Files
KamadoPool/ckpool/patches/0004-dump-pending-block-for-fallback.patch
T
satoshi 99302cf4af Tighten fallback latency + alert UI on degraded states
Submit-first ordering. Patch 0004 now calls generator_submitblock
BEFORE writing the pending-block hex to disk. The happy path adds zero
disk I/O — we only dump when the primary returned false. The same
patch bounds generator_submitblock's "no live current_si" spin to
~3s instead of the original infinite loop, so a permanently-down
primary doesn't pin the stratifier; the bounded spin lets the caller
return false and lets local_block_submit dump for kamado-api to take
over.

Default grace lowered from 30s to 3s. With ckpool's bounded spin and
sub-second sweep cadence, the fallback now reacts within ~4s of a
failed primary submit — fast enough that the work is still relevant
for the current chain tip. The submitter's sweep poll dropped to 1s
to match.

UI HealthBanners. New top-of-page strip surfaces:
  * Fallback used (red banner, 24h after most recent event):
    "primary bitcoind didn't accept; backup X took over Y ago"
  * Submit gap (orange banner, only when no recent fallback):
    "N blocks attempted but unconfirmed — configure backups"
  * ZMQ stale (orange banner): no hashblock frame in 30+ minutes
Operators see degraded-but-not-fatal states without checking logs.

Startup readiness gate. main now waits up to 8s on agg.Ready() before
starting the HTTP server so the very first /api/snapshot doesn't show
all-zero state during the aggregator's first refresh. Capped so a
permanently-down bitcoind can't block startup; /healthz is honest
about the degraded state once we do start serving.
2026-04-27 21:53:23 +03:00

126 lines
4.5 KiB
Diff

diff --git a/src/generator.c b/src/generator.c
index 22e2e08..438b199 100644
--- a/src/generator.c
+++ b/src/generator.c
@@ -351,11 +351,25 @@ bool generator_submitblock(ckpool_t *ckp, const char *buf)
server_instance_t *si;
bool warn = false;
connsock_t *cs;
+ /* Bound the wait for current_si so a permanently-down primary
+ * bitcoind does not pin the caller forever. After this many 10ms
+ * sleeps (~3s), return false so the caller (in our fork:
+ * local_block_submit) can hand off to kamado-api's fallback
+ * broadcaster instead of blocking the stratifier on a dead RPC.
+ * Original upstream behavior was to spin indefinitely; we trade
+ * that for predictable latency. */
+ const int max_no_si_iters = 300;
+ int no_si_iters = 0;
while (unlikely(!(si = gdata->current_si))) {
if (!warn)
- LOGWARNING("No live current server in generator_blocksubmit! Resubmitting indefinitely!");
+ LOGWARNING("No live current server in generator_blocksubmit! Waiting up to ~3s before giving up so fallback can take over...");
warn = true;
+ if (++no_si_iters > max_no_si_iters) {
+ LOGWARNING("generator_submitblock: no live primary server after %d ms, returning false",
+ no_si_iters * 10);
+ return false;
+ }
cksleep_ms(10);
}
cs = &si->cs;
diff --git a/src/stratifier.c b/src/stratifier.c
index 52da790..7caf179 100644
--- a/src/stratifier.c
+++ b/src/stratifier.c
@@ -2069,16 +2069,75 @@ process_block(const workbase_t *wb, const char *coinbase, const int cblen,
return gbt_block;
}
-/* Submit block data locally, absorbing and freeing gbt_block */
+/* Write the raw block hex to a sidecar file under <logdir>/pending-blocks/
+ * so the external watcher (kamado-api) can re-broadcast via fallback RPC
+ * nodes. Best-effort: any error here is logged at INFO and never blocks
+ * the caller. Called only after the primary submit fails so the happy
+ * path stays disk-free. */
+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) for fallback broadcast",
+ height, out_path, blen);
+}
+
+/* Submit block data locally, absorbing and freeing gbt_block.
+ *
+ * Order matters: we always try ckp's primary bitcoind FIRST so the
+ * happy path adds zero latency or disk I/O. Only when the primary
+ * rejects (or generator_submitblock returns false for any other
+ * reason) do we dump the raw hex to <logdir>/pending-blocks/ so the
+ * kamado-api watcher can re-broadcast via fallback RPC nodes. */
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);
+
+ /* Primary submit first — this is the latency-critical path. */
+ ret = generator_submitblock(ckp, gbt_block);
+
+ /* Only touch disk if the primary didn't accept. */
+ if (!ret) {
+ kamado_dump_pending_block(ckp, gbt_block, rhash, height,
+ pending_path, sizeof(pending_path));
+ }
+
+ free(gbt_block);
generator_preciousblock(ckp, rhash);
/* Check failures that may be inconclusive but were submitted via other
@@ -2099,6 +2158,10 @@ static bool local_block_submit(ckpool_t *ckp, char *gbt_block, const uchar *flip
height, ret ? "ACCEPTED" : "REJECTED");
}
}
+ /* Block ended up on chain (either initial submit or precious-block
+ * recovery): the dump file is no longer needed. */
+ if (ret && pending_path[0])
+ unlink(pending_path);
return ret;
}