756 lines
41 KiB
C++
756 lines
41 KiB
C++
#include "FrameDecoder.h"
|
|
|
|
#include <cmath>
|
|
|
|
namespace udpscope {
|
|
|
|
/** Fallback cycle period before the first inter-packet gap is known. */
|
|
static constexpr double kDefaultDt = 1.0e-3;
|
|
|
|
/**
|
|
* How far a chained burst prediction may sit from where arrival time says it
|
|
* should be before the chain is abandoned and time is re-anchored on arrival.
|
|
*
|
|
* This is a backstop, not the primary mechanism: the packet counter normally
|
|
* accounts for lost datagrams exactly, so the prediction and arrival agree.
|
|
* It catches what the counter cannot describe — a producer restart (the
|
|
* counter returns to zero), a counter that never advances, and a declared
|
|
* sampling rate that does not match the producer's real one. A kernel draining
|
|
* a backlog of queued datagrams can legitimately put the prediction a couple of
|
|
* hundred milliseconds from arrival, so the threshold sits well clear of that.
|
|
* Same value and same reasoning as ClockOffset::kRecalibThresholdS.
|
|
*/
|
|
static constexpr double kBurstResyncThresholdS = 0.5;
|
|
|
|
/**
|
|
* Narrowest a burst may be drawn, as a fraction of its nominal width, while a
|
|
* leading timeline is being pulled back. Only a floor: the squeeze is normally
|
|
* proportional to the excess and removes it in a single burst. See the sole use
|
|
* site.
|
|
*/
|
|
static constexpr double kMinBleedFactor = 0.05;
|
|
|
|
/**
|
|
* Largest share of the wall time elapsed since a signal's previous burst that
|
|
* that signal's next burst may advance its own timeline by, while a lead is
|
|
* being pulled back.
|
|
*
|
|
* This, and not kMinBleedFactor, is what makes a lead converge. A fraction of
|
|
* the NOMINAL burst width cannot: the floor still advances the timeline by
|
|
* kMinBleedFactor * nominal per packet while the wall advances one packet
|
|
* interval, so it diverges outright whenever nominal exceeds
|
|
* (1 / kMinBleedFactor) packet intervals — a declared SamplingRate of 30 against
|
|
* a producer really flushing 10 samples at 1 kHz put the trace 667 s ahead after
|
|
* 1000 s of stream. Measuring the allowance against elapsed WALL time instead
|
|
* bounds the advance below the wall's own advance for any declared rate, so the
|
|
* lead strictly falls whatever the config says. Any fraction under 1 converges;
|
|
* a half both converges quickly and leaves the burst visibly compressed rather
|
|
* than frozen.
|
|
*/
|
|
static constexpr double kWallBleedFraction = 0.5;
|
|
|
|
/**
|
|
* A backward jump in producer hrt larger than this is a producer RESTART; a
|
|
* smaller one is a reordered datagram.
|
|
*
|
|
* The two need opposite handling — a reorder must leave the hrt reference
|
|
* untouched (its interval was already counted by the packet that overtook it),
|
|
* a restart must rebase onto the new epoch or the signal never advances again —
|
|
* and nothing but the size of the jump distinguishes them. A second of producer
|
|
* time is orders of magnitude more than any reordering window a UDP path can
|
|
* produce (a few packet intervals) and orders of magnitude less than a restart,
|
|
* which drops hrt from the producer's whole uptime back to near zero.
|
|
*
|
|
* Deliberately NOT kBurstResyncThresholdS: that one asks how far a WALL-clock
|
|
* prediction may sit from arrival, a different quantity in a different clock
|
|
* that happens to be tuned for delivery jitter. Sharing the number would couple
|
|
* two unrelated tunings.
|
|
*/
|
|
static constexpr double kProducerRestartS = 1.0;
|
|
|
|
/**
|
|
* The same reorder/restart question in the DECLARED-rate branch, which has no
|
|
* producer clock to ask and must read it off the packet counter instead: a
|
|
* counter this far behind the front, or further, is a restart; anything nearer
|
|
* is a reordered datagram.
|
|
*
|
|
* Needed for the same reason kProducerRestartS is, and it is not enough to lean
|
|
* on the arrival backstop. Both events make the wrapped gap enormous and both
|
|
* are rejected there — so the backstop cannot tell them apart, and whichever
|
|
* behaviour the counter update takes unconditionally is wrong for one of them.
|
|
* Rolling the counter back on a reorder gives the NEXT packet a gap of dist+1,
|
|
* an inflated `lost`, and a prediction wrong by dist burst widths that still
|
|
* lands inside the backstop and is accepted: measured +10 ms at distance 1,
|
|
* +200 ms at distance 20 (10 samples per 10 ms), never bled off, since an
|
|
* accepted chain is self-consistent and the squeeze never fires. Refusing to
|
|
* roll it back at all instead strands a restarted producer, whose counter
|
|
* begins again from 1: every later packet reads as a reorder and re-anchors on
|
|
* arrival, i.e. the sawtooth, until the new counter climbs past the old one.
|
|
*
|
|
* Both failure modes are bounded by this constant. 64 is far beyond any
|
|
* reordering a UDP path produces (a few packet intervals) and far below any
|
|
* counter a producer accumulates before restarting, so both bounds are slack.
|
|
* The one case it cannot separate is a producer that restarts having sent fewer
|
|
* than 64 updates; that costs at most 64 arrival-anchored bursts and then heals
|
|
* itself.
|
|
*/
|
|
static constexpr uint32_t kMaxReorderPackets = 64u;
|
|
|
|
/**
|
|
* The declared sampling rate, or 0 when there is none to trust.
|
|
*
|
|
* samplingRate arrives unvalidated from a signal descriptor on the wire. A
|
|
* malformed +inf reaches the reciprocal as dt == 0, which makes a burst's
|
|
* nominal width zero and the proportional squeeze compute 0.0/0.0 — and a NaN
|
|
* factor is not caught by the floor, since every comparison against NaN is
|
|
* false, so the whole burst is emitted as NaN. Rejecting it at the boundary
|
|
* costs one test and removes the entire class.
|
|
*/
|
|
static double DeclaredRate(double samplingRate) {
|
|
return (std::isfinite(samplingRate) && samplingRate > 0.0) ? samplingRate
|
|
: 0.0;
|
|
}
|
|
|
|
void FrameDecoder::setSignals(const std::vector<SignalMeta>& signals) {
|
|
signals_ = signals;
|
|
state_.assign(signals_.size(), SigState{});
|
|
hrtFit_.reset();
|
|
}
|
|
|
|
void FrameDecoder::reset() {
|
|
state_.assign(signals_.size(), SigState{});
|
|
hrtFit_.reset();
|
|
}
|
|
|
|
void FrameDecoder::beginFrame(const FrameView& f) {
|
|
if (f.hrt != 0u) { hrtFit_.add(f.hrt, f.recvTime); }
|
|
}
|
|
|
|
bool FrameDecoder::packetBurst(uint32_t idx, uint32_t nElems, double wallNow,
|
|
std::vector<double>& tsOut) {
|
|
SigState& st = state_[idx];
|
|
if (!st.lastPacketValid || wallNow <= st.lastPacketWall) {
|
|
/* No previous arrival to span from, or time went backwards. Remember
|
|
* this one and drop the samples rather than store them at made-up
|
|
* spacing. */
|
|
st.lastPacketWall = wallNow;
|
|
st.lastPacketValid = true;
|
|
return false;
|
|
}
|
|
|
|
const double dt = (wallNow - st.lastPacketWall) / static_cast<double>(nElems);
|
|
tsOut.resize(nElems);
|
|
for (uint32_t e = 0; e < nElems; e++) {
|
|
tsOut[e] = st.lastPacketWall + static_cast<double>(e + 1u) * dt;
|
|
}
|
|
st.lastPacketWall = wallNow;
|
|
return true;
|
|
}
|
|
|
|
bool FrameDecoder::timestamps(const FrameView& f, uint32_t idx,
|
|
std::vector<double>& tsOut) {
|
|
tsOut.clear();
|
|
if (idx >= signals_.size() || idx >= f.numSignals ||
|
|
f.counts == nullptr || f.values == nullptr) {
|
|
return false;
|
|
}
|
|
|
|
const SignalMeta& d = signals_[idx];
|
|
const uint32_t nElems = f.counts[idx];
|
|
if (nElems == 0u) { return false; }
|
|
|
|
const double wallNow = f.recvTime;
|
|
SigState& st = state_[idx];
|
|
|
|
/* A repeated counter is a duplicated datagram — the same update arriving
|
|
* twice because the host joined the multicast group on two interfaces, say.
|
|
* The C client only de-duplicates fragments, so an unfragmented update
|
|
* reaches us intact both times; emitting it again would double the values
|
|
* and advance the timeline by a burst that never existed. Counter zero is
|
|
* excluded because a producer that never sets one leaves it there.
|
|
*
|
|
* Keyed on counterValid, not lastEmittedValid: rules 1 and 2 are exposed to
|
|
* the same double delivery and would otherwise plot every array twice, since
|
|
* neither of them ever joins rule 3's emitted chain. */
|
|
if (st.counterValid && f.counter != 0u && f.counter == st.lastCounter) {
|
|
return false;
|
|
}
|
|
|
|
/* hasTimeSignal() bounds the index against the FRAME's signal count, but
|
|
* the time signal's type code is read from our own table, whose size is
|
|
* independent — a frame carrying more signals than the installed table
|
|
* (briefly possible after a CONFIG change) would otherwise read past it. */
|
|
const bool hasTimeSig = d.hasTimeSignal(f.numSignals) &&
|
|
d.timeSignalIdx < signals_.size();
|
|
const uint32_t tIdx = hasTimeSig ? d.timeSignalIdx : 0u;
|
|
const double tScale = hasTimeSig
|
|
? TimeSignalScale(signals_[tIdx].typeCode)
|
|
: 1.0e-6;
|
|
|
|
/* Rule 1: one stamp per element, straight from the time signal. */
|
|
if (d.timeMode == kTimeFullArray && hasTimeSig &&
|
|
f.counts[tIdx] >= nElems && f.values[tIdx] != nullptr) {
|
|
const double* tv = f.values[tIdx];
|
|
const double t0 = tv[0] * tScale;
|
|
(void) st.offset.map(t0, wallNow);
|
|
const double base = st.offset.offset();
|
|
tsOut.resize(nElems);
|
|
for (uint32_t e = 0; e < nElems; e++) {
|
|
tsOut[e] = base + tv[e] * tScale;
|
|
}
|
|
/* Only so the duplicate-datagram guard above has something to compare
|
|
* against; nothing in this rule reads it back. */
|
|
st.lastCounter = f.counter;
|
|
st.counterValid = true;
|
|
return true;
|
|
}
|
|
|
|
/* Rule 2: anchor from the time signal, spread by the sampling rate. */
|
|
if ((d.timeMode == kTimeFirstSample || d.timeMode == kTimeLastSample) &&
|
|
hasTimeSig && f.counts[tIdx] >= 1u && f.values[tIdx] != nullptr) {
|
|
const double prodSec = f.values[tIdx][0] * tScale;
|
|
|
|
/* An anchor that has not advanced is the same reorder-or-restart
|
|
* question rule 3 answers from hrt, asked of the time signal instead,
|
|
* and separated by the same threshold for the same reason: nothing but
|
|
* the size of the backward step tells them apart.
|
|
*
|
|
* A reordered datagram is DROPPED rather than emitted. Its anchor is
|
|
* genuine producer time, so emitting it would place the whole array
|
|
* before stamps already handed out — measured 7 ms backwards on a
|
|
* single swapped anchor — and this rule has no emitted-timeline chain to
|
|
* clamp against, so there is nowhere honest to put it. packetBurst()
|
|
* makes the same choice for the same reason: drop rather than store at
|
|
* made-up positions. Dropping also protects the NEXT packet, which would
|
|
* otherwise divide a one-packet anchor difference by a counter gap of
|
|
* two and halve its spacing.
|
|
*
|
|
* A restart must instead rebase, or prodSec sits below prevAnchorProdSec
|
|
* for the rest of the session: every later packet reads as a reorder,
|
|
* the anchor pair never advances, and this rule runs on a period
|
|
* measured before the restart until the scope is restarted too. */
|
|
if (st.prevAnchorValid && prodSec <= st.prevAnchorProdSec) {
|
|
if ((st.prevAnchorProdSec - prodSec) <= kProducerRestartS) {
|
|
return false;
|
|
}
|
|
st.offset.reset();
|
|
st.prevAnchorValid = false;
|
|
}
|
|
|
|
const double anchor = st.offset.map(prodSec, wallNow);
|
|
const double rate = DeclaredRate(d.samplingRate);
|
|
double dt = (rate > 0.0) ? (1.0 / rate) : 0.0;
|
|
|
|
/* No rate declared. UDPSourceSession.cpp:522 leaves dt at zero here,
|
|
* which stacks every element of the array on one instant — harmless for
|
|
* a host-local consumer that only stores them, but this scope's ring,
|
|
* decimator and trigger all require a signal's stamps to increase, and a
|
|
* plot of N points at one X is not a trace.
|
|
*
|
|
* The spread is recoverable without a rate: consecutive anchors come
|
|
* from the time signal, so their difference is the burst's true duration
|
|
* in producer seconds, measured on the producer's own clock rather than
|
|
* on arrival — immune to the bursty delivery that corrupts everything
|
|
* arrival-derived. Divide by the counter gap for the same reason rule 3
|
|
* does: a lost datagram widens the anchor difference without widening
|
|
* the array.
|
|
*
|
|
* Which array, though, is a question of which end is anchored. For
|
|
* LAST_SAMPLE the anchors bracket THIS packet's elements, so the divisor
|
|
* is nElems; for FIRST_SAMPLE they bracket the PREVIOUS packet's, so it
|
|
* is that packet's count. Accumulate mode flushes on a timer, so the
|
|
* count really does vary between packets — using the wrong one against a
|
|
* 10,10,2,10,20 pattern gave 5x, 0.2x and 0.5x the true period and one
|
|
* backward step of 3 ms.
|
|
*
|
|
* Two packets cannot always be measured — the first of a run has no
|
|
* predecessor, and neither does the first after a restart. Rather than
|
|
* stack the whole array on one instant, the very defect this paragraph
|
|
* exists to remove, reuse the last period actually measured, exactly as
|
|
* the hrt branch reuses lastHrtDt. Only the genuine first packet stacks,
|
|
* and only until the second arrives. */
|
|
if (!(dt > 0.0) && nElems > 1u) {
|
|
const uint32_t divisor = (d.timeMode == kTimeLastSample)
|
|
? nElems : st.prevAnchorCount;
|
|
const uint32_t rawGap = f.counter - st.lastCounter;
|
|
const bool fwdGap = (f.counter != 0u) && st.counterValid &&
|
|
(rawGap != 0u) && (rawGap < 0x80000000u);
|
|
if (st.prevAnchorValid && divisor > 0u) {
|
|
dt = (prodSec - st.prevAnchorProdSec) /
|
|
(static_cast<double>(divisor) *
|
|
static_cast<double>(fwdGap ? rawGap : 1u));
|
|
st.prevAnchorDt = dt;
|
|
} else if (st.prevAnchorDt > 0.0) {
|
|
dt = st.prevAnchorDt;
|
|
}
|
|
}
|
|
/* Unconditional, and only because the classification above has already
|
|
* sent every packet that must not move these either to `return false`
|
|
* or through prevAnchorValid = false. All four are one quantity: an
|
|
* anchor and the counter its difference is divided by. */
|
|
st.prevAnchorProdSec = prodSec;
|
|
st.prevAnchorCount = nElems;
|
|
st.prevAnchorValid = true;
|
|
st.lastCounter = f.counter;
|
|
st.counterValid = true;
|
|
|
|
tsOut.resize(nElems);
|
|
for (uint32_t e = 0; e < nElems; e++) {
|
|
tsOut[e] = (d.timeMode == kTimeFirstSample)
|
|
? (anchor + static_cast<double>(e) * dt)
|
|
: (anchor - static_cast<double>(nElems - 1u - e) * dt);
|
|
}
|
|
return true;
|
|
}
|
|
|
|
/* Rule 3: accumulated scalar, based on declared sampling rate or hrt.
|
|
*
|
|
* When samplingRate is declared the inter-element step is exact and we
|
|
* anchor from the end of the previous burst rather than from arrival time
|
|
* or hrt. This makes the output immune to arrival jitter: even when the
|
|
* kernel delivers two packets microseconds apart each burst starts exactly
|
|
* one sample period after the previous burst ended.
|
|
*
|
|
* When samplingRate is absent we must derive dt from the hrt gap, which
|
|
* requires the HrtRateFit to be ready. Until then we fall back to
|
|
* packetBurst (arrival-time spanning), which is accurate during the normal
|
|
* pre-burst delivery phase that precedes the fit becoming ready.
|
|
*
|
|
* A signal that has already produced a burst stays on this rule even when a
|
|
* later packet carries a single sample — Accumulate mode flushes on a timer,
|
|
* so a short cycle legitimately yields one. Dropping such a packet to rule 5
|
|
* would date it from arrival while its neighbours are chained, and would
|
|
* leave lastCounter behind so the next real burst read the skip as a lost
|
|
* datagram and reinstated a hole that never existed. A signal that has never
|
|
* burst is a genuine scalar and is left to rule 5. */
|
|
if (d.numElements() == 1u && (nElems > 1u || st.lastEmittedValid)) {
|
|
/* A rate that is not a finite positive number is no rate at all; see
|
|
* DeclaredRate(). Such a signal takes the hrt branch below. */
|
|
const double declared = DeclaredRate(d.samplingRate);
|
|
const double dt = (declared > 0.0) ? (1.0 / declared) : 0.0;
|
|
|
|
if (declared > 0.0) {
|
|
/* Where arrival time says this burst begins: its last element was
|
|
* acquired just before the packet landed. */
|
|
const double arrivalAnchor =
|
|
wallNow - static_cast<double>(nElems - 1u) * dt;
|
|
|
|
/* Chaining onto the end of the previous burst is immune to arrival
|
|
* jitter — a kernel draining several queued datagrams microseconds
|
|
* apart still yields contiguous timestamps. What a bare chain gets
|
|
* wrong is loss: it closes the hole a dropped datagram left, and
|
|
* every later sample is then dated early for the rest of the run.
|
|
*
|
|
* The wire says exactly how much is missing. counter increments
|
|
* once per update, so a gap of g means g-1 lost packets, each
|
|
* carrying (as far as we can tell) as many samples as the last one
|
|
* we saw. Reinstating that duration keeps the chain honest without
|
|
* consulting arrival time at all. */
|
|
double base = arrivalAnchor;
|
|
double step = dt;
|
|
if (st.lastEmittedValid) {
|
|
/* Unsigned subtraction wraps, so this stays right across the
|
|
* counter's own 2^32 rollover.
|
|
*
|
|
* A producer restart or a reordered datagram makes the wrapped
|
|
* gap enormous, and this deliberately does NOT special-case
|
|
* that: an absurd gap yields an absurd prediction, which the
|
|
* arrival backstop below then rejects on its own.
|
|
*
|
|
* Clamping the gap first is not a harmless earlier version of
|
|
* the same decision — it reaches the OPPOSITE answer. A clamp
|
|
* that treats gap > kMaxCounterGap as unknowable has to fall
|
|
* back to lost == 0, so the prediction becomes
|
|
* lastEmittedEnd + dt: one sample period after the last burst,
|
|
* which is exactly the shape of a healthy chain and therefore
|
|
* lands INSIDE the arrival backstop, is accepted, and silently
|
|
* closes an outage of arbitrary length. Letting the absurd gap
|
|
* through produces an absurd prediction that the backstop
|
|
* catches, and the burst re-anchors on arrival — which is the
|
|
* right answer, and what
|
|
* AccumulatedScalarSurvivesAProducerRestart pins down. The
|
|
* arithmetic cannot overflow: gap and prevAccCount are both
|
|
* bounded by 2^32-1, so lost is at most ~1.8e19, finite, and
|
|
* always rejected. */
|
|
const uint32_t gap = f.counter - st.lastCounter;
|
|
const double lost = (gap > 1u)
|
|
? static_cast<double>(gap - 1u) *
|
|
static_cast<double>(st.prevAccCount)
|
|
: 0.0;
|
|
const double predicted = st.lastEmittedEnd + dt * (1.0 + lost);
|
|
|
|
/* Backstop for what the counter cannot express: a producer
|
|
* restart, a counter stuck at zero, or a declared rate that is
|
|
* simply wrong. Beyond this the chain is not recoverable and
|
|
* arrival time is the better of two bad answers. */
|
|
if (std::fabs(predicted - arrivalAnchor) <= kBurstResyncThresholdS) {
|
|
base = predicted;
|
|
}
|
|
|
|
if (base <= st.lastEmittedEnd) {
|
|
/* Re-anchoring here would step backwards, and the ring, the
|
|
* trigger and the exporter all require a signal's stamps to
|
|
* increase. Rejecting the correction outright is not an
|
|
* option either: `predicted` is never less than
|
|
* lastEmittedEnd + dt, so rejection would make the backstop
|
|
* one-directional and let a timeline that runs FAST — two
|
|
* hosts' crystals differ by tens of ppm, so this is certain
|
|
* on a long session, not hypothetical — drift ahead of the
|
|
* wall clock without bound.
|
|
*
|
|
* So compress instead of stepping back: start immediately
|
|
* after the previous burst and spread this one out to
|
|
* arrival. A single packet is drawn narrower than its true
|
|
* width, and in exchange the timeline is back in step. */
|
|
if (wallNow > st.lastEmittedEnd) {
|
|
step = (wallNow - st.lastEmittedEnd) /
|
|
static_cast<double>(nElems);
|
|
base = st.lastEmittedEnd + step;
|
|
} else {
|
|
/* The timeline has run PAST arrival: our last burst is
|
|
* dated later than the moment this packet landed, so
|
|
* there is no room to spread into and no burst can end
|
|
* on arrival without starting before it. Squeeze this
|
|
* one instead, by the excess and by the wall time that
|
|
* has really elapsed since this signal's last burst.
|
|
*
|
|
* Both terms are needed, and only the second one
|
|
* converges. Within this call the wall clock is frozen
|
|
* at wallNow, so ANY positive step increases the lead
|
|
* measured at this instant; the lead falls only because
|
|
* the wall advances BETWEEN packets. A step expressed
|
|
* purely as a fraction of the nominal burst width
|
|
* therefore diverges as soon as the nominal width
|
|
* outruns the packet interval — with the floor alone, a
|
|
* declared 30 Hz against a producer really flushing 10
|
|
* samples at 1 kHz gained ~0.67 s of lead per second of
|
|
* stream, without bound. Capping the burst's total
|
|
* advance at kWallBleedFraction of the elapsed wall time
|
|
* makes it advance strictly slower than the wall for any
|
|
* declared rate, so the lead strictly falls.
|
|
*
|
|
* The proportional term still does the fine work: when
|
|
* the excess is smaller than a burst it removes it in
|
|
* one packet. kMinBleedFactor only keeps that term
|
|
* positive when the excess exceeds a whole burst.
|
|
*
|
|
* Steady state is a sawtooth, not a fixed offset: the
|
|
* squeeze pulls the lead down, ordinary chaining resumes
|
|
* on the very next packet and pushes it back up until
|
|
* the prediction misses arrival by more than
|
|
* kBurstResyncThresholdS. So the lead cycles between a
|
|
* fraction of a millisecond and roughly that threshold —
|
|
* bounded, which is what matters, but not zero. */
|
|
const double nominal = static_cast<double>(nElems) * dt;
|
|
const double excess = st.lastEmittedEnd - wallNow;
|
|
double factor = 1.0 - excess / nominal;
|
|
if (factor < kMinBleedFactor) { factor = kMinBleedFactor; }
|
|
double advance = nominal * factor;
|
|
|
|
/* A non-positive elapsed means the wall has not moved
|
|
* since this signal's previous burst. Skipping the cap
|
|
* then is deliberate and, more to the point, makes no
|
|
* difference: forcing the cap to zero instead sends step
|
|
* through the floor below to dt * kMinBleedFactor, which
|
|
* is the same number the proportional factor already
|
|
* yields once the excess exceeds one burst. Both leave
|
|
* the same-tick case diverging; only real elapsed wall
|
|
* time can bleed lead off, and a recv_time from
|
|
* CLOCK_REALTIME (udps_client.c:120) does not repeat. */
|
|
const double wallElapsed = wallNow - st.lastEmittedWall;
|
|
if (wallElapsed > 0.0) {
|
|
const double cap = kWallBleedFraction * wallElapsed;
|
|
if (cap < advance) { advance = cap; }
|
|
}
|
|
step = advance / static_cast<double>(nElems);
|
|
/* Unreachable with a finite positive dt — kept because
|
|
* downstream monotonicity must not depend on that
|
|
* argument holding for every value off the wire. */
|
|
if (!(step > 0.0)) { step = dt * kMinBleedFactor; }
|
|
base = st.lastEmittedEnd + step;
|
|
}
|
|
}
|
|
}
|
|
tsOut.resize(nElems);
|
|
for (uint32_t e = 0; e < nElems; e++) {
|
|
tsOut[e] = base + static_cast<double>(e) * step;
|
|
}
|
|
st.lastEmittedEnd = tsOut[nElems - 1u];
|
|
st.lastEmittedWall = wallNow;
|
|
/* The same lockstep rule the hrt branch applies to lastAccHrt, read
|
|
* off the counter alone because this branch has no producer clock.
|
|
* lastCounter is the reference the next packet's gap is measured
|
|
* from and prevAccCount is the burst width that gap is multiplied
|
|
* by, so they are one quantity and only a packet that defines the
|
|
* new front of the stream may move it. A datagram that arrived late
|
|
* is not that packet: see kMaxReorderPackets. */
|
|
const uint32_t back = st.lastCounter - f.counter;
|
|
if (!st.counterValid || f.counter == 0u || back == 0u ||
|
|
back >= kMaxReorderPackets) {
|
|
st.lastCounter = f.counter;
|
|
st.counterValid = true;
|
|
st.prevAccCount = nElems;
|
|
}
|
|
st.lastEmittedValid = true;
|
|
return true;
|
|
}
|
|
|
|
/* No declared rate: need hrt-derived dt. */
|
|
if (!hrtFit_.ready() || f.hrt == 0u) {
|
|
const bool ok = packetBurst(idx, nElems, wallNow, tsOut);
|
|
/* Carry the warm-up's state into the hrt branch, or the handover
|
|
* from one to the other is a discontinuity in both directions.
|
|
*
|
|
* The producer-clock reference (lastAccHrt, prevAccCount) matters
|
|
* most. Without it the first hrt packet has no previous tick to
|
|
* subtract, falls back to kDefaultDt for its inter-element step and
|
|
* latches ClockOffset against wallNow - (nElems-1)*kDefaultDt.
|
|
* kDefaultDt is only right when the burst happens to run at 1 kHz;
|
|
* at 100 samples per 10 ms packet it is ten times too wide and the
|
|
* latch lands 89 ms in the past — permanently, since it is below
|
|
* ClockOffset's recalibration threshold. Seeding here means the
|
|
* first hrt packet measures a real tick delta and latches correctly.
|
|
*
|
|
* The emitted-timeline reference (lastEmitted*) then only has to
|
|
* cover residual disagreement, but it is what keeps the handover
|
|
* MONOTONIC: packetBurst ends its burst at wallNow while the hrt
|
|
* branch ends at wallNow - (nElems-1)*hrtDt, and without a previous
|
|
* end to clamp against the first hrt packet steps the signal
|
|
* backwards by up to a whole burst width. */
|
|
if (f.hrt != 0u) {
|
|
st.lastAccHrt = f.hrt;
|
|
st.lastAccValid = true;
|
|
}
|
|
/* Same lockstep rule as the hrt branch below. A packet with hrt == 0
|
|
* lands here mid-stream and cannot move the tick reference, so it
|
|
* must not move the counter either: advancing the counter alone
|
|
* makes the next packet's elapsed span two intervals while its gap
|
|
* reports one, drawing that burst twice too wide and ending it
|
|
* 22.5 ms in the future at 10 samples per 25 ms packet (6x and
|
|
* +112 ms after five such packets). Before any tick reference exists
|
|
* nothing is keyed to the counter, so it is free to advance and arm
|
|
* the duplicate guard for a producer that never sets hrt at all.
|
|
*
|
|
* prevAccCount belongs to the same group. It is the OTHER factor of
|
|
* the denominator — cycles = prevAccCount * gap — and it means "how
|
|
* many cycles the reference packet spanned", so it is keyed to
|
|
* lastAccHrt exactly as the counter is. Accumulate flushes on a
|
|
* timer, so a short packet here is ordinary: a 2-sample stray with
|
|
* hrt == 0 that moved prevAccCount alone drew the next real burst
|
|
* five times too wide and ended it +90 ms in the future, then took
|
|
* eight squeezed bursts to bleed back. */
|
|
if (f.hrt != 0u || !st.lastAccValid) {
|
|
st.lastCounter = f.counter;
|
|
st.counterValid = true;
|
|
st.prevAccCount = nElems;
|
|
}
|
|
if (!ok) { return false; }
|
|
st.lastEmittedEnd = tsOut[nElems - 1u];
|
|
st.lastEmittedWall = wallNow;
|
|
st.lastEmittedValid = true;
|
|
return true;
|
|
}
|
|
const double rate = hrtFit_.ticksPerSecond();
|
|
|
|
/* Integrate short tick DELTAS. Never convert an absolute tick count, and
|
|
* never subtract two such conversions.
|
|
*
|
|
* hrt counts from the producer's boot, so it is already ~1e11 ticks when
|
|
* the scope attaches, while the fit is re-estimated on every packet and
|
|
* wobbles by a few parts in 1e4. Any absolute hrt/rate therefore carries
|
|
* that relative wobble multiplied by the whole elapsed epoch — tens of
|
|
* milliseconds, moving in either direction from one packet to the next.
|
|
* As a burst's position that is not merely imprecise, it is
|
|
* NON-MONOTONIC: on a 2 h stream with ordinary scheduling jitter a few
|
|
* percent of samples land before their own predecessor.
|
|
*
|
|
* A delta spans one packet, so its share of the wobble is microseconds,
|
|
* and summing deltas keeps it there. ClockOffset then latches the
|
|
* arbitrary epoch that leaves behind, exactly as it would have latched
|
|
* the producer's boot epoch. */
|
|
double elapsed = 0.0;
|
|
/* Whether lastAccHrt should take this packet's value. Only a packet
|
|
* that legitimately defines the new front of producer time may move it;
|
|
* see the backward case below. */
|
|
bool takeHrt = true;
|
|
if (st.lastAccValid) {
|
|
if (f.hrt > st.lastAccHrt) {
|
|
elapsed = static_cast<double>(f.hrt - st.lastAccHrt) / rate;
|
|
} else {
|
|
/* hrt went backwards. Two entirely different events look like
|
|
* this and only the SIZE of the jump separates them.
|
|
*
|
|
* A small one is a reordered datagram: the packet that overtook
|
|
* it already counted the interval it covers, so it must
|
|
* contribute nothing — and must also leave lastAccHrt alone.
|
|
* Letting it write lastAccHrt anyway (which is what this code
|
|
* used to do unconditionally) rolls the reference back one
|
|
* interval, so the NEXT packet's delta spans two and fabricates
|
|
* a whole extra packet of producer time. It never heals:
|
|
* ClockOffset would correct it, but the monotonic clamp below
|
|
* discards every backward correction. A hundred swaps on a
|
|
* 25 ms stream left the trace 3.5 s ahead, permanently. The C
|
|
* client does not reorder for us — udps_client.c only COUNTS
|
|
* counter gaps — so this is reachable on any real network.
|
|
*
|
|
* A large one is a producer restart: hrt drops from the
|
|
* producer's whole uptime to near zero. Here the unconditional
|
|
* write was the right behaviour and must be kept, because
|
|
* refusing to regress would leave every subsequent packet below
|
|
* lastAccHrt forever, elapsed permanently zero and the signal
|
|
* frozen. Rebase, and reset the offset so it re-latches against
|
|
* the new epoch instead of being dragged there by recalibration. */
|
|
const double backward =
|
|
static_cast<double>(st.lastAccHrt - f.hrt) / rate;
|
|
if (backward > kProducerRestartS) {
|
|
st.accOffset.reset();
|
|
} else {
|
|
takeHrt = false;
|
|
}
|
|
}
|
|
}
|
|
st.accProdSec += elapsed;
|
|
|
|
/* The flushes carry contiguous RT cycles, so the tick gap divided by the
|
|
* number of cycles it spans is exactly one cycle period. That count is
|
|
* NOT prevAccCount: elapsed spans every packet since the last one we
|
|
* saw, so a lost datagram makes the tick gap wider without making
|
|
* prevAccCount larger. Dividing by prevAccCount alone therefore returns
|
|
* a period scaled by the whole counter gap — 2x for one lost datagram,
|
|
* 11x for ten — which draws the recovery burst that many times too wide
|
|
* and, because the burst is anchored on its LAST element, ends it in the
|
|
* FUTURE (measured: +22.5 ms for one loss, +225 ms for ten, at 10
|
|
* samples per 25 ms packet). At 1% loss that mis-spaced 4.0% of all
|
|
* samples. The declared branch already reads the counter for exactly
|
|
* this purpose (`lost`, above); the hrt branch must too.
|
|
*
|
|
* The gap and `elapsed` must be measured from the SAME packet, or the
|
|
* division mixes references. That is why lastCounter is written under
|
|
* takeHrt below, in lockstep with lastAccHrt: a reordered datagram that
|
|
* rolled lastCounter back while leaving lastAccHrt alone would give the
|
|
* next in-order packet a gap of d+1 against an elapsed spanning one
|
|
* interval, dividing its period by d+1 — measured 0.5x the true spacing
|
|
* for a swap of neighbours, 0.048x for a distance of twenty.
|
|
*
|
|
* Unsigned subtraction wraps, which is what makes this right across the
|
|
* counter's own 2^32 rollover. A gap in the top half of the range is not
|
|
* a forward gap at all but a backward one seen through the wrap, so it
|
|
* is treated as no information rather than as 2 billion lost packets. */
|
|
const uint32_t rawGap = f.counter - st.lastCounter;
|
|
const bool fwdGap = (f.counter != 0u) && st.counterValid &&
|
|
(rawGap != 0u) && (rawGap < 0x80000000u);
|
|
const double cycles = static_cast<double>(st.prevAccCount) *
|
|
static_cast<double>(fwdGap ? rawGap : 1u);
|
|
|
|
/* Falling back to kDefaultDt is a last resort, not a default: see
|
|
* SigState::lastHrtDt. What makes the fallback matter is the producer
|
|
* restart, because that is the one path where elapsed is zero AND
|
|
* offset.reset() has just forced a re-latch, so the burst width used
|
|
* here is the one calibrated against — measured 13.5 ms of standing
|
|
* displacement at 10 samples per 25 ms packet, 89 ms at 100 per 10 ms,
|
|
* both below kRecalibThresholdS and so never corrected. A reorder also
|
|
* reaches the fallback but does not re-latch, and its measured standing
|
|
* error is 0.013 ms, i.e. nothing.
|
|
*
|
|
* This is better than kDefaultDt at every cadence except one: a producer
|
|
* that restarts having CHANGED its cycle time is remembered wrongly, and
|
|
* a tenfold change measured -20 ms against kDefaultDt's -6.8 ms. Both
|
|
* are bounded and neither is correct; the remembered period wins the
|
|
* case that actually happens. */
|
|
double hrtDt;
|
|
if (elapsed > 0.0 && cycles > 0.0) {
|
|
hrtDt = elapsed / cycles;
|
|
st.lastHrtDt = hrtDt;
|
|
} else if (st.lastHrtDt > 0.0) {
|
|
hrtDt = st.lastHrtDt;
|
|
} else {
|
|
hrtDt = kDefaultDt;
|
|
}
|
|
|
|
/* Anchor the burst's LAST element on arrival, not its first. The
|
|
* packet's hrt is the tick count of sample 0 (UDPSourceSession.cpp:574),
|
|
* so stepping forward from it is right — but ClockOffset latches
|
|
* offset = wall - producerSec on its first call, and passing the raw
|
|
* arrival would put sample 0 at the instant the packet carrying the
|
|
* whole burst LANDED, dating every sample in it late by a burst. The
|
|
* declared-rate branch above already anchors on the burst end
|
|
* (arrivalAnchor), and two accumulated scalars in one scope, one with a
|
|
* declared rate and one without, would otherwise sit a burst apart on a
|
|
* shared X axis — 9 ms for 10 samples at 1 kHz, plain to see at a 200 ms
|
|
* window. Since map() latches once, this is a constant shift applied at
|
|
* latch and recalibration only; it changes no spacing. */
|
|
double base = st.accOffset.map(
|
|
st.accProdSec,
|
|
wallNow - static_cast<double>(nElems - 1u) * hrtDt);
|
|
double step = hrtDt;
|
|
|
|
/* ClockOffset recalibrates once true drift passes its threshold, and a
|
|
* recalibration can land behind where this signal already is.
|
|
* Downstream requires increasing stamps, so step forward minimally —
|
|
* but a bare forward step is one-directional, exactly the defect the
|
|
* declared branch's squeeze exists to avoid. A backward wall step (an
|
|
* NTP correction, a suspend/resume) would otherwise leave this signal
|
|
* permanently ahead of the wall clock, since the recalibrated base is
|
|
* behind lastEmittedEnd on every later packet too and the clamp keeps
|
|
* discarding it. So cap the burst's total advance against the wall time
|
|
* elapsed since this signal's previous burst, for the reason spelled out
|
|
* at kWallBleedFraction: only that makes the lead bleed off. */
|
|
if (st.lastEmittedValid && base <= st.lastEmittedEnd) {
|
|
const double wallElapsed = wallNow - st.lastEmittedWall;
|
|
if (wallElapsed > 0.0) {
|
|
const double cap = kWallBleedFraction * wallElapsed /
|
|
static_cast<double>(nElems);
|
|
if (cap < step) { step = cap; }
|
|
}
|
|
base = st.lastEmittedEnd + step;
|
|
}
|
|
|
|
tsOut.resize(nElems);
|
|
for (uint32_t e = 0; e < nElems; e++) {
|
|
tsOut[e] = base + static_cast<double>(e) * step;
|
|
}
|
|
if (takeHrt) { st.lastAccHrt = f.hrt; }
|
|
st.lastAccValid = true;
|
|
st.lastEmittedEnd = tsOut[nElems - 1u];
|
|
st.lastEmittedWall = wallNow;
|
|
/* Keep packetBurst's reference current even though this branch does not
|
|
* use it. A single packet with hrt == 0 re-enters the warm-up branch
|
|
* above, and packetBurst would otherwise span from whenever this signal
|
|
* last took that branch — the whole session. Measured: 153 packets into
|
|
* a 25 ms stream, one zero-hrt packet emitted a burst starting 2.74 s
|
|
* behind the trace, and that figure grows with session length. */
|
|
st.lastPacketWall = wallNow;
|
|
st.lastPacketValid = true;
|
|
/* In lockstep with lastAccHrt, and for the same reason: lastAccHrt is
|
|
* the numerator of the next packet's period and these two are its
|
|
* denominator, so only a packet that defines the new front of producer
|
|
* time may move any of them. Advancing the counter alone on a reordered
|
|
* datagram halves the next packet's spacing; see the gap comment above.
|
|
* prevAccCount is in the group because cycles multiplies the two
|
|
* together — it means "cycles spanned by the reference packet", and
|
|
* since Accumulate flushes on a timer the count really does vary
|
|
* between packets. Leaving a counter behind at all is what lets the
|
|
* duplicate-datagram guard at the top of timestamps() fire — a host
|
|
* joined on two interfaces receives every unfragmented update twice,
|
|
* and the original always sets takeHrt. */
|
|
if (takeHrt) {
|
|
st.lastCounter = f.counter;
|
|
st.counterValid = true;
|
|
st.prevAccCount = nElems;
|
|
}
|
|
st.lastEmittedValid = true;
|
|
return true;
|
|
}
|
|
|
|
/* Rule 4: PACKET burst with no time reference at all. */
|
|
if (nElems > 1u) {
|
|
return packetBurst(idx, nElems, wallNow, tsOut);
|
|
}
|
|
|
|
/* Rule 5: plain scalar. */
|
|
tsOut.assign(1, wallNow);
|
|
return true;
|
|
}
|
|
|
|
} /* namespace udpscope */
|