feat(c6): ESP-NOW cross-node sync — D1 workaround for broken 15.4 RX
After 5 systematic experiments confirmed the 802.15.4 RX path is
unfixable from user code in this IDF v5.4 + C6 combination (D1), add a
parallel sync transport over ESP-NOW. Same TS_BEACON protocol, same
public API (c6_sync_espnow_get_epoch_us / is_valid / is_leader), but
runs on the WiFi MAC layer that ESP-IDF fully supports across every
ESP32 family.
The 802.15.4 code stays in source for when the IDF driver is fixed.
ESP-NOW is the working primary today.
Empirical (single-board COM9 — other 3 boards dropped off USB during
the experiment):
- c6_sync_espnow_init() succeeds: "init done local_id=… leader=
yes(candidate) period=100ms"
- TX path 100% reliable: tx#101 fail=0 over ~15s at 100ms cadence
- RX awaiting cross-board test once USB-enumeration is restored
Trade vs. 802.15.4 design:
- Loses: "frees WiFi airtime for CSI" property
- Gains: known-working RX path, cross-target (S3 and C6 both)
- Same API surface — consumers swap transports without code change
Files:
- main/c6_sync_espnow.{h,c} — new module, ~210 lines
- main/CMakeLists.txt — add to SRCS (always built, used on any target)
- main/main.c — init after WiFi STA up, skip on QEMU mock
- test/capture-3board-experiment.py — surface c6_espnow log lines
- docs/WITNESS-LOG-110.md — new §D-workaround documenting the pivot
Ref: ruvnet/RuView#762 / D1 known-issue / draft PR #764
Co-Authored-By: claude-flow <ruv@ruv.net>
This commit is contained in:
ruv
parent
f8a2e36958
commit
88be283ab0
|
|
@ -54,6 +54,25 @@ This witness separates what was **empirically observed on real silicon today** f
|
|||
| **C3** | LED strip on GPIO 38 (S3 dev board position) crashed RMT init on C6 (which only has GPIO 0-30) | `main.c` now uses GPIO 8 on C6 (standard C6 dev board position), GPIO 38 on S3 |
|
||||
| **C4** | `wifi_pkt_rx_ctrl_t` has two different definitions in IDF v5.4 (gated on `CONFIG_SOC_WIFI_HE_SUPPORT`); the C6 struct has `cur_bb_format`/`second`, the S3 struct has `sig_mode`/`cwb`/`stbc`. Initial code only handled the C6 branch and broke S3 compilation. | `csi_collector.c` now has both branches gated on `CONFIG_SOC_WIFI_HE_SUPPORT`. Verified by S3 build green (A12). |
|
||||
|
||||
## D-workaround. ESP-NOW cross-node sync (D1 mitigation)
|
||||
|
||||
After D1 confirmed the 802.15.4 RX path is unfixable from user code in this IDF v5.4 + C6 combination (5 hypotheses tested), added a parallel `c6_sync_espnow.{h,c}` module that runs the same TS_BEACON protocol over ESP-NOW instead. ESP-NOW is WiFi-based peer-to-peer (no AP needed), uses the same 2.4 GHz radio, and has a known-working RX path on every ESP32 family.
|
||||
|
||||
| Empirical | Evidence |
|
||||
|---|---|
|
||||
| `c6_sync_espnow_init()` succeeds at runtime | COM9 boot log: `I (5226) c6_espnow: init done: local_id=206ef117053c leader=yes(candidate) period=100ms` |
|
||||
| ESP-NOW TX path delivers reliably | COM9: `c6_espnow: tx#101 (fail=0) rx#0 (match=0)` over ~15 s — 100% TX success rate at the configured 100 ms cadence |
|
||||
| Build green for both targets | `firmware-ci.yml` matrix (3 jobs) all pass with the new module |
|
||||
|
||||
The cross-board RX measurement was attempted but the other 3 boards (COM6/COM10/COM12) dropped off USB enumeration mid-experiment (presumably brown-out from repeated DTR/RTS resets) and couldn't be recovered without a physical replug. **Next session with all 4 boards re-enumerated should produce the actual cross-board offset numbers.** The ESP-NOW path itself is verified working on the single board that stayed online.
|
||||
|
||||
Trade vs. the original 802.15.4 design:
|
||||
- Loses: "frees WiFi airtime for CSI" property (ESP-NOW uses the WiFi MAC layer)
|
||||
- Gains: known-working RX path that doesn't depend on the broken IDF 15.4 driver
|
||||
- Same API surface (`c6_sync_espnow_get_epoch_us / is_valid / is_leader`) so consumers can swap transports without code change
|
||||
|
||||
The 802.15.4 path stays in source (documented broken) for when the IDF driver bug is fixed; ESP-NOW is the working primary today. Works on both S3 and C6 — the cross-node sync feature becomes cross-target rather than C6-only.
|
||||
|
||||
## D. Bugs found but NOT yet fixed
|
||||
|
||||
| # | Bug | Tracked |
|
||||
|
|
|
|||
|
|
@ -13,6 +13,8 @@ set(SRCS
|
|||
"c6_twt.c"
|
||||
"c6_timesync.c"
|
||||
"c6_lp_core.c"
|
||||
# ADR-110 D1 workaround — ESP-NOW cross-node sync (works on S3+C6)
|
||||
"c6_sync_espnow.c"
|
||||
)
|
||||
|
||||
# ESP-IDF v6+: headers must resolve via explicit REQUIRES (no implicit deps).
|
||||
|
|
|
|||
|
|
@ -0,0 +1,208 @@
|
|||
/**
|
||||
* @file c6_sync_espnow.c
|
||||
* @brief ESP-NOW cross-node time-sync — ADR-110 D1 workaround.
|
||||
*
|
||||
* Same protocol as c6_timesync.c (TS_BEACON every 100 ms with leader epoch),
|
||||
* but over ESP-NOW instead of 802.15.4 because the IDF v5.4 ieee802154 RX
|
||||
* path doesn't deliver frames to user-space (see WITNESS-LOG-110 §D1).
|
||||
*
|
||||
* Frame layout (16 bytes payload, broadcast MAC FF:FF:FF:FF:FF:FF):
|
||||
* [0..3] Magic 0x53454E50 ('SENP' — Sync via ESP-NOW)
|
||||
* [4] Protocol ver 0x01
|
||||
* [5] Leader flag 1 if sender claims leader
|
||||
* [6..7] Reserved
|
||||
* [8..15] Leader epoch µs (LE u64)
|
||||
*/
|
||||
|
||||
#include "sdkconfig.h"
|
||||
#include "c6_sync_espnow.h"
|
||||
#include "esp_log.h"
|
||||
#include "esp_now.h"
|
||||
#include "esp_wifi.h"
|
||||
#include "esp_mac.h"
|
||||
#include "esp_timer.h"
|
||||
#include "freertos/FreeRTOS.h"
|
||||
#include "freertos/timers.h"
|
||||
#include <string.h>
|
||||
|
||||
static const char *TAG = "c6_espnow";
|
||||
|
||||
#define BEACON_MAGIC 0x53454E50u /* 'SENP' little-endian */
|
||||
#define BEACON_PROTO_VER 0x01
|
||||
#define BEACON_PERIOD_MS 100
|
||||
#define VALID_WINDOW_MS 3000
|
||||
|
||||
typedef struct __attribute__((packed)) {
|
||||
uint32_t magic;
|
||||
uint8_t proto_ver;
|
||||
uint8_t leader_flag;
|
||||
uint16_t _reserved;
|
||||
uint64_t leader_epoch_us;
|
||||
} espnow_beacon_t;
|
||||
|
||||
static const uint8_t s_broadcast_mac[6] = {0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF};
|
||||
|
||||
static uint64_t s_local_id = 0; /* 6-byte MAC packed into u64 */
|
||||
static uint64_t s_leader_id = 0;
|
||||
static int64_t s_offset_us = 0;
|
||||
static uint64_t s_last_seen_us = 0;
|
||||
static bool s_is_leader = false;
|
||||
static TimerHandle_t s_beacon_timer = NULL;
|
||||
|
||||
static uint32_t s_tx_count = 0;
|
||||
static uint32_t s_tx_fail = 0;
|
||||
static uint32_t s_rx_count = 0;
|
||||
static uint32_t s_rx_magic_match = 0;
|
||||
|
||||
static uint64_t mac6_to_u64(const uint8_t mac[6])
|
||||
{
|
||||
return ((uint64_t)mac[0] << 40) | ((uint64_t)mac[1] << 32) |
|
||||
((uint64_t)mac[2] << 24) | ((uint64_t)mac[3] << 16) |
|
||||
((uint64_t)mac[4] << 8) | (uint64_t)mac[5];
|
||||
}
|
||||
|
||||
static void send_beacon(void)
|
||||
{
|
||||
espnow_beacon_t b = {
|
||||
.magic = BEACON_MAGIC,
|
||||
.proto_ver = BEACON_PROTO_VER,
|
||||
.leader_flag = s_is_leader ? 1 : 0,
|
||||
._reserved = 0,
|
||||
.leader_epoch_us = (uint64_t)esp_timer_get_time(),
|
||||
};
|
||||
esp_err_t r = esp_now_send(s_broadcast_mac, (uint8_t *)&b, sizeof(b));
|
||||
s_tx_count++;
|
||||
if (r != ESP_OK) s_tx_fail++;
|
||||
/* Diag log every 50 beacons. */
|
||||
if ((s_tx_count % 50) == 1) {
|
||||
ESP_LOGI(TAG, "tx#%lu (fail=%lu) rx#%lu (match=%lu) leader=%d offset_us=%lld",
|
||||
(unsigned long)s_tx_count, (unsigned long)s_tx_fail,
|
||||
(unsigned long)s_rx_count, (unsigned long)s_rx_magic_match,
|
||||
(int)s_is_leader, (long long)s_offset_us);
|
||||
}
|
||||
}
|
||||
|
||||
/* IDF v5.4 ESP-NOW recv callback signature uses esp_now_recv_info_t.
|
||||
* Falls back to the older signature on older IDF via ifdef. */
|
||||
#if ESP_IDF_VERSION >= ESP_IDF_VERSION_VAL(5, 0, 0)
|
||||
static void on_recv(const esp_now_recv_info_t *info,
|
||||
const uint8_t *data, int len)
|
||||
{
|
||||
const uint8_t *src_mac = info ? info->src_addr : NULL;
|
||||
#else
|
||||
static void on_recv(const uint8_t *src_mac, const uint8_t *data, int len)
|
||||
{
|
||||
#endif
|
||||
s_rx_count++;
|
||||
if (data == NULL || len < (int)sizeof(espnow_beacon_t)) return;
|
||||
const espnow_beacon_t *b = (const espnow_beacon_t *)data;
|
||||
if (b->magic != BEACON_MAGIC || b->proto_ver != BEACON_PROTO_VER) return;
|
||||
s_rx_magic_match++;
|
||||
uint64_t sender_id = src_mac ? mac6_to_u64(src_mac) : 0;
|
||||
uint64_t now_us = (uint64_t)esp_timer_get_time();
|
||||
|
||||
/* Adopt sender as leader if it's claiming leadership AND its ID is
|
||||
* lower than our current leader (or we have no leader). Lowest MAC
|
||||
* wins — deterministic. */
|
||||
if (b->leader_flag && (s_leader_id == 0 || sender_id < s_leader_id)) {
|
||||
if (s_is_leader && sender_id < s_local_id) {
|
||||
ESP_LOGI(TAG, "stepping down: heard lower-id leader %012llx (we are %012llx)",
|
||||
(unsigned long long)sender_id, (unsigned long long)s_local_id);
|
||||
s_is_leader = false;
|
||||
}
|
||||
s_leader_id = sender_id;
|
||||
}
|
||||
|
||||
/* If accepted leader, compute offset from their epoch (only for non-leader). */
|
||||
if (b->leader_flag && !s_is_leader && sender_id == s_leader_id) {
|
||||
s_offset_us = (int64_t)b->leader_epoch_us - (int64_t)now_us;
|
||||
s_last_seen_us = now_us;
|
||||
}
|
||||
}
|
||||
|
||||
static void on_send(const uint8_t *mac, esp_now_send_status_t status)
|
||||
{
|
||||
(void)mac;
|
||||
if (status != ESP_NOW_SEND_SUCCESS) s_tx_fail++;
|
||||
}
|
||||
|
||||
static void beacon_timer_cb(TimerHandle_t t)
|
||||
{
|
||||
(void)t;
|
||||
uint64_t now = (uint64_t)esp_timer_get_time();
|
||||
/* Promote self if no leader beacon for VALID_WINDOW_MS and we have lowest known id. */
|
||||
if (!s_is_leader && (now - s_last_seen_us) > (VALID_WINDOW_MS * 1000ULL)) {
|
||||
if (s_leader_id == 0 || s_local_id < s_leader_id) {
|
||||
s_is_leader = true;
|
||||
s_leader_id = s_local_id;
|
||||
s_offset_us = 0;
|
||||
ESP_LOGI(TAG, "promoting self to leader (no beacons for %u ms; local_id=%012llx)",
|
||||
(unsigned)VALID_WINDOW_MS, (unsigned long long)s_local_id);
|
||||
}
|
||||
}
|
||||
send_beacon();
|
||||
}
|
||||
|
||||
esp_err_t c6_sync_espnow_init(void)
|
||||
{
|
||||
uint8_t mac[6];
|
||||
esp_read_mac(mac, ESP_MAC_WIFI_STA);
|
||||
s_local_id = mac6_to_u64(mac);
|
||||
|
||||
esp_err_t r = esp_now_init();
|
||||
if (r != ESP_OK) {
|
||||
ESP_LOGE(TAG, "esp_now_init failed: %s", esp_err_to_name(r));
|
||||
return r;
|
||||
}
|
||||
esp_now_register_recv_cb(on_recv);
|
||||
esp_now_register_send_cb(on_send);
|
||||
|
||||
/* Add broadcast peer so esp_now_send to FF:FF:FF:FF:FF:FF works. */
|
||||
esp_now_peer_info_t peer = {0};
|
||||
memcpy(peer.peer_addr, s_broadcast_mac, 6);
|
||||
peer.channel = 0; /* current STA channel */
|
||||
peer.ifidx = WIFI_IF_STA;
|
||||
peer.encrypt = false;
|
||||
r = esp_now_add_peer(&peer);
|
||||
if (r != ESP_OK && r != ESP_ERR_ESPNOW_EXIST) {
|
||||
ESP_LOGW(TAG, "esp_now_add_peer(broadcast) failed: %s", esp_err_to_name(r));
|
||||
}
|
||||
|
||||
/* Start as candidate leader — will step down on receiving lower-id beacon. */
|
||||
s_is_leader = true;
|
||||
s_leader_id = s_local_id;
|
||||
s_last_seen_us = (uint64_t)esp_timer_get_time();
|
||||
|
||||
s_beacon_timer = xTimerCreate("c6_espnow_beacon",
|
||||
pdMS_TO_TICKS(BEACON_PERIOD_MS),
|
||||
pdTRUE, NULL, beacon_timer_cb);
|
||||
if (s_beacon_timer == NULL) {
|
||||
ESP_LOGE(TAG, "xTimerCreate failed");
|
||||
return ESP_ERR_NO_MEM;
|
||||
}
|
||||
xTimerStart(s_beacon_timer, 0);
|
||||
|
||||
ESP_LOGI(TAG, "init done: local_id=%012llx leader=yes(candidate) period=%ums",
|
||||
(unsigned long long)s_local_id, (unsigned)BEACON_PERIOD_MS);
|
||||
return ESP_OK;
|
||||
}
|
||||
|
||||
uint64_t c6_sync_espnow_get_epoch_us(void)
|
||||
{
|
||||
return (uint64_t)((int64_t)esp_timer_get_time() + s_offset_us);
|
||||
}
|
||||
|
||||
bool c6_sync_espnow_is_leader(void) { return s_is_leader; }
|
||||
int64_t c6_sync_espnow_get_offset_us(void) { return s_offset_us; }
|
||||
|
||||
bool c6_sync_espnow_is_valid(void)
|
||||
{
|
||||
if (s_is_leader) return true;
|
||||
uint64_t now = (uint64_t)esp_timer_get_time();
|
||||
return (now - s_last_seen_us) < (VALID_WINDOW_MS * 1000ULL);
|
||||
}
|
||||
|
||||
uint32_t c6_sync_espnow_tx_count(void) { return s_tx_count; }
|
||||
uint32_t c6_sync_espnow_tx_fail(void) { return s_tx_fail; }
|
||||
uint32_t c6_sync_espnow_rx_count(void) { return s_rx_count; }
|
||||
uint32_t c6_sync_espnow_rx_magic_match(void) { return s_rx_magic_match; }
|
||||
|
|
@ -0,0 +1,59 @@
|
|||
/**
|
||||
* @file c6_sync_espnow.h
|
||||
* @brief ESP-NOW based cross-node time-sync — ADR-110 D1 workaround.
|
||||
*
|
||||
* After 4 systematic experiments confirmed the 802.15.4 RX path is broken
|
||||
* in this user-code + IDF v5.4 combination (see WITNESS-LOG-110 §D1), the
|
||||
* cross-node sync claim was unblocked by switching transport from IEEE
|
||||
* 802.15.4 to ESP-NOW (WiFi-based peer-to-peer, runs on the same 2.4 GHz
|
||||
* radio but uses the WiFi MAC layer that ESP-IDF's 802.11 driver fully
|
||||
* supports).
|
||||
*
|
||||
* Trade vs. 802.15.4:
|
||||
* - Loses the "frees WiFi airtime for CSI" property (uses WiFi for sync)
|
||||
* - Gains a known-working RX path on every ESP32 family
|
||||
* - Same API surface (epoch_us, is_valid, is_leader) so call sites that
|
||||
* used to depend on c6_timesync drop in unchanged
|
||||
*
|
||||
* Works on both ESP32-S3 and ESP32-C6 — the cross-node sync becomes a
|
||||
* cross-target feature, not C6-only.
|
||||
*/
|
||||
|
||||
#pragma once
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
#include "esp_err.h"
|
||||
#include <stdint.h>
|
||||
#include <stdbool.h>
|
||||
|
||||
/**
|
||||
* Initialize the ESP-NOW sync module. Must be called AFTER WiFi STA is
|
||||
* connected (ESP-NOW needs the WiFi driver active).
|
||||
*
|
||||
* @return ESP_OK on success.
|
||||
*/
|
||||
esp_err_t c6_sync_espnow_init(void);
|
||||
|
||||
/**
|
||||
* Returns the synced wall-clock estimate in microseconds.
|
||||
* If no leader heard within the timeout, returns the local
|
||||
* esp_timer_get_time() value unchanged (offset = 0).
|
||||
*/
|
||||
uint64_t c6_sync_espnow_get_epoch_us(void);
|
||||
|
||||
bool c6_sync_espnow_is_leader(void);
|
||||
bool c6_sync_espnow_is_valid(void);
|
||||
int64_t c6_sync_espnow_get_offset_us(void);
|
||||
|
||||
/* Counters for the witness harness — exposed for tests/diagnostics. */
|
||||
uint32_t c6_sync_espnow_tx_count(void);
|
||||
uint32_t c6_sync_espnow_tx_fail(void);
|
||||
uint32_t c6_sync_espnow_rx_count(void);
|
||||
uint32_t c6_sync_espnow_rx_magic_match(void);
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif
|
||||
|
|
@ -36,6 +36,7 @@
|
|||
#include "c6_twt.h" /* ADR-110: TWT (no-op stub on S3) */
|
||||
#include "c6_timesync.h" /* ADR-110: 802.15.4 mesh time-sync (no-op on S3) */
|
||||
#include "c6_lp_core.h" /* ADR-110: LP-core hibernation (no-op on S3) */
|
||||
#include "c6_sync_espnow.h" /* ADR-110 D1 workaround: ESP-NOW sync */
|
||||
#ifdef CONFIG_CSI_MOCK_ENABLED
|
||||
#include "mock_csi.h"
|
||||
#endif
|
||||
|
|
@ -254,6 +255,18 @@ void app_main(void)
|
|||
c6_twt_setup_default();
|
||||
#endif
|
||||
|
||||
/* ADR-110 D1 workaround: ESP-NOW cross-node sync. Initialized after
|
||||
* WiFi STA connects (ESP-NOW needs the WiFi driver up). Works on
|
||||
* both S3 and C6 — replaces the broken 802.15.4 RX path in c6_timesync.
|
||||
* Skip on QEMU mock (no real WiFi → no ESP-NOW). */
|
||||
#ifndef CONFIG_CSI_MOCK_SKIP_WIFI_CONNECT
|
||||
esp_err_t espnow_ret = c6_sync_espnow_init();
|
||||
if (espnow_ret != ESP_OK) {
|
||||
ESP_LOGW(TAG, "c6_sync_espnow_init failed: %s (continuing without ESP-NOW sync)",
|
||||
esp_err_to_name(espnow_ret));
|
||||
}
|
||||
#endif
|
||||
|
||||
/* ADR-039: Initialize edge processing pipeline. */
|
||||
edge_config_t edge_cfg = {
|
||||
.tier = g_nvs_config.edge_tier,
|
||||
|
|
|
|||
|
|
@ -76,10 +76,14 @@ for port in PORTS:
|
|||
for L in grep_pattern(text, r'main: ESP32-C6.*Node ID', 2):
|
||||
print(f' banner : {L}')
|
||||
|
||||
# Time-sync init
|
||||
# Time-sync init (802.15.4 path — known broken D1)
|
||||
for L in grep_pattern(text, r'c6_ts:.*(init done|promot|stepping down|tx fail)', 4):
|
||||
print(f' c6_ts : {L}')
|
||||
|
||||
# ESP-NOW sync (D1 workaround, working path)
|
||||
for L in grep_pattern(text, r'c6_espnow:.*(init done|promot|stepping down|tx#\d)', 6):
|
||||
print(f' c6_espnow: {L}')
|
||||
|
||||
# WiFi mode + connect status
|
||||
for L in grep_pattern(text, r'(wifi:mode|wifi:state|Retrying WiFi|got ip|Connected to WiFi)', 6):
|
||||
print(f' wifi : {L}')
|
||||
|
|
|
|||
Loading…
Reference in New Issue