Optionally fetch ARP stats via rtnetlink instead of procfs (#2777)

* Optionally fetch ARP stats via rtnetlink instead of procfs

Implement collection of ARP stats via rtnetlink to work around
shortcomings in the output of /proc/net/arp, which truncates InfiniBand
link-layer addresses.

Fixes: #2776

---------

Signed-off-by: Daniel Swarbrick <daniel.swarbrick@gmail.com>
Co-authored-by: Ben Kochie <superq@gmail.com>

collector/arp_linux.go

@@ -17,16 +17,22 @@
 package collector
 
 import (
+	"errors"
 	"fmt"
+	"net"
+
 	"github.com/alecthomas/kingpin/v2"
 	"github.com/go-kit/log"
+	"github.com/jsimonetti/rtnetlink"
 	"github.com/prometheus/client_golang/prometheus"
 	"github.com/prometheus/procfs"
+	"golang.org/x/sys/unix"
 )
 
 var (
 	arpDeviceInclude = kingpin.Flag("collector.arp.device-include", "Regexp of arp devices to include (mutually exclusive to device-exclude).").String()
 	arpDeviceExclude = kingpin.Flag("collector.arp.device-exclude", "Regexp of arp devices to exclude (mutually exclusive to device-include).").String()
+	arpNetlink       = kingpin.Flag("collector.arp.netlink", "Use netlink to gather stats instead of /proc/net/arp.").Default("true").Bool()
 )
 
 type arpCollector struct {
@@ -69,13 +75,65 @@ func getTotalArpEntries(deviceEntries []procfs.ARPEntry) map[string]uint32 {
 	return entries
 }
 
-func (c *arpCollector) Update(ch chan<- prometheus.Metric) error {
+func getTotalArpEntriesRTNL() (map[string]uint32, error) {
-	entries, err := c.fs.GatherARPEntries()
+	conn, err := rtnetlink.Dial(nil)
+	if err != nil {
+		return nil, err
+	}
+	defer conn.Close()
+
+	neighbors, err := conn.Neigh.List()
 	if err != nil {
-		return fmt.Errorf("could not get ARP entries: %w", err)
+		return nil, err
+	}
+
+	ifIndexEntries := make(map[uint32]uint32)
+
+	for _, n := range neighbors {
+		// Neighbors will also contain IPv6 neighbors, but since this is purely an ARP collector,
+		// restrict to AF_INET. Also skip entries which have state NUD_NOARP to conform to output
+		// of /proc/net/arp.
+		if n.Family == unix.AF_INET && n.State&unix.NUD_NOARP == 0 {
+			ifIndexEntries[n.Index]++
+		}
 	}
 
-	enumeratedEntry := getTotalArpEntries(entries)
+	enumEntries := make(map[string]uint32)
+
+	// Convert interface indexes to names.
+	for ifIndex, entryCount := range ifIndexEntries {
+		iface, err := net.InterfaceByIndex(int(ifIndex))
+		if err != nil {
+			if errors.Unwrap(err).Error() == "no such network interface" {
+				continue
+			}
+			return nil, err
+		}
+
+		enumEntries[iface.Name] = entryCount
+	}
+
+	return enumEntries, nil
+}
+
+func (c *arpCollector) Update(ch chan<- prometheus.Metric) error {
+	var enumeratedEntry map[string]uint32
+
+	if *arpNetlink {
+		var err error
+
+		enumeratedEntry, err = getTotalArpEntriesRTNL()
+		if err != nil {
+			return fmt.Errorf("could not get ARP entries: %w", err)
+		}
+	} else {
+		entries, err := c.fs.GatherARPEntries()
+		if err != nil {
+			return fmt.Errorf("could not get ARP entries: %w", err)
+		}
+
+		enumeratedEntry = getTotalArpEntries(entries)
+	}
 
 	for device, entryCount := range enumeratedEntry {
 		if c.deviceFilter.ignored(device) {

end-to-end-test.sh

@@ -132,6 +132,7 @@ fi
   --collector.qdisc.fixtures="collector/fixtures/qdisc/" \
   --collector.qdisc.device-include="(wlan0|eth0)" \
   --collector.arp.device-exclude="nope" \
+  --no-collector.arp.netlink \
   --collector.hwmon.chip-include="(applesmc|coretemp|hwmon4|nct6779)" \
   --collector.netclass.ignored-devices="(dmz|int)" \
   --collector.netclass.ignore-invalid-speed \

go.mod

@@ -14,7 +14,7 @@ require (
 	github.com/hodgesds/perf-utils v0.7.0
 	github.com/illumos/go-kstat v0.0.0-20210513183136-173c9b0a9973
 	github.com/josharian/native v1.1.0
-	github.com/jsimonetti/rtnetlink v1.3.4
+	github.com/jsimonetti/rtnetlink v1.3.5
 	github.com/lufia/iostat v1.2.1
 	github.com/mattn/go-xmlrpc v0.0.3
 	github.com/mdlayher/ethtool v0.1.0
@@ -29,7 +29,7 @@ require (
 	github.com/prometheus/procfs v0.11.1
 	github.com/safchain/ethtool v0.3.0
 	golang.org/x/exp v0.0.0-20230522175609-2e198f4a06a1
-	golang.org/x/sys v0.10.0
+	golang.org/x/sys v0.11.0
 	howett.net/plist v1.0.0
 )
 

go.sum

@@ -8,7 +8,7 @@ github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
 github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
 github.com/cespare/xxhash/v2 v2.2.0 h1:DC2CZ1Ep5Y4k3ZQ899DldepgrayRUGE6BBZ/cd9Cj44=
 github.com/cespare/xxhash/v2 v2.2.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
-github.com/cilium/ebpf v0.10.0 h1:nk5HPMeoBXtOzbkZBWym+ZWq1GIiHUsBFXxwewXAHLQ=
+github.com/cilium/ebpf v0.11.0 h1:V8gS/bTCCjX9uUnkUFUpPsksM8n1lXBAvHcpiFk1X2Y=
 github.com/coreos/go-systemd/v22 v22.5.0 h1:RrqgGjYQKalulkV8NGVIfkXQf6YYmOyiJKk8iXXhfZs=
 github.com/coreos/go-systemd/v22 v22.5.0/go.mod h1:Y58oyj3AT4RCenI/lSvhwexgC+NSVTIJ3seZv2GcEnc=
 github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
@@ -47,8 +47,8 @@ github.com/josharian/native v1.1.0 h1:uuaP0hAbW7Y4l0ZRQ6C9zfb7Mg1mbFKry/xzDAfmtL
 github.com/josharian/native v1.1.0/go.mod h1:7X/raswPFr05uY3HiLlYeyQntB6OO7E/d2Cu7qoaN2w=
 github.com/jpillora/backoff v1.0.0 h1:uvFg412JmmHBHw7iwprIxkPMI+sGQ4kzOWsMeHnm2EA=
 github.com/jpillora/backoff v1.0.0/go.mod h1:J/6gKK9jxlEcS3zixgDgUAsiuZ7yrSoa/FX5e0EB2j4=
-github.com/jsimonetti/rtnetlink v1.3.4 h1:uUcd9SE8sQe/enLBEVaWDkgGYWNsX3EU4eIxbEZYmF0=
+github.com/jsimonetti/rtnetlink v1.3.5 h1:hVlNQNRlLDGZz31gBPicsG7Q53rnlsz1l1Ix/9XlpVA=
-github.com/jsimonetti/rtnetlink v1.3.4/go.mod h1:jGCNm5lJdGplEXKCVwqhQ5tRIGV0dNREhLyNWVzBxHc=
+github.com/jsimonetti/rtnetlink v1.3.5/go.mod h1:0LFedyiTkebnd43tE4YAkWGIq9jQphow4CcwxaT2Y00=
 github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
 github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
 github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
@@ -141,8 +141,9 @@ golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.9.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.10.0 h1:SqMFp9UcQJZa+pmYuAKjd9xq1f0j5rLcDIk0mj4qAsA=
 golang.org/x/sys v0.10.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.11.0 h1:eG7RXZHdqOJ1i+0lgLgCpSXAp6M3LYlAo6osgSi0xOM=
+golang.org/x/sys v0.11.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
 golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=