Files
KamadoPool/api/internal/httpapi/server.go
T
satoshi a4a894e196 P1 reliability + block-broadcast fallback path
P1 audits / fixes:

* Bitcoin Core RPC now retries up to 3 times with linear backoff on
  transport errors, 5xx responses, and warm-up/loading RPC errors
  (code -28). Hard "no" answers (block-not-found etc.) bubble up
  immediately so we don't mask real errors.

* WebSocket hub disconnects clients that miss 6 consecutive broadcasts
  (~30s with the default poll cadence). Stuck readers no longer hold
  stale snapshots indefinitely or freeze hub state.

* ZMQ subscriber freshness: aggregator records the last-event
  timestamp, surfaces zmq_enabled / has_last_zmq_event /
  last_zmq_event_age in the snapshot. /healthz flags zmq_stale when
  the gap exceeds 30 minutes.

* /healthz expanded with submit_attempts / submits_confirmed /
  submit_gap, fallback_submits_total + last_fallback_*, and the zmq
  staleness check. Now usable as a real-world ops dashboard signal.

Block-broadcast fallback (new feature):

  * ckpool patch 0004: hooks local_block_submit to write the raw block
    hex to <logdir>/pending-blocks/<height>-<hash16>.hex right before
    invoking generator_submitblock. Unlinks on success. ckpool's normal
    flow is otherwise untouched.

  * api/internal/blocksubmit: watcher polls the dir every 5s. Files
    sitting longer than the grace window (default 30s, configurable)
    are re-broadcast through operator-supplied backup RPC URLs in
    sequence. Treats both null and any "duplicate*" reject reason as
    success (the block landed). Pre-checks the primary chain first so
    a stale file from a successful-but-unlinked submit gets cleaned
    up without bothering fallbacks.

  * Aggregator records each successful fallback submission as a
    persistent counter and surfaces it in the snapshot so the UI can
    show a "primary bitcoind isn't accepting submits" alert.

  * Config: BACKUP_RPC_URLS (comma- or newline-separated, with
    optional inline credentials) plus PENDING_BLOCKS_DIR and
    PENDING_BLOCKS_GRACE. URLs are parsed via net/url so
    https://user:pass@host:port/ works cleanly.

The fallback is opt-in and disabled by default. Once enabled with at
least one URL, a primary bitcoind outage at the moment of solving no
longer means a lost block — kamado-api re-broadcasts via whichever
backup the operator trusts (a second self-hosted node, an
authenticated public RPC service, etc.).
2026-04-27 21:25:56 +03:00

165 lines
5.3 KiB
Go

// Package httpapi serves the Kamado REST API. WebSocket push and static
// UI serving land in a follow-up commit.
package httpapi
import (
"encoding/json"
"errors"
"io/fs"
"log/slog"
"net/http"
"strings"
"github.com/kamadopool/kamado-api/internal/state"
"github.com/kamadopool/kamado-api/internal/webui"
)
type Server struct {
Agg *state.Aggregator
Hub *Hub
Log *slog.Logger
}
func New(agg *state.Aggregator, log *slog.Logger) *Server {
return &Server{Agg: agg, Hub: NewHub(), Log: log}
}
// Handler returns an http.Handler with all kamado routes mounted under
// /api and the embedded Svelte dashboard served under /. Unknown
// non-/api paths fall back to index.html for SPA-style routing.
func (s *Server) Handler() http.Handler {
mux := http.NewServeMux()
mux.HandleFunc("GET /api/health", s.health)
mux.HandleFunc("GET /api/pool", s.pool)
mux.HandleFunc("GET /api/users", s.users)
mux.HandleFunc("GET /api/workers", s.workers)
mux.HandleFunc("GET /api/clients", s.clients)
mux.HandleFunc("GET /api/blocks", s.blocks)
mux.HandleFunc("GET /api/snapshot", s.snapshot)
mux.HandleFunc("GET /api/ws", s.handleWS)
mux.Handle("/", spaHandler(webui.FS()))
return mux
}
// spaHandler serves static files from the embedded dist tree and
// falls back to index.html on 404 so client-side routing works. It
// refuses anything under /api to keep the contract with mux patterns
// explicit (those routes register their own handlers above).
func spaHandler(root fs.FS) http.Handler {
fileServer := http.FileServerFS(root)
return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
// Defence-in-depth — /api routes are matched by the mux first
// with their GET patterns, but a bare POST /api/... would fall
// through here. Return 404 so we don't accidentally shadow
// API semantics with HTML.
if strings.HasPrefix(r.URL.Path, "/api/") || r.URL.Path == "/api" {
http.NotFound(w, r)
return
}
// Fast path: exact file exists in the embed.
clean := strings.TrimPrefix(r.URL.Path, "/")
if clean == "" {
clean = "index.html"
}
if _, err := fs.Stat(root, clean); err == nil {
fileServer.ServeHTTP(w, r)
return
} else if !errors.Is(err, fs.ErrNotExist) {
http.Error(w, "webui: "+err.Error(), http.StatusInternalServerError)
return
}
// SPA fallback: serve index.html with a 200 so reloads on a
// client-side route don't 404.
r2 := r.Clone(r.Context())
r2.URL.Path = "/"
fileServer.ServeHTTP(w, r2)
})
}
func writeJSON(w http.ResponseWriter, status int, v any) {
w.Header().Set("Content-Type", "application/json; charset=utf-8")
w.Header().Set("Cache-Control", "no-store")
w.WriteHeader(status)
_ = json.NewEncoder(w).Encode(v)
}
// ---- handlers ---------------------------------------------------------
func (s *Server) health(w http.ResponseWriter, r *http.Request) {
snap := s.Agg.Snapshot()
status := http.StatusOK
// Submit-attempt gap: if we've tried to submit more blocks than have
// been confirmed, surface the gap. A non-zero gap is a strong signal
// even if everything else looks healthy.
submitGap := snap.BlockSubmitAttempts - snap.BlockSubmitsConfirmed
if submitGap < 0 {
submitGap = 0
}
// ZMQ freshness: only meaningful if the operator enabled it. Stale
// = no event in 30 minutes (typical mainnet block interval is 10
// min, but spikes happen).
zmqStale := false
if snap.ZMQEnabled && snap.HasLastZMQEvent && snap.LastZMQEventAge > 1800 {
zmqStale = true
}
overallOK := snap.CKPoolOK && snap.BitcoinOK && submitGap == 0 && !zmqStale
if !snap.CKPoolOK || !snap.BitcoinOK {
status = http.StatusServiceUnavailable
}
writeJSON(w, status, map[string]any{
"ok": overallOK,
"ckpool": snap.CKPoolOK,
"bitcoin": snap.BitcoinOK,
"submit_attempts": snap.BlockSubmitAttempts,
"submits_confirmed": snap.BlockSubmitsConfirmed,
"submit_gap": submitGap,
"fallback_submits_total": snap.FallbackSubmitsTotal,
"last_fallback_submit_at": snap.LastFallbackSubmitAt,
"last_fallback_via": snap.LastFallbackVia,
"zmq_enabled": snap.ZMQEnabled,
"zmq_event_age_seconds": snap.LastZMQEventAge,
"zmq_has_event": snap.HasLastZMQEvent,
"zmq_stale": zmqStale,
"last_error": snap.LastError,
})
}
func (s *Server) snapshot(w http.ResponseWriter, r *http.Request) {
writeJSON(w, http.StatusOK, s.Agg.Snapshot())
}
func (s *Server) pool(w http.ResponseWriter, r *http.Request) {
snap := s.Agg.Snapshot()
writeJSON(w, http.StatusOK, map[string]any{
"pool": snap.Pool,
"uptime_seconds": snap.Uptime,
"hashrate_hs_1m": snap.HashrateHs,
"hashrate_hs_5m": snap.HashrateHs5m,
"hashrate_hs_1h": snap.HashrateHs1h,
"hashrate_hs_24h": snap.HashrateHs24h,
"chain": snap.Chain,
"network_hashrate_hs": snap.NetworkHashrateHs,
})
}
func (s *Server) users(w http.ResponseWriter, r *http.Request) {
writeJSON(w, http.StatusOK, s.Agg.Snapshot().Users)
}
func (s *Server) workers(w http.ResponseWriter, r *http.Request) {
writeJSON(w, http.StatusOK, s.Agg.Snapshot().Workers)
}
func (s *Server) clients(w http.ResponseWriter, r *http.Request) {
writeJSON(w, http.StatusOK, s.Agg.Snapshot().Clients)
}
func (s *Server) blocks(w http.ResponseWriter, r *http.Request) {
writeJSON(w, http.StatusOK, s.Agg.Blocks())
}