BCM module diagnostics replace timestamp probes: bringup forces EEE off and runs ECD (re-run on every reset, re-baselining past its blip), 1 Hz SNR margin + corrected counters on panel and console; X520 bench divergences bypassed and tracked in open-questions

counters.go

@@ -1,7 +1,9 @@
 package main
 
 import (
+	"fmt"
 	"os"
+	"path/filepath"
 	"strconv"
 	"strings"
 	"sync/atomic"
@@ -28,22 +30,43 @@ var nicTxFields = []string{
 // Receiving is the hardware's, and is taken from the driver's own array, which
 // sysfs both flattens and overlaps: ice folds crc errors and jabbers into
 // rx_errors, so the old sum of rx_errors alongside rx_crc_errors charged every
-// bad frame check twice. Named individually here, so nothing contains anything
-// else in the list.
-var nicRxStats = []string{
-	"rx_crc_errors.nic",
-	"rx_jabber.nic",
-	"rx_undersize.nic",
-	"rx_oversize.nic",
-	"rx_fragments.nic",
-	"rx_dropped.nic",
-	// Below the frame: a 64b/66b block that decoded to no legal symbol, and the
-	// fault ordered sets the pcs sends when it loses sync. A cable going
-	// marginal moves these while every frame still arrives intact, which is as
-	// close to a bit error rate as this link will report.
-	"illegal_bytes.nic",
-	"mac_local_faults.nic",
-	"mac_remote_faults.nic",
+// bad frame check twice. Named individually per driver, so nothing contains
+// anything else in its list.
+var nicRxStatsByDriver = map[string][]string{
+	// The reference set (E810). Below the frame: illegal_bytes is a 64b/66b
+	// block that decoded to no legal symbol, and the faults are the ordered
+	// sets the pcs sends when it loses sync. A cable going marginal moves
+	// these while every frame still arrives intact, which is as close to a
+	// bit error rate as this link will report.
+	"ice": {
+		"rx_crc_errors.nic",
+		"rx_jabber.nic",
+		"rx_undersize.nic",
+		"rx_oversize.nic",
+		"rx_fragments.nic",
+		"rx_dropped.nic",
+		"illegal_bytes.nic",
+		"mac_local_faults.nic",
+		"mac_remote_faults.nic",
+	},
+	// The 82599 exposes no jabber, fragment, illegal-byte or fault counters
+	// through ethtool — this is the closest bench set, and one of the X520
+	// divergences listed in docs/open-questions.md.
+	"ixgbe": {
+		"rx_crc_errors",
+		"rx_missed_errors",
+		"rx_length_errors",
+		"rx_long_length_errors",
+		"rx_short_length_errors",
+	},
+}
+
+func ifDriver(name string) (string, error) {
+	link, err := os.Readlink("/sys/class/net/" + name + "/device/driver")
+	if err != nil {
+		return "", err
+	}
+	return filepath.Base(link), nil
 }
 
 func readUint(path string) (uint64, bool) {
@@ -93,7 +116,15 @@ type nicPoller struct {
 }
 
 func newNICPoller(fd int, txName, rxName string, total *atomic.Uint64) (*nicPoller, error) {
-	rx, err := newStatReader(fd, rxName, nicRxStats)
+	drv, err := ifDriver(rxName)
+	if err != nil {
+		return nil, err
+	}
+	want, ok := nicRxStatsByDriver[drv]
+	if !ok {
+		return nil, fmt.Errorf("%s: no rx error statistic set for driver %s", rxName, drv)
+	}
+	rx, err := newStatReader(fd, rxName, want)
 	if err != nil {
 		return nil, err
 	}