satoshi
a4a894e196
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.).
81 lines
2.6 KiB
Diff
81 lines
2.6 KiB
Diff
diff --git a/src/stratifier.c b/src/stratifier.c
|
|
index 52da790..815eb01 100644
|
|
--- a/src/stratifier.c
|
|
+++ b/src/stratifier.c
|
|
@@ -2069,16 +2069,64 @@ process_block(const workbase_t *wb, const char *coinbase, const int cblen,
|
|
return gbt_block;
|
|
}
|
|
|
|
+/* Write the raw block hex to a sidecar file under <logdir>/pending-blocks/
|
|
+ * before submitting, so an external watcher (kamado-api) can re-broadcast
|
|
+ * via fallback RPC nodes if our primary bitcoind doesn't accept it. The
|
|
+ * file is unlinked once generator_submitblock returns success. Best-
|
|
+ * effort: any error here is logged at INFO and never blocks the submit. */
|
|
+static void kamado_dump_pending_block(ckpool_t *ckp, const char *gbt_block,
|
|
+ const char *rhash, int height,
|
|
+ char *out_path, size_t out_path_len)
|
|
+{
|
|
+ char dir[512] = {};
|
|
+ int fd;
|
|
+ size_t blen;
|
|
+ ssize_t w;
|
|
+
|
|
+ out_path[0] = '\0';
|
|
+ if (!ckp || !ckp->logdir || !gbt_block)
|
|
+ return;
|
|
+ snprintf(dir, sizeof(dir), "%spending-blocks", ckp->logdir);
|
|
+ if (mkdir(dir, 0750) < 0 && errno != EEXIST) {
|
|
+ LOGINFO("kamado: mkdir %s failed: %s", dir, strerror(errno));
|
|
+ return;
|
|
+ }
|
|
+ snprintf(out_path, out_path_len, "%s/%d-%.16s.hex", dir, height, rhash);
|
|
+ fd = open(out_path, O_WRONLY | O_CREAT | O_TRUNC, 0640);
|
|
+ if (fd < 0) {
|
|
+ LOGINFO("kamado: open %s failed: %s", out_path, strerror(errno));
|
|
+ out_path[0] = '\0';
|
|
+ return;
|
|
+ }
|
|
+ blen = strlen(gbt_block);
|
|
+ w = write(fd, gbt_block, blen);
|
|
+ close(fd);
|
|
+ if (w != (ssize_t)blen) {
|
|
+ LOGINFO("kamado: short write to %s (%zd/%zu)", out_path, w, blen);
|
|
+ unlink(out_path);
|
|
+ out_path[0] = '\0';
|
|
+ return;
|
|
+ }
|
|
+ LOGNOTICE("kamado: dumped pending block height %d to %s (%zu bytes)",
|
|
+ height, out_path, blen);
|
|
+}
|
|
+
|
|
/* Submit block data locally, absorbing and freeing gbt_block */
|
|
static bool local_block_submit(ckpool_t *ckp, char *gbt_block, const uchar *flip32, int height)
|
|
{
|
|
- bool ret = generator_submitblock(ckp, gbt_block);
|
|
char heighthash[68] = {}, rhash[68] = {};
|
|
+ char pending_path[512] = {};
|
|
uchar swap256[32];
|
|
+ bool ret;
|
|
|
|
- free(gbt_block);
|
|
swap_256(swap256, flip32);
|
|
__bin2hex(rhash, swap256, 32);
|
|
+ kamado_dump_pending_block(ckp, gbt_block, rhash, height,
|
|
+ pending_path, sizeof(pending_path));
|
|
+
|
|
+ ret = generator_submitblock(ckp, gbt_block);
|
|
+
|
|
+ free(gbt_block);
|
|
generator_preciousblock(ckp, rhash);
|
|
|
|
/* Check failures that may be inconclusive but were submitted via other
|
|
@@ -2099,6 +2147,8 @@ static bool local_block_submit(ckpool_t *ckp, char *gbt_block, const uchar *flip
|
|
height, ret ? "ACCEPTED" : "REJECTED");
|
|
}
|
|
}
|
|
+ if (ret && pending_path[0])
|
|
+ unlink(pending_path);
|
|
return ret;
|
|
}
|
|
|