Reported as samples sporadically carrying a previous packet's timestamp: holes on one side of the stream and collisions on the other, in both the Go and the MARTe2 receiver. That it appeared in both is what located it -- the shared cause is upstream of either client. Four independent defects, all of which end in a packet's values being placed at a time that is not theirs. Reassembly slot exhaustion (the "Reassembly slots full; evicting oldest" flood). Chunk size was learnt only from fragment 0, so an out-of-order burst destroyed a packet whose bytes had all arrived and left the slot occupied until the 2 s GC. Slots were keyed on the counter alone, but DATA and CONFIG number independently, so equal counters merged the two streams. The 32-byte received-mask covered 256 of the 512 fragments the client accepts, so a duplicate above 255 was counted as new and the packet was delivered with a hole of stale bytes in it. And one datagram was read per Execute(), which cannot drain a fast producer. Fixed with a pendingTail deferral, (counter, type) keying, a 64-byte mask, a 256-datagram drain, counter-age slot reclamation, and a 1 Hz aggregated warning in place of the per-eviction flood. UDPStreamer dropping whole Accumulate batches. EventSem::ResetWait is Reset-then-Wait, so a Post() landing while the sender thread was inside ServiceClients()/SendData() was destroyed by the next Reset. The batch was then skipped with dataReady false, readyFill was never cleared, and the following flush overwrote it: an entire run of RT cycles never reached the wire. The record of pending work now lives in the buffers rather than in the semaphore edge, which also removes up to UDPS_DATA_WAIT_MS of latency; genuine backpressure overwrites are counted and reported. Against the unfixed code the new test sees 2999/3000 batches never consumed. Period inflation after loss. Accumulated scalars carry no SamplingRate, so the receiver derives dt from the sender-clock gap -- but dividing it by the previous packet's sample count is only right while nothing is lost. One loss doubles the reported period, which spreads a batch a full batch past its own end and into the range the next packet claims. That is the hole and the collision, exactly. Inferring the cycle count from the estimate's own period is not a way out: it has a stable fixed point wherever gap/dt is an integer, so a real rate change locks it at the old one for good (AccumDtGTest.FollowsSustainedRateChange). The packet counter removes the ambiguity, so all three receivers now order on it: a DATA packet that does not advance the counter is dropped rather than delivered, because its values are older than data already handed over. Ordering is on the signed difference so it survives the uint32 wrap, and the sequence resets on reconnect, where the producer's counter restarts independently of ours. The loss count that falls out of the same delta feeds the period estimate as cycles = prevN * (1 + lost), which reduces exactly to gap/prevN when nothing is lost and therefore still tracks a genuine rate change. UDPSClient::AcceptDataCounter (C++), udpsprotocol.SequenceGate (Go), decode_data (C). The C client's existing gap counter was wrap-unsafe and let a stale packet rewind last_counter, which made every subsequent gap wrong; it uses the same code now. Docs/Protocol.md gains an Ordering DATA section stating the requirement for any receiver, including ones outside this repository. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
417 lines
13 KiB
Go
417 lines
13 KiB
Go
package udpsprotocol
|
||
|
||
import (
|
||
"bytes"
|
||
"encoding/binary"
|
||
"fmt"
|
||
"math"
|
||
"time"
|
||
)
|
||
|
||
// ─── Constants ───────────────────────────────────────────────────────────────
|
||
|
||
const (
|
||
MagicUDPS uint32 = 0x53504455 // 'UDPS' little-endian
|
||
|
||
PktData uint8 = 0
|
||
PktConfig uint8 = 1
|
||
PktACK uint8 = 2
|
||
PktConnect uint8 = 3
|
||
PktDisconnect uint8 = 4
|
||
|
||
HeaderSize = 17
|
||
SigDescSize = 136
|
||
NoTimeSignal = uint32(0xFFFFFFFF)
|
||
|
||
QuantNone uint8 = 0
|
||
QuantUint8 uint8 = 1
|
||
QuantInt8 uint8 = 2
|
||
QuantUint16 uint8 = 3
|
||
QuantInt16 uint8 = 4
|
||
|
||
// TimeMode values – must match UDPStreamerTimeMode enum in UDPStreamer.h
|
||
TimeModePacket uint8 = 0 // use wall-clock packet arrival time
|
||
TimeModeFullArray uint8 = 1 // TimeSignal has same N elements; not expanded here
|
||
TimeModeFirstSample uint8 = 2 // TimeSignal scalar = time of element [0]
|
||
TimeModeLastSample uint8 = 3 // TimeSignal scalar = time of element [N-1]
|
||
|
||
// PublishMode values – must match UDPStreamerPublishMode enum in UDPStreamer.h
|
||
PublishModeStrict uint8 = 0 // one packet per Synchronise() call
|
||
PublishModeAccumulate uint8 = 1 // variable batch; DATA has [8 HRT][4 numSamples][signals...]
|
||
PublishModeDecimate uint8 = 2 // one packet every Ratio calls
|
||
)
|
||
|
||
// ─── Packet header (17 bytes, little-endian, packed) ─────────────────────────
|
||
|
||
type PacketHeader struct {
|
||
Magic uint32
|
||
Type uint8
|
||
Counter uint32
|
||
FragmentIdx uint16
|
||
TotalFragments uint16
|
||
PayloadBytes uint32
|
||
}
|
||
|
||
// ParseHeader decodes exactly HeaderSize bytes into a PacketHeader.
|
||
func ParseHeader(b []byte) (PacketHeader, error) {
|
||
if len(b) < HeaderSize {
|
||
return PacketHeader{}, fmt.Errorf("header too short: %d bytes", len(b))
|
||
}
|
||
var h PacketHeader
|
||
r := bytes.NewReader(b[:HeaderSize])
|
||
if err := binary.Read(r, binary.LittleEndian, &h); err != nil {
|
||
return PacketHeader{}, err
|
||
}
|
||
if h.Magic != MagicUDPS {
|
||
return PacketHeader{}, fmt.Errorf("bad magic: 0x%08X", h.Magic)
|
||
}
|
||
return h, nil
|
||
}
|
||
|
||
// buildHeader serialises a PacketHeader to a 17-byte slice.
|
||
func buildHeader(h PacketHeader) []byte {
|
||
buf := new(bytes.Buffer)
|
||
_ = binary.Write(buf, binary.LittleEndian, h)
|
||
return buf.Bytes()
|
||
}
|
||
|
||
// BuildConnectPacket returns a 17-byte CONNECT datagram.
|
||
func BuildConnectPacket() []byte {
|
||
return buildHeader(PacketHeader{
|
||
Magic: MagicUDPS,
|
||
Type: PktConnect,
|
||
Counter: 0,
|
||
FragmentIdx: 0,
|
||
TotalFragments: 1,
|
||
PayloadBytes: 0,
|
||
})
|
||
}
|
||
|
||
// BuildDisconnectPacket returns a 17-byte DISCONNECT datagram.
|
||
func BuildDisconnectPacket() []byte {
|
||
return buildHeader(PacketHeader{
|
||
Magic: MagicUDPS,
|
||
Type: PktDisconnect,
|
||
Counter: 0,
|
||
FragmentIdx: 0,
|
||
TotalFragments: 1,
|
||
PayloadBytes: 0,
|
||
})
|
||
}
|
||
|
||
// BuildAckPacket returns a 17-byte ACK datagram. Unicast clients send it
|
||
// periodically as a keepalive: UDPSServer refreshes the client's last-seen
|
||
// without re-sending CONFIG (which a repeated CONNECT would trigger).
|
||
func BuildAckPacket() []byte {
|
||
return buildHeader(PacketHeader{
|
||
Magic: MagicUDPS,
|
||
Type: PktACK,
|
||
Counter: 0,
|
||
FragmentIdx: 0,
|
||
TotalFragments: 1,
|
||
PayloadBytes: 0,
|
||
})
|
||
}
|
||
|
||
// ─── Signal descriptor (136 bytes) ───────────────────────────────────────────
|
||
|
||
// SignalInfo holds the parsed metadata for one signal.
|
||
type SignalInfo struct {
|
||
Name string `json:"name"`
|
||
TypeCode uint8 `json:"typeCode"`
|
||
QuantType uint8 `json:"quantType"`
|
||
NumDimensions uint8 `json:"numDimensions"`
|
||
NumRows uint32 `json:"numRows"`
|
||
NumCols uint32 `json:"numCols"`
|
||
RangeMin float64 `json:"rangeMin"`
|
||
RangeMax float64 `json:"rangeMax"`
|
||
TimeMode uint8 `json:"timeMode"`
|
||
SamplingRate float64 `json:"samplingRate"`
|
||
TimeSignalIdx uint32 `json:"timeSignalIdx"`
|
||
Unit string `json:"unit"`
|
||
}
|
||
|
||
// NumElements returns the total number of scalar values in one sample of this signal.
|
||
func (s SignalInfo) NumElements() int {
|
||
r := int(s.NumRows)
|
||
c := int(s.NumCols)
|
||
if r == 0 {
|
||
r = 1
|
||
}
|
||
if c == 0 {
|
||
c = 1
|
||
}
|
||
/* HI-2: cap at 1M to prevent integer overflow / OOM from crafted packets */
|
||
n := r * c
|
||
if n < 0 || n > 1024*1024 {
|
||
return 1024 * 1024
|
||
}
|
||
return n
|
||
}
|
||
|
||
// rawTypeSize returns the byte size for one element of the raw (unquantised) type.
|
||
func rawTypeSize(typeCode uint8) int {
|
||
switch typeCode {
|
||
case 0, 1: // uint8, int8
|
||
return 1
|
||
case 2, 3: // uint16, int16
|
||
return 2
|
||
case 4, 5: // uint32, int32
|
||
return 4
|
||
case 6, 7: // uint64, int64
|
||
return 8
|
||
case 8: // float32
|
||
return 4
|
||
case 9: // float64
|
||
return 8
|
||
default:
|
||
return 1
|
||
}
|
||
}
|
||
|
||
// quantSize returns the byte size of one quantised element.
|
||
func quantSize(qt uint8) int {
|
||
switch qt {
|
||
case QuantUint8, QuantInt8:
|
||
return 1
|
||
case QuantUint16, QuantInt16:
|
||
return 2
|
||
default:
|
||
return 0
|
||
}
|
||
}
|
||
|
||
// readRawElement reads one element at offset and converts it to float64.
|
||
func readRawElement(b []byte, offset int, typeCode uint8) float64 {
|
||
switch typeCode {
|
||
case 0:
|
||
return float64(b[offset])
|
||
case 1:
|
||
return float64(int8(b[offset]))
|
||
case 2:
|
||
return float64(binary.LittleEndian.Uint16(b[offset:]))
|
||
case 3:
|
||
return float64(int16(binary.LittleEndian.Uint16(b[offset:])))
|
||
case 4:
|
||
return float64(binary.LittleEndian.Uint32(b[offset:]))
|
||
case 5:
|
||
return float64(int32(binary.LittleEndian.Uint32(b[offset:])))
|
||
case 6:
|
||
return float64(binary.LittleEndian.Uint64(b[offset:]))
|
||
case 7:
|
||
return float64(int64(binary.LittleEndian.Uint64(b[offset:])))
|
||
case 8:
|
||
bits := binary.LittleEndian.Uint32(b[offset:])
|
||
return float64(math.Float32frombits(bits))
|
||
case 9:
|
||
bits := binary.LittleEndian.Uint64(b[offset:])
|
||
return math.Float64frombits(bits)
|
||
default:
|
||
return 0
|
||
}
|
||
}
|
||
|
||
// dequantise converts a raw quantised integer to a physical float64.
|
||
func dequantise(qt uint8, raw uint16, rangeMin, rangeMax float64) float64 {
|
||
span := rangeMax - rangeMin
|
||
switch qt {
|
||
case QuantUint8:
|
||
return rangeMin + (float64(uint8(raw))/255.0)*span
|
||
case QuantInt8:
|
||
return rangeMin + (float64(int8(raw)+127)/254.0)*span
|
||
case QuantUint16:
|
||
return rangeMin + (float64(raw)/65535.0)*span
|
||
case QuantInt16:
|
||
return rangeMin + (float64(int16(raw)+32767)/65534.0)*span
|
||
default:
|
||
return 0
|
||
}
|
||
}
|
||
|
||
// nullTermString converts a zero-padded byte slice to a Go string.
|
||
func nullTermString(b []byte) string {
|
||
n := bytes.IndexByte(b, 0)
|
||
if n < 0 {
|
||
return string(b)
|
||
}
|
||
return string(b[:n])
|
||
}
|
||
|
||
// ─── CONFIG payload parser ────────────────────────────────────────────────────
|
||
|
||
// ParseConfig decodes a fully-reassembled CONFIG payload.
|
||
// Returns the signal list, the publishing mode byte (PublishMode*), and any error.
|
||
func ParseConfig(payload []byte) ([]SignalInfo, uint8, error) {
|
||
if len(payload) < 4 {
|
||
return nil, 0, fmt.Errorf("config payload too short")
|
||
}
|
||
numSigs := binary.LittleEndian.Uint32(payload[0:4])
|
||
/* HI-2: validate numSigs against payload length before allocating */
|
||
maxSigs := uint32(len(payload) / SigDescSize)
|
||
if numSigs > maxSigs {
|
||
return nil, 0, fmt.Errorf("config claims %d signals but payload can hold at most %d", numSigs, maxSigs)
|
||
}
|
||
offset := 4
|
||
sigs := make([]SignalInfo, 0, numSigs)
|
||
for i := uint32(0); i < numSigs; i++ {
|
||
if offset+SigDescSize > len(payload) {
|
||
return nil, 0, fmt.Errorf("config payload truncated at signal %d", i)
|
||
}
|
||
raw := payload[offset : offset+SigDescSize]
|
||
si := SignalInfo{
|
||
Name: nullTermString(raw[0:64]),
|
||
TypeCode: raw[64],
|
||
QuantType: raw[65],
|
||
NumDimensions: raw[66],
|
||
NumRows: binary.LittleEndian.Uint32(raw[67:71]),
|
||
NumCols: binary.LittleEndian.Uint32(raw[71:75]),
|
||
RangeMin: math.Float64frombits(binary.LittleEndian.Uint64(raw[75:83])),
|
||
RangeMax: math.Float64frombits(binary.LittleEndian.Uint64(raw[83:91])),
|
||
TimeMode: raw[91],
|
||
SamplingRate: math.Float64frombits(binary.LittleEndian.Uint64(raw[92:100])),
|
||
TimeSignalIdx: binary.LittleEndian.Uint32(raw[100:104]),
|
||
Unit: nullTermString(raw[104:136]),
|
||
}
|
||
sigs = append(sigs, si)
|
||
offset += SigDescSize
|
||
}
|
||
// Trailing publish-mode byte (added after signal descriptors).
|
||
publishMode := PublishModeStrict
|
||
if offset < len(payload) {
|
||
publishMode = payload[offset]
|
||
}
|
||
return sigs, publishMode, nil
|
||
}
|
||
|
||
// ─── DATA payload parser ──────────────────────────────────────────────────────
|
||
|
||
// DataSample holds the decoded values from one DATA packet.
|
||
type DataSample struct {
|
||
HRTTimestamp uint64
|
||
WallTime time.Time // wall-clock time at UDP arrival; used as x-axis
|
||
Values map[string][]float64 // key = signal name, value = []float64 with NumElements entries
|
||
// Lost is the number of DATA packets missing between the previous sample
|
||
// and this one, taken from the producer's packet counter (see
|
||
// SequenceGate). Consumers that derive a per-element period from the
|
||
// inter-packet gap need it: the gap widens with every lost packet, and
|
||
// dividing it by this packet's element count alone reports a period too
|
||
// long by exactly that factor — which walks the packet's elements past
|
||
// their own end and into the range the next packet claims.
|
||
Lost uint32
|
||
}
|
||
|
||
// parseElems reads n elements for sig from payload at offset, advancing offset.
|
||
// Returns the slice of float64 values and the new offset.
|
||
func parseElems(payload []byte, offset, n int, sig SignalInfo) ([]float64, int, error) {
|
||
sz := rawTypeSize(sig.TypeCode)
|
||
if sig.QuantType != QuantNone {
|
||
sz = quantSize(sig.QuantType)
|
||
}
|
||
// Bounds-check before allocating. In Accumulate mode n is numSamples ×
|
||
// NumElements, so a malformed packet could otherwise ask for an allocation
|
||
// far larger than its own payload could ever justify.
|
||
if n < 0 || n > (len(payload)-offset)/sz {
|
||
return nil, offset, fmt.Errorf("data payload truncated for signal %q", sig.Name)
|
||
}
|
||
elems := make([]float64, n)
|
||
needed := n * sz
|
||
if sig.QuantType == QuantNone {
|
||
for i := 0; i < n; i++ {
|
||
elems[i] = readRawElement(payload, offset+i*sz, sig.TypeCode)
|
||
}
|
||
offset += needed
|
||
} else {
|
||
for i := 0; i < n; i++ {
|
||
var raw uint16
|
||
if sz == 1 {
|
||
raw = uint16(payload[offset+i])
|
||
} else {
|
||
raw = binary.LittleEndian.Uint16(payload[offset+i*2:])
|
||
}
|
||
elems[i] = dequantise(sig.QuantType, raw, sig.RangeMin, sig.RangeMax)
|
||
}
|
||
offset += needed
|
||
}
|
||
return elems, offset, nil
|
||
}
|
||
|
||
// ParseData decodes a fully-reassembled DATA payload using the provided signal config
|
||
// and publishing mode. arrivalTime is the wall-clock time at which the packet arrived.
|
||
//
|
||
// For PublishModeAccumulate the payload format is:
|
||
//
|
||
// [8 HRT][4 numSamples][for each signal: numSamples × NumElements elems]
|
||
//
|
||
// Every signal is accumulated, arrays included: the producer captures one full
|
||
// snapshot of the whole signal set per RT cycle and lays the cycles out
|
||
// contiguously per signal (UDPStreamer::SerializeAccumulated). Reading only
|
||
// NumElements for an array would hand every slot the first cycle's data and
|
||
// slide all later signals into that array's tail.
|
||
//
|
||
// The function returns one DataSample per accumulated snapshot so the hub can
|
||
// process each slot independently with its own timestamp.
|
||
func ParseData(payload []byte, sigs []SignalInfo, publishMode uint8, arrivalTime time.Time) ([]DataSample, error) {
|
||
if len(payload) < 8 {
|
||
return nil, fmt.Errorf("data payload too short")
|
||
}
|
||
hrt := binary.LittleEndian.Uint64(payload[0:8])
|
||
offset := 8
|
||
|
||
if publishMode == PublishModeAccumulate {
|
||
if len(payload) < 12 {
|
||
return nil, fmt.Errorf("accumulate data payload too short (missing numSamples)")
|
||
}
|
||
numSamples := int(binary.LittleEndian.Uint32(payload[8:12]))
|
||
offset = 12
|
||
if numSamples == 0 {
|
||
return []DataSample{}, nil
|
||
}
|
||
/* HI-2: sanity-cap numSamples to prevent OOM from crafted packets */
|
||
if numSamples < 0 || numSamples > 1024*1024 {
|
||
return nil, fmt.Errorf("accumulate numSamples %d out of range", numSamples)
|
||
}
|
||
|
||
// Parse per-signal data blocks (all slots for a signal are contiguous).
|
||
accumVals := make(map[string][]float64, len(sigs)) // numSamples × NumElements
|
||
accumElems := make(map[string]int, len(sigs))
|
||
|
||
for _, sig := range sigs {
|
||
n := sig.NumElements()
|
||
elems, newOff, err := parseElems(payload, offset, numSamples*n, sig)
|
||
if err != nil {
|
||
return nil, err
|
||
}
|
||
offset = newOff
|
||
accumVals[sig.Name] = elems
|
||
accumElems[sig.Name] = n
|
||
}
|
||
|
||
// Build one DataSample per slot.
|
||
samples := make([]DataSample, numSamples)
|
||
for k := 0; k < numSamples; k++ {
|
||
vals := make(map[string][]float64, len(sigs))
|
||
for sigName, av := range accumVals {
|
||
n := accumElems[sigName]
|
||
// Sub-slice of the decoded block; the hub treats values as
|
||
// read-only, so no copy is needed.
|
||
vals[sigName] = av[k*n : (k+1)*n : (k+1)*n]
|
||
}
|
||
samples[k] = DataSample{HRTTimestamp: hrt, WallTime: arrivalTime, Values: vals}
|
||
}
|
||
return samples, nil
|
||
}
|
||
|
||
// Strict / Decimate: single snapshot, one element set per signal.
|
||
vals := make(map[string][]float64, len(sigs))
|
||
for _, sig := range sigs {
|
||
n := sig.NumElements()
|
||
elems, newOff, err := parseElems(payload, offset, n, sig)
|
||
if err != nil {
|
||
return nil, err
|
||
}
|
||
offset = newOff
|
||
vals[sig.Name] = elems
|
||
}
|
||
return []DataSample{{HRTTimestamp: hrt, WallTime: arrivalTime, Values: vals}}, nil
|
||
}
|