Separate network faults from software drops and fix CPU temperature history

network_faults.go

@@ -0,0 +1,103 @@
+package main
+
+import (
+	"context"
+	"os/exec"
+	"path/filepath"
+	"strconv"
+	"strings"
+	"time"
+)
+
+func counterDelta(current, previous uint64) uint64 {
+	if current < previous {
+		return 0
+	}
+	return current - previous
+}
+
+func updateInterfaceDeltas(v *NetworkInterface, old NetworkInterface, elapsed float64) {
+	if elapsed <= 0 {
+		return
+	}
+	v.ReceivePerSec = float64(counterDelta(v.ReceiveBytes, old.ReceiveBytes)) / elapsed
+	v.TransmitPerSec = float64(counterDelta(v.TransmitBytes, old.TransmitBytes)) / elapsed
+	v.NewErrors = counterDelta(v.ReceiveErrors, old.ReceiveErrors) + counterDelta(v.TransmitErrors, old.TransmitErrors)
+	v.NewReceiveDrops = counterDelta(v.ReceiveDrops, old.ReceiveDrops)
+	v.NewTransmitDrops = counterDelta(v.TransmitDrops, old.TransmitDrops)
+	v.NewDrops = v.NewReceiveDrops + v.NewTransmitDrops
+	for name, value := range v.FaultCounters {
+		if previous, ok := old.FaultCounters[name]; ok {
+			v.NewFaults += counterDelta(value, previous)
+		}
+	}
+	// A transition matters even if the interface has not carried traffic yet.
+	v.LinkDown = old.Carrier && !v.Carrier
+}
+
+func interfaceLinkDown(v NetworkInterface) bool {
+	if v.Kind == "Firewall bridge" || v.Kind == "Firewall link" {
+		return false
+	}
+	if v.LinkDown {
+		return true
+	}
+	used := v.Master != "" || v.ReceiveBytes+v.TransmitBytes > 0
+	if v.Kind == "Physical" {
+		return used && (!v.Carrier || v.State == "down")
+	}
+	return used && v.State == "down"
+}
+
+func collectInterfaceFaults(v *NetworkInterface) {
+	base := filepath.Join("/sys/class/net", v.Name)
+	// /proc/net/dev folds missed packets into RX drop. Sysfs keeps software
+	// drops separate from rx_missed_errors, which must still trigger an alert.
+	if n, err := strconv.ParseUint(readTrimmed(filepath.Join(base, "statistics/rx_dropped")), 10, 64); err == nil {
+		v.ReceiveDrops = n
+	}
+	v.FaultCounters = map[string]uint64{}
+	for _, name := range []string{"rx_crc_errors", "rx_frame_errors", "rx_fifo_errors", "rx_missed_errors", "tx_fifo_errors", "tx_carrier_errors", "carrier_down_count"} {
+		path := filepath.Join(base, "statistics", name)
+		if name == "carrier_down_count" {
+			path = filepath.Join(base, name)
+		}
+		if n, err := strconv.ParseUint(readTrimmed(path), 10, 64); err == nil {
+			v.FaultCounters[name] = n
+		}
+	}
+	// Only Atlantic exposes the driver-specific names below. No configuration
+	// changes, and a missing ethtool is not itself a network failure.
+	driver, err := filepath.EvalSymlinks(filepath.Join(base, "device/driver"))
+	if err != nil || filepath.Base(driver) != "atlantic" {
+		return
+	}
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second)
+	defer cancel()
+	if out, err := exec.CommandContext(ctx, "ethtool", "-S", v.Name).Output(); err == nil {
+		for k, n := range parseAtlanticFaults(string(out)) {
+			v.FaultCounters["atlantic:"+k] = n
+		}
+	}
+}
+
+func parseAtlanticFaults(output string) map[string]uint64 {
+	result := map[string]uint64{}
+	for _, line := range strings.Split(output, "\n") {
+		key, value, ok := strings.Cut(strings.TrimSpace(line), ":")
+		if !ok {
+			continue
+		}
+		fields := strings.Fields(key)
+		if len(fields) == 0 {
+			continue
+		}
+		switch fields[len(fields)-1] {
+		case "InErrors", "InDroppedDma", "AllocFails", "SkbAllocFails", "Restarts":
+			if n, err := strconv.ParseUint(strings.TrimSpace(value), 10, 64); err == nil {
+				result[key] = n
+			}
+		}
+	}
+	return result
+}