Files
KamadoPool/api/internal/config/config.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

109 lines
3.3 KiB
Go

// Package config loads kamado-api configuration from environment variables.
// Missing required values are a hard error at startup; optional values get
// documented defaults.
package config
import (
"fmt"
"os"
"strconv"
"time"
)
type Config struct {
// HTTP server
ListenAddr string
// CKPool socket
CKPoolSockDir string
// Bitcoin Core RPC
BitcoinRPCURL string // full URL e.g. http://bitcoind:8332
BitcoinRPCUser string
BitcoinRPCPassword string
BitcoinRPCTimeout time.Duration
// ZMQ (Phase 2b)
BitcoinZMQBlock string // e.g. tcp://bitcoind:28332, empty to disable
// CKPool log file, for block-solve detection (Phase 2b)
CKPoolLogFile string
// SQLite DB path for persistence (Phase 2b)
DBPath string
// Poll interval for refreshing ckpool stats
PollInterval time.Duration
// Optional mempool.space-compatible explorer base URL. Empty means
// the UI uses the public mempool.space; non-empty means the user
// has pointed Kamado at their own instance via the StartOS config.
MempoolBaseURL string
// Directory ckpool's patched local_block_submit writes raw block
// hex into. Empty disables the fallback submitter.
PendingBlocksDir string
// Comma- or newline-separated list of fallback bitcoind RPC URLs
// that the submitter will try in order if a block stays pending
// past the grace window. Each entry can encode credentials inline:
// https://user:pass@host:8332/
// or without (e.g. an unauthenticated localhost backup node).
BackupRPCURLs string
// How long a pending block file must persist before the submitter
// will try fallback RPCs. Defaults to 30s — long enough for
// ckpool's own retry loop and a fast ckpool->bitcoind round-trip.
PendingBlocksGrace time.Duration
}
func FromEnv() (*Config, error) {
cfg := &Config{
ListenAddr: getenv("LISTEN_ADDR", ":8080"),
CKPoolSockDir: getenv("CKPOOL_SOCKDIR", "/run/ckpool"),
BitcoinRPCURL: os.Getenv("BITCOIN_RPC_URL"),
BitcoinRPCUser: os.Getenv("BITCOIN_RPC_USER"),
BitcoinRPCPassword: os.Getenv("BITCOIN_RPC_PASSWORD"),
BitcoinRPCTimeout: getenvDuration("BITCOIN_RPC_TIMEOUT", 10*time.Second),
BitcoinZMQBlock: os.Getenv("BITCOIN_ZMQ_BLOCK"),
CKPoolLogFile: getenv("CKPOOL_LOGFILE", "/var/log/ckpool/ckpool.log"),
DBPath: getenv("DB_PATH", "/var/lib/kamado/kamado.db"),
PollInterval: getenvDuration("POLL_INTERVAL", 5*time.Second),
MempoolBaseURL: os.Getenv("MEMPOOL_BASE_URL"),
PendingBlocksDir: os.Getenv("PENDING_BLOCKS_DIR"),
BackupRPCURLs: os.Getenv("BACKUP_RPC_URLS"),
PendingBlocksGrace: getenvDuration("PENDING_BLOCKS_GRACE", 30*time.Second),
}
if cfg.BitcoinRPCURL == "" {
return nil, fmt.Errorf("BITCOIN_RPC_URL is required")
}
if cfg.BitcoinRPCUser == "" || cfg.BitcoinRPCPassword == "" {
return nil, fmt.Errorf("BITCOIN_RPC_USER and BITCOIN_RPC_PASSWORD are required")
}
return cfg, nil
}
func getenv(key, def string) string {
if v := os.Getenv(key); v != "" {
return v
}
return def
}
func getenvDuration(key string, def time.Duration) time.Duration {
v := os.Getenv(key)
if v == "" {
return def
}
// Accept both Go duration syntax ("5s", "10s") and bare seconds ("10").
if d, err := time.ParseDuration(v); err == nil {
return d
}
if n, err := strconv.Atoi(v); err == nil {
return time.Duration(n) * time.Second
}
return def
}