Hardware lock-in cleanup: ice RX counter set and by-driver map collapsed to the single ixgbe nicRxFields list (newNICPoller drops its redundant driver gate), checkCoalesce loses the try-tx-then-EINVAL fallback and sets rx-usecs shared with tx as the one path, ice-attributed comments neutralized, dead errs.total removed with its redundant test assertion; ice counter reference set recorded in docs/nics/e810; verified on hardware (20.00G, zero errors, ECD 41m)

docs/nics/e810/README.md

@@ -7,6 +7,10 @@ Out of the box. The measurement path was originally built against it — its dat
 - `irdma` autoloads and binds ice ports, making `ETHTOOL_SCHANNELS` fail EBUSY ("Cannot change channels when RDMA is active") and failing the channels host check. `sudo rmmod irdma` (usage count 0; returns on reboot). The appliance kernel has no irdma.
 - ice refuses channel changes while ntuple rules exist — cabletest clears its own stale rules first.
 
+## RX error counter reference set
+
+The richest per-frame RX error breakdown of the NICs used — `illegal_bytes` and the MAC faults move while every frame still arrives intact, as close to a bit error rate as a link reports. `ethtool -S` names: `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`. Read the driver's own array, never sysfs beside it: ice folds crc errors and jabbers into `rx_errors`, so summing `rx_errors` alongside `rx_crc_errors` charges every bad frame twice.
+
 ## Module I2C: multi-byte framing works, writes are policy-blocked
 
 - topo-I2C (0x06E2/E3) has offset-size control: params bit[7] repeated-start, [6:5] address length, [3:0] data size. **Reads work perfectly.**

docs/nics/x520/README.md

@@ -4,8 +4,8 @@
 
 - PCIe Gen2 ×8 (5 GT/s, 32 Gb/s raw, ~25–26 Gb/s/dir effective vs 20 needed) — enough for 2×10G full duplex at the default mix; the 64 B case was host-bound already on the E810. Verify 5 GT/s ×8 trained (`lspci -vv`).
 - Loss attribution survives here: missed-packet (RXMPC → `rx_missed_errors`) and per-queue drop (QPRDC) counters — "prove host-side zero" works.
-- The RX error counter set is the 82599's slimmer one (`counters.go`): no jabber, fragment, illegal-byte or MAC-fault counters exist — crc/missed/length errors are what this link reports; the ice set remains the richer reference.
-- ixgbe's mixed rx/tx interrupt vectors reject a tx-specific coalesce value; `checkCoalesce` falls back to rx-shared-with-tx on EINVAL, which is the normal path here. The full rx=8160/tx=4096 ring ask is taken as-is.
+- The RX error counter set is the 82599's slimmer one (`counters.go`): no jabber, fragment, illegal-byte or MAC-fault counters exist — crc/missed/length errors are what this link reports; the richer ice reference set is recorded in [../e810/README.md](../e810/README.md).
+- ixgbe's mixed rx/tx interrupt vectors take one moderation value per vector, so `checkCoalesce` sets rx-usecs shared with tx. The full rx=8160/tx=4096 ring ask is taken as-is.
 - **`allow_unsupported_sfp=1` is mandatory** (`ixgbe_main.c:165`): the FS module's honest 10GBASE-T EEPROM fails Intel qualification and kills the whole port probe (error -95, no netdev). `load-ixgbe` passes it.
 
 ## The smoothed-bucket rate: read-time buckets, backward smear, no hardware stamps