/binfmt:af88a591f9cc896a52ce596b9cf7ca26a061ef97
       - run: promu crossbuild -v --parallelism $CIRCLE_NODE_TOTAL --parallelism-thread $CIRCLE_NODE_INDEX
       - run: promu --config .promu-cgo.yml crossbuild -v --parallelism $CIRCLE_NODE_TOTAL --parallelism-thread $CIRCLE_NODE_INDEX
       - persist_to_workspace:

.github/workflows/golangci-lint.yml

@@ -22,7 +22,7 @@ jobs:
       - name: install Go
         uses: actions/setup-go@6edd4406fa81c3da01a34fa6f6343087c207a568 # v3.5.0
         with:
-          go-version: 1.20.x
+          go-version: 1.21.x
       - name: Install snmp_exporter/generator dependencies
         run: sudo apt-get update && sudo apt-get -y install libsnmp-dev
         if: github.repository == 'prometheus/snmp_exporter'

CHANGELOG.md

@@ -5,6 +5,23 @@
 * [ENHANCEMENT]
 * [BUGFIX]
 
+## 1.7.0 / 2023-11-11
+
+* [FEATURE] Add ZFS freebsd per dataset stats #2753
+* [FEATURE] Add cpu vulnerabilities reporting from sysfs #2721
+* [ENHANCEMENT] Parallelize stat calls in Linux filesystem collector #1772
+* [ENHANCEMENT] Add missing linkspeeds to ethtool collector 2711
+* [ENHANCEMENT] Add CPU MHz as the value for `node_cpu_info` metric #2778
+* [ENHANCEMENT] Improve qdisc collector performance #2779
+* [ENHANCEMENT] Add include and exclude filter for hwmon collector #2699
+* [ENHANCEMENT] Optionally fetch ARP stats via rtnetlink instead of procfs #2777
+* [BUFFIX] Fix ZFS arcstats on FreeBSD 14.0+ 2754
+* [BUGFIX] Fallback to 32-bit stats in netdev #2757
+* [BUGFIX] Close btrfs.FS handle after use #2780
+* [BUGFIX] Move RO status before error return #2807
+* [BUFFIX] Fix `promhttp_metric_handler_errors_total` being always active #2808
+* [BUGFIX] Fix nfsd v4 index miss #2824
+
 ## 1.6.1 / 2023-06-17
 
 Rebuild with latest Go compiler bugfix release.

VERSION

@@ -1 +1 @@
-1.6.1
+1.7.0

collector/fixtures/e2e-64k-page-output.txt

@@ -2815,6 +2815,7 @@ node_nfsd_requests_total{method="SetClientIDConfirm",proto="4"} 3
 node_nfsd_requests_total{method="SymLink",proto="2"} 0
 node_nfsd_requests_total{method="SymLink",proto="3"} 0
 node_nfsd_requests_total{method="Verify",proto="4"} 0
+node_nfsd_requests_total{method="WdelegGetattr",proto="4"} 15
 node_nfsd_requests_total{method="WrCache",proto="2"} 0
 node_nfsd_requests_total{method="Write",proto="2"} 0
 node_nfsd_requests_total{method="Write",proto="3"} 0

collector/fixtures/e2e-output.txt

@@ -2837,6 +2837,7 @@ node_nfsd_requests_total{method="SetClientIDConfirm",proto="4"} 3
 node_nfsd_requests_total{method="SymLink",proto="2"} 0
 node_nfsd_requests_total{method="SymLink",proto="3"} 0
 node_nfsd_requests_total{method="Verify",proto="4"} 0
+node_nfsd_requests_total{method="WdelegGetattr",proto="4"} 15
 node_nfsd_requests_total{method="WrCache",proto="2"} 0
 node_nfsd_requests_total{method="Write",proto="2"} 0
 node_nfsd_requests_total{method="Write",proto="3"} 0

collector/fixtures/proc/net/rpc/nfsd

@@ -9,3 +9,4 @@ proc2 18 2 69 0 0 4410 0 0 0 0 0 0 0 0 0 0 0 99 2
 proc3 22 2 112 0 2719 111 0 0 0 0 0 0 0 0 0 0 0 27 216 0 2 1 0
 proc4 2 2 10853
 proc4ops 72 0 0 0 1098 2 0 0 0 0 8179 5896 0 0 0 0 5900 0 0 2 0 2 0 9609 0 2 150 1272 0 0 0 1236 0 0 0 0 3 3 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
+wdeleg_getattr 15

collector/nfsd_linux.go

@@ -82,6 +82,8 @@ func (c *nfsdCollector) Update(ch chan<- prometheus.Metric) error {
 	c.updateNFSdRequestsv2Stats(ch, &stats.V2Stats)
 	c.updateNFSdRequestsv3Stats(ch, &stats.V3Stats)
 	c.updateNFSdRequestsv4Stats(ch, &stats.V4Ops)
+	ch <- prometheus.MustNewConstMetric(c.requestsDesc, prometheus.CounterValue,
+		float64(stats.WdelegGetattr), "4", "WdelegGetattr")
 
 	return nil
 }

docs/node-mixin/alerts/alerts.libsonnet

@@ -10,7 +10,7 @@
               (
                 node_filesystem_avail_bytes{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} / node_filesystem_size_bytes{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} * 100 < %(fsSpaceFillingUpWarningThreshold)d
               and
-                predict_linear(node_filesystem_avail_bytes{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s}[6h], 24*60*60) < 0
+                predict_linear(node_filesystem_avail_bytes{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s}[%(fsSpaceFillingUpPredictionWindow)s], 24*60*60) < 0
               and
                 node_filesystem_readonly{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} == 0
               )
@@ -407,6 +407,20 @@
               description: 'Systemd service {{ $labels.name }} has entered failed state at {{ $labels.instance }}',
             },
           },
+          {
+            alert: 'NodeBondingDegraded',
+            expr: |||
+              (node_bonding_slaves - node_bonding_active) != 0
+            ||| % $._config,
+            'for': '5m',
+            labels: {
+              severity: 'warning',
+            },
+            annotations: {
+              summary: 'Bonding interface is degraded',
+              description: 'Bonding interface {{ $labels.master }} on {{ $labels.instance }} is in degraded state due to one or more slave failures.',
+            },
+          },
         ],
       },
     ],

docs/node-mixin/config.libsonnet

@@ -54,13 +54,19 @@
     // 'NodeFilesystemSpaceFillingUp' alerts. These alerts fire if the disk
     // usage grows in a way that it is predicted to run out in 4h or 1d
     // and if the provided thresholds have been reached right now.
-    // In some cases you'll want to adjust these, e.g. by default Kubernetes
+    // In some cases you'll want to adjust these, e.g., by default, Kubernetes
     // runs the image garbage collection when the disk usage reaches 85%
     // of its available space. In that case, you'll want to reduce the
     // critical threshold below to something like 14 or 15, otherwise
     // the alert could fire under normal node usage.
+    // Additionally, the prediction window for the alert can be configured
+    // to account for environments where disk usage can fluctuate within
+    // a short time frame. By extending the prediction window, you can
+    // reduce false positives caused by temporary spikes, providing a
+    // more accurate prediction of disk space issues.
     fsSpaceFillingUpWarningThreshold: 40,
     fsSpaceFillingUpCriticalThreshold: 20,
+    fsSpaceFillingUpPredictionWindow: '6h',
 
     // Available disk space (%) thresholds on which to trigger the
     // 'NodeFilesystemAlmostOutOfSpace' alerts.

go.mod

@@ -1,6 +1,6 @@
 module github.com/prometheus/node_exporter
 
-go 1.19
+go 1.20
 
 require (
 	github.com/alecthomas/kingpin/v2 v2.3.2