jeremy/rm3100
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
rm3100/logger.py

758 lines
34 KiB
Python
Executable file
Raw Blame History

#!/usr/bin/env python3
"""Log RM3100 magnetometer data over a CH347 USB-I2C adapter.
Run ./setup.sh first to install the udev rule and create the virtualenv, then:
./.venv/bin/python logger.py --duration 60
./.venv/bin/python logger.py --scan-only
The chip samples on its own internal schedule (manual sections 5.7.2, 5.8.2), so
`sample_index` is a grid coordinate. A late read returns the *newer* measurement,
so every miss is detected and written as an explicit placeholder row, which keeps
the index contiguous and the gap visible. The run continues and reports the total
at the end.
Only irreducible facts are written: the sample count, the host clock, and the raw
counts. Chip time, tesla and magnitude are reconstructed on load by capture.py.
"""
import argparse
import csv
import os
import queue
import sys
import textwrap
import threading
import time
from datetime import datetime
import ch347
import rm3100
CSV_FIELDS = ["sample_index", "system_time_unix", "x_raw", "y_raw", "z_raw",
"warning"]
# Mains fundamental. Below twice this the line folds onto signal permanently,
# which is the one error post-processing cannot undo.
MAINS_HZ = 60.0
CONSOLE_REFRESH_S = 0.05
FLUSH_INTERVAL_S = 0.5
# How long to let the writer finish its backlog once sampling has stopped. Far
# longer than a healthy writer needs, so reaching it means rows are lost and the
# run says so.
WRITER_DRAIN_TIMEOUT_S = 30.0
# The sampling loop releases the GIL inside each USB transfer and has to take it
# back, so Python's default 5 ms switch interval becomes the jitter floor: the
# writer can hold the GIL that long, stalling the sampler and inflating the DRDY
# bracket past its budget. Handing off 10x more often costs little throughput,
# the writer being I/O bound.
GIL_SWITCH_INTERVAL_S = 0.0005
# Thread priority. The sampling loop runs on the main thread and is the only
# latency-sensitive part. Lowering the writer needs no privilege and is always
# done: the *relative* priority is what matters, and on Linux nice is per-thread.
# Raising the sampler needs CAP_SYS_NICE, so it is opt-in via --high-priority,
# which fails loudly when the privilege is missing.
SAMPLER_NICE = -10
WRITER_NICE = 10
def restore_ownership(path):
"""Hand a file created under sudo back to the invoking user.
--high-priority needs root and anything root writes stays root-owned, so
the ownership is handed back here. Privilege buys scheduling and nothing else.
"""
if os.geteuid() != 0:
return
uid, gid = os.environ.get("SUDO_UID"), os.environ.get("SUDO_GID")
if uid is None:
return
try:
os.chown(path, int(uid), int(gid) if gid else -1)
except OSError as exc:
print(f"WARNING: could not hand {path} back to uid {uid}: {exc}",
file=sys.stderr)
def set_thread_nice(value):
"""Renice the calling thread. Returns the nice actually in effect, or None.
Linux threads are tasks, so PRIO_PROCESS with a native thread id applies to
just this thread. Elsewhere it may be a no-op or reach the whole process.
Failure is tolerated, priority being an optimisation.
"""
try:
tid = threading.get_native_id()
os.setpriority(os.PRIO_PROCESS, tid, value)
return os.getpriority(os.PRIO_PROCESS, tid)
except (AttributeError, OSError):
return None
# Bounded, so a stalled writer degrades predictably on a long run. Far above the
# depth a healthy writer reaches, so filling it means the writer is wedged. The
# run then ends, which keeps sample_index contiguous over everything written.
QUEUE_MAX = 200_000
_SENTINEL = object()
# Rows carry flags in a `warning` column, space separated, empty when fine. See
# the capture format in the README; the two are independent, so a row can carry
# either or both.
WARN_MISSED = "MISSED" # placeholder: the measurement was never read
WARN_AMBIGUOUS = "AMBIGUOUS" # gap of uncertain length ends here
# How near a half-period the rounding may fall before the count is a coin toss.
AMBIGUITY_MARGIN = 0.25
def parse_args():
p = argparse.ArgumentParser(description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter)
knob = p.add_mutually_exclusive_group()
knob.add_argument("--rate", type=float, default=None,
help="target sample rate in Hz. The cycle count and TMRC "
"are derived from it, which is usually what you want "
"-- the cycle count is a continuous rate knob where "
"TMRC offers only factor-of-two steps")
knob.add_argument("--cycle-count", type=int, default=None,
help="cycle count per axis, setting both the rate and the "
"resolution. Lower is faster but more coarsely "
f"quantised (default: {rm3100.DEFAULT_CYCLE_COUNT})")
p.add_argument("--tmrc", type=lambda s: int(s, 0), default=None,
help="continuous-mode rate register, 0x92 (fastest) to 0x9D "
"(slowest). Default is the fastest, which lets the cycle "
"count set the rate; give one only to sample slower "
"than the cycle count allows")
p.add_argument("--duration", type=float, default=0.0,
help="seconds to log, or 0 to run until Ctrl-C (default: %(default)s)")
p.add_argument("--output", default=None,
help="CSV output path (default: rm3100_<timestamp>.csv)")
p.add_argument("--address", type=lambda s: int(s, 0), default=None,
help="I2C address, skipping the scan (default: autodetect)")
p.add_argument("--bus-speed", type=int, choices=sorted(ch347.SPEEDS),
default=ch347.DEFAULT_SPEED_KHZ,
help="I2C bus speed in kHz. The default cycle count runs near "
"282 Hz, where 100 kHz would spend 42%% of each period on "
"the bus; 750 spends 6%% (default: %(default)s)")
p.add_argument("--calibrate", type=float, default=1.0,
help="seconds of loss-free samples used to measure the true "
"measurement period before recording starts; the run "
"aborts if no clean stretch can be found (default: "
"%(default)s)")
p.add_argument("--note", default=None,
help="free-text label recorded in the capture header, e.g. "
"the supply under test. Keeps the configuration with the "
"data instead of only in the filename")
p.add_argument("--high-priority", action="store_true",
help=f"raise the sampling thread to nice {SAMPLER_NICE}. "
"Needs CAP_SYS_NICE, so run under sudo; the run aborts "
"if the priority cannot be set. Output files are handed "
"back to the invoking user afterwards")
p.add_argument("--scan-only", action="store_true",
help="scan the bus, report what responded, and exit")
return p.parse_args()
def print_plan(cfg, bus_speed, requested_rate, sampler_nice=None):
"""Show how the configuration was derived, so it can be checked not trusted."""
lsb = rm3100.tesla_per_count(cfg.cycle_count) * rm3100.NT_PER_TESLA
dither = rm3100.expected_noise_nt(cfg.cycle_count) / lsb
period = 1.0 / cfg.predicted_hz
bus = i2c_bus_time(bus_speed)
share = bus / period
print("Configuration")
if requested_rate is not None:
print(f" requested {requested_rate:g} Hz")
print(f" cycle count {cfg.cycle_count:,}"
f"{'':<8}1 / (3 x ({cfg.cycle_count}/"
f"{rm3100.COUNTS_PER_SECOND:,.0f} + "
f"{rm3100.AXIS_OVERHEAD_S * 1e6:.1f} us))")
print(f" sensor ceiling {1 / rm3100.sample_period(cfg.cycle_count):.2f} Hz")
print(f" TMRC 0x{cfg.tmrc:02x} = "
f"{rm3100.TMRC_RATES[cfg.tmrc]:g} Hz, {cfg.governed_by} governs")
print(f" predicted rate {cfg.predicted_hz:.2f} Hz "
f"+/-{rm3100.RATE_TOLERANCE:.0%} (nominal-model spread; measured below)")
print(f" resolution {lsb:.2f} nT/LSB dither {dither:.2f} LSB "
"at spec noise")
print(f" duty {cfg.duty:.1%} integration / period")
print(f" bus {bus_speed} kHz {bus * 1e3:.3f} ms/sample "
f"{share:.1%} of the period")
if sampler_nice is not None:
detail = (f"nice {sampler_nice}, writer at {WRITER_NICE}"
if sampler_nice < 0 else
f"nice {sampler_nice}, writer at {WRITER_NICE} "
"(--high-priority raises the sampler, needs sudo)")
print(f" priority {detail}")
for note in cfg.notes:
print(f" note: {note}")
# Nothing below is ever fixed silently: changing a setting the user asked
# for would hide the problem behind a configuration change. Say what is
# wrong and what would fix it, then run what was requested.
warnings = []
# What a low cycle count costs is duty; see rm3100.MIN_CYCLE_COUNT. Dither
# is the more commonly cited worry, so it is reported alongside.
if cfg.cycle_count < rm3100.RECOMMENDED_MIN_CYCLE_COUNT:
reference_duty = (rm3100.integration_time(rm3100.DEFAULT_CYCLE_COUNT)
/ rm3100.sample_period(rm3100.DEFAULT_CYCLE_COUNT))
penalty = (reference_duty / cfg.duty) ** 0.5 - 1.0
warnings.append(
f"cycle count {cfg.cycle_count} is below the recommended "
f"{rm3100.RECOMMENDED_MIN_CYCLE_COUNT}: the per-axis overhead holds "
f"duty to {cfg.duty:.0%} against {reference_duty:.0%} at cycle "
f"count {rm3100.DEFAULT_CYCLE_COUNT}, which costs {penalty:.0%} of "
f"post-filter noise floor. Dither is {dither:.2f} LSB at spec noise "
f"({lsb:.1f} nT/LSB); characterize.py prints the measured sd/LSB "
"per axis, which settles it from the first capture.")
# The worst configuration mistake: TMRC slower than the cycle-count ceiling
# leaves the sensor idle, and idle time buys nothing. Idle is the shortfall
# against the ceiling; the per-axis overhead is active time too.
idle = 1.0 - cfg.predicted_hz * rm3100.sample_period(cfg.cycle_count)
if cfg.governed_by == "TMRC" and idle > 0.2:
# Against the duty the *same rate* would reach on the cycle count alone,
# which is not 100%: the per-axis overhead is a fixed cost per sample, so
# even a free-running sensor gives some of it back at high rates.
best_duty = 1.0 - rm3100.AXES * rm3100.AXIS_OVERHEAD_S * cfg.predicted_hz
warnings.append(
f"TMRC 0x{cfg.tmrc:02x} governs and leaves the sensor idle "
f"{idle:.0%} of each period, holding duty to {cfg.duty:.0%} against "
f"the {best_duty:.0%} this rate reaches on the cycle count alone. "
f"Post-filter noise goes as 1/sqrt(duty), so that is "
f"{(best_duty / cfg.duty) ** 0.5:.2f}x the noise floor for nothing.")
# Every figure above is derived from the rate, so a rate that came back
# different from the one asked for is worth saying out loud.
if (requested_rate is not None and abs(cfg.predicted_hz / requested_rate - 1)
> rm3100.RATE_TOLERANCE):
warnings.append(
f"{requested_rate:g} Hz was requested but this configuration runs "
f"at {cfg.predicted_hz:.2f} Hz.")
# Below 2x mains the line folds onto signal, and no filter undoes an alias.
if cfg.predicted_hz < 2 * MAINS_HZ:
alias = abs(MAINS_HZ - round(MAINS_HZ / cfg.predicted_hz) * cfg.predicted_hz)
warnings.append(
f"Nyquist is {cfg.predicted_hz / 2:.1f} Hz, below {MAINS_HZ:g} Hz "
f"mains: interference folds to {alias:.2f} Hz and cannot be removed "
"afterwards. Sampling faster and decimating gives the same noise "
"floor with the mains line still visible.")
if cfg.cycle_count > rm3100.MAX_SPEC_CYCLE_COUNT:
warnings.append(
f"cycle count {cfg.cycle_count:,} is past the {rm3100.MAX_SPEC_CYCLE_COUNT} "
"where Table 3-1 ends, so the spec noise and gain above are "
"extrapolated, not specified.")
if share > 0.5:
faster = [s for s in sorted(ch347.SPEEDS) if i2c_bus_time(s) / period < 0.25]
fix = f"; {faster[0]} kHz would fit" if faster else ""
warnings.append(f"the bus needs {share:.0%} of every period{fix}.")
for text in warnings:
print(textwrap.fill(text, width=79, initial_indent=" WARNING: ",
subsequent_indent=" "), file=sys.stderr)
def find_sensor(bus, address):
"""Locate the RM3100, or exit with wiring guidance."""
if address is not None:
print(f"Using I2C address 0x{address:02x} (scan skipped)")
return address
candidates = [a for a in rm3100.RM3100.ADDRESSES if bus.probe(a)]
if not candidates:
print("No RM3100 responded at 0x20-0x23.", file=sys.stderr)
others = bus.scan()
if others:
print("Other devices on the bus: "
+ ", ".join(f"0x{a:02x}" for a in others), file=sys.stderr)
else:
print("Nothing responded anywhere on the bus. Check, in order:\n"
" - I2CEN tied high (otherwise the chip stays in SPI mode)\n"
" - AVDD/VDD powered, not just DVDD\n"
" - SDA/SCL not swapped\n"
" - SDA and SCL pull-up resistors present", file=sys.stderr)
sys.exit(1)
if len(candidates) > 1:
print("Multiple devices responded at "
+ ", ".join(f"0x{a:02x}" for a in candidates)
+ "; use --address to pick one.", file=sys.stderr)
sys.exit(1)
print(f"Found a device at 0x{candidates[0]:02x}")
return candidates[0]
def start_sensor(sensor, cycle_count, tmrc):
"""Identify and configure the sensor, printing each step. Returns REVID."""
revid = sensor.revid()
if revid == rm3100.EXPECTED_REVID:
print(f"REVID 0x{revid:02x}, RM3100 confirmed")
else:
print(f"WARNING: REVID 0x{revid:02x}, expected "
f"0x{rm3100.EXPECTED_REVID:02x}", file=sys.stderr)
sensor.set_cycle_counts(cycle_count)
readback = sensor.get_cycle_counts()
if readback != (cycle_count,) * 3:
print(f"ERROR: cycle count read back as {readback}, expected "
f"{(cycle_count,) * 3}", file=sys.stderr)
sys.exit(1)
lsb_nt = rm3100.tesla_per_count(cycle_count) * rm3100.NT_PER_TESLA
print(f"Cycle counts set to {readback}, 1 LSB = {lsb_nt:.2f} nT")
# Raises if DRC1 did not take; exactly-once sampling depends on it.
sensor.configure()
sensor.set_rate(tmrc)
sensor.start_cmm()
print("Continuous measurement mode started")
return revid
def write_header(handle, meta):
for key, value in meta.items():
handle.write(f"# {key}: {value}\n")
def writer_thread(q, path, meta, stats):
"""Drain samples to CSV and drive the console, off the sampling thread."""
# Stand aside for the sampler: this thread is not latency-sensitive.
set_thread_nice(WRITER_NICE)
lsb_nt = float(meta["tesla_per_count"]) * rm3100.NT_PER_TESLA
with open(path, "w", newline="") as handle:
restore_ownership(path)
write_header(handle, meta)
out = csv.writer(handle)
out.writerow(CSV_FIELDS)
last_print = 0.0
last_flush = time.monotonic()
while True:
item = q.get()
if item is _SENTINEL:
break
index, system_time, cx, cy, cz, warning = item
# 6 decimals is microsecond resolution on an epoch value, far finer
# than the ~1 ms bracket uncertainty. Placeholders carry zeros rather
# than blanks: the warning column already says the row has no data,
# so x/y/z stay strictly integer and trivial to parse.
out.writerow([index, f"{system_time:.6f}",
0 if cx is None else cx,
0 if cy is None else cy,
0 if cz is None else cz, warning])
stats["rows"] += 1
now = time.monotonic()
if now - last_flush >= FLUSH_INTERVAL_S:
handle.flush()
last_flush = now
if now - last_print >= CONSOLE_REFRESH_S and cx is not None:
# Placeholders carry no field values, so the display holds the
# last real reading.
last_print = now
x, y, z = cx * lsb_nt, cy * lsb_nt, cz * lsb_nt
print(f"\r{stats['rows']:,} samples ({stats['missed']} missed)"
f" | X {x:+10.1f} | Y {y:+10.1f} | Z {z:+10.1f}"
f" | T {(x * x + y * y + z * z) ** 0.5:10.1f} nT",
end="", flush=True)
handle.flush()
def i2c_bus_time(bus_speed_khz):
"""Seconds of I2C traffic the bus carries per sample.
A combined register read of n payload bytes clocks n+3 bytes (write address,
register, read address, payload) at 9 bit-times each, 8 data plus ACK, and
spends roughly a bit-time on each START and STOP. One sample costs a STATUS
poll of 1 payload byte plus a results read of 9.
This is the irreducible traffic, and the figure worth reading against the
sample period. The loop polls continuously while waiting for DRDY, so raw
bus occupancy approaches 100%.
"""
bits = 0
for payload in (1, 9):
bits += (payload + 3) * 9 + 3 # 2 STARTs and a STOP
return bits / (bus_speed_khz * 1000.0)
def calibrate_period(sensor, dt_nominal, seconds, attempts=3):
"""Measure the true measurement period from a clean stretch of samples.
Miss detection needs the real period. The table value is a nominal model,
out by up to ~6% on this unit, which is enough to miscount grid points
inside a bracket and slip the sample index.
Least-squares slope of read time against index, which over one second pins
the period to roughly 0.03%, far finer than the resolution needed to tell k
grid points from k+1.
Requires a stretch with no miss, since an interval spanning one is a multiple
of the period. Returns None when no clean stretch is available, which is
itself the answer: the rate is not sustainable.
Also returns the mean host cost of one sample's traffic, a DRDY poll plus a
results read, timed here for free from the transactions being performed.
"""
poll_ready, read_raw = sensor.poll_ready, sensor.read_raw
monotonic = time.monotonic
# Bootstrap the period from observation rather than the TMRC table. When the
# cycle count governs, the table value is out by a large factor: at cc=400
# with TMRC 0x92 it says 1.67 ms against a real 13.5 ms, and a threshold
# built on it rejects every interval. The median of a handful of raw
# intervals is robust to the occasional stall and seeds the real fit.
probe = []
clear = monotonic()
deadline = clear + max(seconds, 0.25)
while monotonic() < deadline and len(probe) < 24:
ready_now, stamp, _ = poll_ready()
if not ready_now:
continue
read_raw()
probe.append(stamp)
if len(probe) >= 4:
gaps = sorted(b - a for a, b in zip(probe, probe[1:]))
dt_nominal = gaps[len(gaps) // 2]
for _ in range(attempts):
times = []
poll_cost = read_cost = 0.0
polls = 0
clear = monotonic()
deadline = clear + seconds
clean = True
while monotonic() < deadline:
before = monotonic()
ready_now, after, _ = poll_ready()
poll_cost += monotonic() - before
polls += 1
if not ready_now:
clear = after
continue
ready = after
if ready - clear >= dt_nominal: # conservative: nominal is short
clean = False
break
# Timed from here. `ready` is the instant the STATUS reply landed
# on the wire, so it carries the tail of the poll transaction.
before = monotonic()
read_raw()
read_cost += monotonic() - before
times.append(ready)
clear = ready
n = len(times)
if not clean or n < 8:
continue
# slope of t against i for i = 0..n-1, where Sxx = n(n^2-1)/12.
mean_i = (n - 1) / 2.0
mean_t = sum(times) / n
sxy = sum((i - mean_i) * (t - mean_t) for i, t in enumerate(times))
return (sxy / (n * (n * n - 1) / 12.0),
poll_cost / max(polls, 1) + read_cost / n)
return None, None
def sample_loop(sensor, q, duration, dt_nominal, stats):
"""Read every measurement, recording placeholders for any that are lost.
Miss detection uses the **DRDY bracket**: the span between the last poll
showing DRDY clear and the poll showing it set. The bracket is exact. A
results read is what clears DRDY, so everything earlier has been read;
measurements complete one period apart, so a bracket narrower than a period
holds at most one completion, and DRDY going high proves it held at least
one. Host stalls push the read-to-read interval well past a period, and this
is unaffected by them.
The timestamp recorded per sample is the midpoint of that bracket, the best
estimate available without a hardware DRDY line.
Ends the run if the queue fills, which keeps sample_index contiguous and so
keeps every row written a valid chip-time grid coordinate.
"""
read_raw = sensor.read_raw
poll_ready = sensor.poll_ready
monotonic = time.monotonic
put = q.put_nowait
# DRDY may already be set from whatever ran before; BIST zeroes the result
# registers and leaves it high. Discard one reading so sample 0 is fresh.
if poll_ready()[0]:
read_raw()
deadline = monotonic() + duration if duration > 0 else float("inf")
index = 0
# Bracket lower bound: the most recent moment DRDY was seen clear.
clear_mono, clear_wall = monotonic(), time.time()
# dt_nominal here is the *calibrated* period from calibrate_period(), not
# the table value. Keep refining it from clean intervals so the estimate
# follows the oscillator's thermal drift.
dt_est = dt_nominal
previous_mono = previous_wall = None
DT_SMOOTHING = 0.02
while True:
if monotonic() >= deadline:
return
# The stamps come back with the STATUS reply itself, taken the instant
# it landed.
ready, ready_mono, ready_wall = poll_ready()
if not ready:
clear_mono, clear_wall = ready_mono, ready_wall
continue
# Monotonic drives detection so an NTP step cannot fake a miss; the
# wall clock is recorded so a real NTP correction stays visible.
bracket = ready_mono - clear_mono
if bracket > stats["max_bracket"]:
stats["max_bracket"] = bracket
# Two stages, because the two questions have different best answers.
# "Did we lose any?" is settled rigorously by the bracket, above. "How
# many?" is better answered by the interval since the previous accepted
# sample: each accepted read sits on a grid point, so that interval is
# very close to an exact multiple of the period and rounding recovers
# the multiple. The bracket reaches back only to the last poll that saw
# DRDY clear, which loses track of where the grid sits.
lost = 0
uncertain = False
if bracket >= dt_est and previous_mono is not None:
periods = (ready_mono - previous_mono) / dt_est
lost = max(0, round(periods) - 1)
# Uncertainty is a property of the gap: one rounding to zero losses
# can still be a coin toss, with no placeholder to carry the flag.
uncertain = abs(periods - round(periods)) > AMBIGUITY_MARGIN
if uncertain:
stats["ambiguous"] += 1
elif previous_mono is not None:
# A clean interval is exactly one period, so it calibrates dt_est.
# Only clean ones qualify: an interval spanning a miss is a multiple.
dt_est += (ready_mono - previous_mono - dt_est) * DT_SMOOTHING
if lost:
stats["missed"] += lost
# Placeholders sit on the grid, one period apart from the previous
# accepted sample, which is where the lost measurements completed
# and what keeps the rate fit straight.
flags = (f"{WARN_MISSED} {WARN_AMBIGUOUS}" if uncertain
else WARN_MISSED)
for k in range(lost):
try:
put((index, previous_wall + dt_est * (k + 1),
None, None, None, flags))
except queue.Full:
stats["truncated"] = True
return
index += 1
sample_wall = (clear_wall + ready_wall) / 2.0
(cx, cy, cz), _, _ = read_raw()
try:
# An uncertain gap that produced no placeholder still has to be
# flagged, so it rides on the real sample that ends it.
put((index, sample_wall, cx, cy, cz,
WARN_AMBIGUOUS if uncertain and not lost else ""))
except queue.Full:
stats["truncated"] = True
return
index += 1
previous_mono, previous_wall = ready_mono, sample_wall
# The read just cleared DRDY, so this is a known-clear instant.
clear_mono, clear_wall = ready_mono, ready_wall
def main():
args = parse_args()
sys.setswitchinterval(GIL_SWITCH_INTERVAL_S)
sampler_nice = None
if args.high_priority:
sampler_nice = set_thread_nice(SAMPLER_NICE)
if sampler_nice is None:
sys.exit(
f"--high-priority needs CAP_SYS_NICE to set nice "
f"{SAMPLER_NICE}, and this process does not have it.\n"
"Re-run under sudo, using the venv interpreter by absolute "
"path:\n"
f" sudo {sys.executable} {' '.join(sys.argv)}\n"
"Or drop the flag: the writer thread already steps aside, "
f"which is the half that needs no privilege.")
else:
try:
sampler_nice = os.getpriority(os.PRIO_PROCESS,
threading.get_native_id())
except (AttributeError, OSError):
pass
if args.cycle_count is not None and not 1 <= args.cycle_count <= 0xFFFF:
sys.exit(f"--cycle-count {args.cycle_count} outside 1..65535")
if args.rate is not None and args.rate <= 0:
sys.exit(f"--rate {args.rate:g} must be positive")
if args.tmrc is not None and args.tmrc not in rm3100.TMRC_RATES:
sys.exit(f"--tmrc 0x{args.tmrc:02x} is not a valid rate register value")
cfg = rm3100.plan(rate_hz=args.rate, cycle_count=args.cycle_count,
tmrc=args.tmrc)
args.cycle_count, args.tmrc = cfg.cycle_count, cfg.tmrc
try:
bus = ch347.CH347I2C(ch347.SPEEDS[args.bus_speed])
except IOError as exc:
sys.exit(str(exc))
with bus:
print(f"CH347 adapter opened, I2C at {args.bus_speed} kHz")
if args.scan_only:
found = bus.scan()
print("Devices found: " + ", ".join(f"0x{a:02x}" for a in found)
if found else "No devices responded on the bus.")
return 0
address = find_sensor(bus, args.address)
sensor = rm3100.RM3100(bus, address)
try:
revid = start_sensor(sensor, args.cycle_count, args.tmrc)
except IOError as exc:
sys.exit(str(exc))
print()
print_plan(cfg, args.bus_speed, args.rate, sampler_nice)
print()
nominal_rate = cfg.predicted_hz
# Miss detection, placeholder counting and the sample-index grid all
# depend on the real period, so measure it first.
dt, host_cost = calibrate_period(sensor, 1.0 / nominal_rate,
args.calibrate)
if dt is None:
sensor.stop_cmm()
sys.exit(
f"Could not find {args.calibrate:g} s of loss-free samples at "
f"{nominal_rate:.1f} Hz.\n"
"Without a clean stretch the true period cannot be measured, so "
"misses cannot be\ncounted reliably and the sample index would "
"not track chip time.\n"
"Lower the rate (higher --tmrc) or raise --bus-speed.")
# Against the predicted rate, which is what the configuration aimed
# for once the cycle count governs.
print(f"Calibrated period {dt * 1e3:.4f} ms = {1 / dt:.4f} Hz "
f"({(1 / dt) / cfg.predicted_hz - 1:+.2%} vs predicted)")
# Whether the host is the constraint is a measurement. It costs a
# near-constant ~0.9 ms per sample, so it dominates at short periods
# and disappears at long ones.
share = host_cost / dt
margin = ("little margin, expect misses under load" if share > 0.5
else "modest margin" if share > 0.25
else "ample margin")
print(f"Host cost {host_cost * 1e3:.3f} ms/sample "
f"({share:.1%} of the period, {margin})")
meta = {
"rm3100_capture": 1,
# Whichever of the two ceilings governs.
"nominal_rate_hz": nominal_rate,
"tmrc_nominal_hz": rm3100.TMRC_RATES[args.tmrc],
"tmrc": f"0x{args.tmrc:02x}",
"cycle_count": args.cycle_count,
# repr() so the constant round-trips through float64 exactly.
"tesla_per_count": repr(rm3100.tesla_per_count(args.cycle_count)),
"i2c_address": f"0x{address:02x}",
"bus_speed_khz": args.bus_speed,
"revid": f"0x{revid:02x}",
# What miss detection actually used. capture.py fits the whole run,
# so this figure lives only here.
"calibrated_period_s": repr(dt),
}
if args.note:
# Newlines would break the one-line-per-key header format.
meta["note"] = " ".join(args.note.split())
path = args.output or datetime.now().strftime("rm3100_%Y%m%d_%H%M%S.csv")
print(f"Logging to {path}, Ctrl-C to stop\n")
q = queue.Queue(maxsize=QUEUE_MAX)
stats = {"rows": 0, "missed": 0, "ambiguous": 0, "max_bracket": 0.0,
"truncated": False}
writer = threading.Thread(target=writer_thread,
args=(q, path, meta, stats), daemon=True)
writer.start()
try:
sample_loop(sensor, q, args.duration, dt, stats)
except KeyboardInterrupt:
pass
finally:
q.put(_SENTINEL)
writer.join(timeout=WRITER_DRAIN_TIMEOUT_S)
drained = not writer.is_alive()
print()
try:
sensor.stop_cmm()
print("Continuous measurement mode stopped")
except IOError as exc:
print(f"WARNING: could not stop CMM: {exc}", file=sys.stderr)
print(f"Wrote {stats['rows']} samples to {path}")
# How close the run came to losing a measurement: the number to watch
# before committing to a long run. Quoted against the calibrated period,
# which is the threshold enforced.
print(f"Worst DRDY bracket {stats['max_bracket'] * 1e3:.2f} ms of "
f"{dt * 1e3:.2f} ms allowed "
f"({stats['max_bracket'] / dt * 100:.0f}% of margin used)")
# Each of these leaves the capture usable but compromised in a way the
# file alone conceals, so each is said out loud and each makes the exit
# status non-zero.
failed = False
if stats["truncated"]:
failed = True
print("\nWARNING: recording stopped early. The writer could not "
"keep up and the\nqueue filled, so the run ended to keep "
"sample_index contiguous.\nEverything written is valid.",
file=sys.stderr)
if not drained:
failed = True
# The writer is a daemon thread, so anything still queued dies with
# the process. Say so, since a short tail is invisible in the file.
print(f"\nWARNING: the writer did not finish within "
f"{WRITER_DRAIN_TIMEOUT_S:g} s, so the last\n"
f"{q.qsize():,} queued row(s) were dropped. The file is valid "
"up to where it stops.", file=sys.stderr)
if stats["ambiguous"]:
failed = True
print(f"\nWARNING: {stats['ambiguous']:,} gap(s) could not be "
"counted confidently. The interval fell near a\nhalf-period, "
"so the number of lost measurements is a guess and "
"sample_index\nmay have slipped from there on. Those rows "
f"carry {WARN_AMBIGUOUS} in the\nwarning column. Re-record "
"before using this capture's time axis.",
file=sys.stderr)
if stats["missed"]:
failed = True
pct = stats["missed"] / max(stats["rows"], 1) * 100
print(f"\nWARNING: {stats['missed']:,} measurement(s) were lost "
f"({pct:.3f}% of rows), flagged {WARN_MISSED}.\n"
"The gaps are explicit, so the sample index still tracks chip "
"time, and those\nrows carry no field data. Lower the rate "
"(higher --tmrc) or raise --bus-speed\nto remove them.",
file=sys.stderr)
return 1 if failed else 0
return 0
if __name__ == "__main__":
sys.exit(main())
Reference in a new issue View git blame Copy permalink