fix(pgxl): match a reply to the command that asked for it

The amplifier PUSHES status frames ("S0|state=…") on the same socket it answers
commands on, and it pushes them constantly once in OPERATE - power, SWR and
temperature all move while transmitting.

command() read exactly one line and took whatever arrived first as its answer.
One pushed frame therefore put the stream permanently one reply behind: every
later command read the PREVIOUS command's answer, and eventually one waited out
the 3 s deadline, failed, and dropped the connection. Hence a fresh TCP
connection and a fresh authentication every few seconds in the log.

The stall in transmit is the same defect seen from the other side: command()
holds the connection mutex across that whole dead wait, so SetOperate and every
other control queued behind up to three seconds of nothing.

It only appeared remotely and in OPERATE because that is when there is anything
to push - on a LAN with an idle amplifier the race hardly ever opens. Which is
why it did not do this yesterday.

readReplyLocked now reads until the R<id>| that belongs to the command, feeding
every frame it passes to parse() on the way - a pushed status is fresher than
the one we were about to ask for, so nothing is wasted.

authLocked used the same one-line read and worked around this by re-sending the
whole handshake, which is visible in the log as "auth reply=S0|state=IDLE
(try 1)" followed by a second attempt. It goes through the same reader now.
This commit is contained in:
2026-08-10 19:45:54 +02:00
parent ae7472a67d
commit bde136b98b
2 changed files with 42 additions and 16 deletions
+38 -14
View File
@@ -21,9 +21,9 @@ import (
)
const (
defaultPort = 9008
dialTimeout = 5 * time.Second
ioTimeout = 3 * time.Second
defaultPort = 9008
dialTimeout = 5 * time.Second
ioTimeout = 3 * time.Second
// Poll fast enough that the amp's OWN forward/current figures make a usable
// live meter on their own — the UI prefers them over the FlexRadio VITA stream
// (which never traverses a public-IP/NAT link), so this direct reading is what
@@ -240,12 +240,10 @@ func (c *Client) authLocked() error {
if _, err := fmt.Fprintf(c.conn, "C%d|auth code=%s\n", id, c.password); err != nil {
return err
}
_ = c.conn.SetReadDeadline(time.Now().Add(ioTimeout))
line, err := c.reader.ReadString('\n')
line, err := c.readReplyLocked(fmt.Sprintf("R%d|", id))
if err != nil {
return err
}
line = strings.TrimSpace(line)
applog.Printf("pgxl: auth reply=%q (try %d)", line, try)
hex, msg := "", ""
if p := strings.SplitN(line, "|", 3); len(p) >= 2 {
@@ -264,6 +262,39 @@ func (c *Client) authLocked() error {
return fmt.Errorf("powergenius: authentication failed after 4 tries (R|%s|) — check the remote code", lastHex)
}
// readReplyLocked reads until the reply carrying `want` as its prefix arrives,
// feeding every unsolicited frame it passes to parse() on the way.
//
// The amplifier PUSHES status frames ("S0|state=…") on the same socket, and it
// pushes them constantly once it is in OPERATE — power, SWR and temperature all
// move while transmitting. The old code read exactly one line per command and
// took whatever came first as its answer, so a single pushed frame put the
// stream permanently one reply behind: every later command read the PREVIOUS
// command's answer, and the last one waited out the 3 s deadline, failed, and
// dropped the connection. That is the reconnect-every-few-seconds seen in the
// field, and the stall in transmit — command() holds the mutex across that whole
// dead wait, so anything else touching the amplifier queued behind it.
//
// It only showed up remotely and in OPERATE: on a LAN with an idle amplifier
// there is almost nothing to push and the race hardly ever opens.
func (c *Client) readReplyLocked(want string) (string, error) {
deadline := time.Now().Add(ioTimeout)
for {
_ = c.conn.SetReadDeadline(deadline)
line, err := c.reader.ReadString('\n')
if err != nil {
return "", err
}
line = strings.TrimSpace(line)
// Every frame is worth having, ours or not — a pushed status is fresher
// than the one we were about to ask for.
c.parse(line)
if strings.HasPrefix(line, want) {
return line, nil
}
}
}
func (c *Client) dropConn() {
c.mu.Lock()
if c.conn != nil {
@@ -286,14 +317,7 @@ func (c *Client) command(cmd string) (string, error) {
if _, err := fmt.Fprintf(c.conn, "C%d|%s\n", id, cmd); err != nil {
return "", err
}
_ = c.conn.SetReadDeadline(time.Now().Add(ioTimeout))
line, err := c.reader.ReadString('\n')
if err != nil {
return "", err
}
line = strings.TrimSpace(line)
c.parse(line)
return line, nil
return c.readReplyLocked(fmt.Sprintf("R%d|", id))
}
// parse handles "R<id>|0|<k=v …>" and "S0|<k=v …>" status lines.