adam/meshcore-stats
1
0
Fork 0
mirror of https://github.com/jorijn/meshcore-stats.git synced 2026-08-08 17:52:48 +02:00
Code Issues Packages Projects Releases Wiki Activity

feat: add telemetry collection for companion and repeater nodes (#24)

Browse Source 
Add environmental telemetry collection (temperature, humidity, barometric
pressure, voltage) from both the repeater node (over LoRa) and companion
node (local serial). Telemetry is stored in the same EAV metrics table
with `telemetry.` prefix.

Key changes:
- Add TELEMETRY_ENABLED feature flag (defaults to OFF)
- Add telemetry-specific timeout/retry settings
- Create shared telemetry.py module with extract_lpp_from_payload()
  and extract_telemetry_metrics() helpers
- Handle MeshCore API dict payload format: {'pubkey_pre': '...', 'lpp': [...]}
- Repeater: store status metrics BEFORE attempting telemetry (LoRa reliability)
- Companion: merge telemetry into single DB write (serial is reliable)
- Telemetry failures do NOT affect circuit breaker state

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Jorijn Schrijvershof
2026-01-06 09:53:15 +01:00
committed by GitHub
parent 5545ce5b28
commit a3015e2209
7 changed files with 303 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/collect_companion.py
+18 -2
View File
@@ -27,6 +27,7 @@ from meshmon.env import get_config
from meshmon import log
from meshmon.meshcore_client import connect_with_lock, run_command
from meshmon.db import init_db, insert_metrics
from meshmon.telemetry import extract_lpp_from_payload, extract_telemetry_metrics
async def collect_companion() -> int:
@@ -93,15 +94,26 @@ async def collect_companion() -> int:
else:
log.error(f"get_time failed: {err}")
# get_self_telemetry
# get_self_telemetry - collect environmental sensor data
# Note: The call happens regardless of telemetry_enabled for device query completeness,
# but we only extract and store metrics if the feature is enabled.
ok, evt_type, payload, err = await run_command(
mc, cmd.get_self_telemetry(), "get_self_telemetry"
)
if ok:
commands_succeeded += 1
log.debug(f"get_self_telemetry: {payload}")
# Extract and store telemetry if enabled
if cfg.telemetry_enabled:
lpp_data = extract_lpp_from_payload(payload)
if lpp_data is not None:
telemetry_metrics = extract_telemetry_metrics(lpp_data)
if telemetry_metrics:
metrics.update(telemetry_metrics)
log.debug(f"Extracted {len(telemetry_metrics)} telemetry metrics")
else:
log.error(f"get_self_telemetry failed: {err}")
# Debug level because not all devices have sensors attached - this is expected
log.debug(f"get_self_telemetry failed: {err}")
# get_custom_vars
ok, evt_type, payload, err = await run_command(
@@ -176,6 +188,10 @@ async def collect_companion() -> int:
summary_parts.append(f"rx={int(metrics['recv'])}")
if "sent" in metrics:
summary_parts.append(f"tx={int(metrics['sent'])}")
# Add telemetry count to summary if present
telemetry_count = sum(1 for k in metrics if k.startswith("telemetry."))
if telemetry_count > 0:
summary_parts.append(f"telem={telemetry_count}")
log.info(f"Companion: {', '.join(summary_parts)}")
scripts/collect_repeater.py
+65 -24
View File
@@ -32,10 +32,10 @@ from meshmon.meshcore_client import (
get_contact_by_name,
get_contact_by_key_prefix,
extract_contact_info,
list_contacts_summary,
)
from meshmon.db import init_db, insert_metrics
from meshmon.retry import get_repeater_circuit_breaker, with_retries
from meshmon.telemetry import extract_lpp_from_payload, extract_telemetry_metrics
async def find_repeater_contact(mc: Any) -> Optional[Any]:
@@ -143,8 +143,10 @@ async def query_repeater_with_retry(
async def collect_repeater() -> int:
"""
Collect data from remote repeater node.
"""Collect data from remote repeater node.
Collects status metrics (battery, uptime, packet counters, etc.) and
optionally telemetry data (temperature, humidity, pressure) if enabled.
Returns:
Exit code (0 = success, 1 = error)
@@ -162,7 +164,8 @@ async def collect_repeater() -> int:
return 0
# Metrics to insert (firmware field names from req_status_sync)
metrics: dict[str, float] = {}
status_metrics: dict[str, float] = {}
telemetry_metrics: dict[str, float] = {}
node_name = "unknown"
status_ok = False
@@ -213,7 +216,7 @@ async def collect_repeater() -> int:
except Exception as e:
log.debug(f"Login not supported: {e}")
# Query status (using _sync version which returns payload directly)
# Phase 1: Status collection (affects circuit breaker)
# Use timeout=0 to let the device suggest timeout, with min_timeout as floor
log.debug("Querying repeater status...")
success, payload, err = await query_repeater_with_retry(
@@ -227,12 +230,12 @@ async def collect_repeater() -> int:
# Insert all numeric fields from status response
for key, value in payload.items():
if isinstance(value, (int, float)):
metrics[key] = float(value)
status_metrics[key] = float(value)
log.debug(f"req_status_sync: {payload}")
else:
log.warn(f"req_status_sync failed: {err}")
# Update circuit breaker
# Update circuit breaker based on status result
if status_ok:
cb.record_success()
log.debug("Circuit breaker: recorded success")
@@ -240,6 +243,51 @@ async def collect_repeater() -> int:
cb.record_failure(cfg.remote_cb_fails, cfg.remote_cb_cooldown_s)
log.debug(f"Circuit breaker: recorded failure ({cb.consecutive_failures}/{cfg.remote_cb_fails})")
# CRITICAL: Store status metrics immediately before attempting telemetry
# This ensures critical data is saved even if telemetry fails
if status_ok and status_metrics:
try:
inserted = insert_metrics(ts=ts, role="repeater", metrics=status_metrics)
log.debug(f"Stored {inserted} status metrics (ts={ts})")
except Exception as e:
log.error(f"Failed to store status metrics: {e}")
return 1
# Phase 2: Telemetry collection (does NOT affect circuit breaker)
if cfg.telemetry_enabled and status_ok:
log.debug("Querying repeater telemetry...")
try:
# Note: Telemetry uses its own retry settings and does NOT
# affect circuit breaker. Status success proves the link is up;
# telemetry failures are likely firmware/capability issues.
telem_success, telem_payload, telem_err = await with_retries(
lambda: cmd.req_telemetry_sync(
contact, timeout=0, min_timeout=cfg.telemetry_timeout_s
),
attempts=cfg.telemetry_retry_attempts,
backoff_s=cfg.telemetry_retry_backoff_s,
name="req_telemetry_sync",
)
if telem_success and telem_payload:
log.debug(f"req_telemetry_sync: {telem_payload}")
lpp_data = extract_lpp_from_payload(telem_payload)
if lpp_data is not None:
telemetry_metrics = extract_telemetry_metrics(lpp_data)
log.debug(f"Extracted {len(telemetry_metrics)} telemetry metrics")
# Store telemetry metrics
if telemetry_metrics:
try:
inserted = insert_metrics(ts=ts, role="repeater", metrics=telemetry_metrics)
log.debug(f"Stored {inserted} telemetry metrics")
except Exception as e:
log.warn(f"Failed to store telemetry metrics: {e}")
else:
log.warn(f"req_telemetry_sync failed: {telem_err}")
except Exception as e:
log.warn(f"Telemetry collection error (continuing): {e}")
except Exception as e:
log.error(f"Error during collection: {e}")
cb.record_failure(cfg.remote_cb_fails, cfg.remote_cb_cooldown_s)
@@ -248,28 +296,21 @@ async def collect_repeater() -> int:
# Print summary
summary_parts = [f"ts={ts}"]
if "bat" in metrics:
bat_v = metrics["bat"] / 1000.0
if "bat" in status_metrics:
bat_v = status_metrics["bat"] / 1000.0
summary_parts.append(f"bat={bat_v:.2f}V")
if "uptime" in metrics:
uptime_days = metrics["uptime"] // 86400
if "uptime" in status_metrics:
uptime_days = status_metrics["uptime"] // 86400
summary_parts.append(f"uptime={int(uptime_days)}d")
if "nb_recv" in metrics:
summary_parts.append(f"rx={int(metrics['nb_recv'])}")
if "nb_sent" in metrics:
summary_parts.append(f"tx={int(metrics['nb_sent'])}")
if "nb_recv" in status_metrics:
summary_parts.append(f"rx={int(status_metrics['nb_recv'])}")
if "nb_sent" in status_metrics:
summary_parts.append(f"tx={int(status_metrics['nb_sent'])}")
if telemetry_metrics:
summary_parts.append(f"telem={len(telemetry_metrics)}")
log.info(f"Repeater ({node_name}): {', '.join(summary_parts)}")
# Write metrics to database
if status_ok and metrics:
try:
inserted = insert_metrics(ts=ts, role="repeater", metrics=metrics)
log.debug(f"Inserted {inserted} metrics to database (ts={ts})")
except Exception as e:
log.error(f"Failed to write metrics to database: {e}")
return 1
return 0 if status_ok else 1