diff options
| author | bitflash-maintainer <noreply@bitflash.invalid> | 2026-09-02 14:46:38 +0000 |
|---|---|---|
| committer | bitflash-maintainer <noreply@bitflash.invalid> | 2026-09-02 14:46:38 +0000 |
| commit | 9a409d8ba97251f29ba80913a4014b8a369c52c0 (patch) | |
| tree | b3e5d74b827f29af8fe36a4409abdde8259e50b2 /src/rpc.cpp | |
| parent | e4f898c4a6b9900553c64b9804889b5fdae3e55f (diff) | |
pool: advertise a rendezvous only once registered, and log the pin
Issue #2 reported that /rvrelay does not govern registration. It does:
BtfAllRelays() returns vBtfMeetingRelays alone when fBtfRelayPinned, and
every relay-choosing site -- the pool's AcceptLoopFn, the node's
ThreadBtfAccept, and the dial path -- draws from it. vBtfMeetingRelays
has exactly one writer, the pin itself. A pinned pool therefore spawns
one accept thread, at the pin, and no discovered relay is registered at.
The registration the incident actually caught was not the pool's. The
"registered at" line it quotes exists only in ThreadBtfAccept, and
90.156.222.107:8434 is not a stranger's relay -- it is the third
hardcoded seed, one of the three ThreadBtfAccept picks between at random
when no pin is in force. That relay is only reachable with the pin
absent, so the binary that logged it did not have one; both the pin and
the operator-mode skip that keeps a pool out of that thread landed two
days before the observation.
What was genuinely wrong is that none of this could be read off a log.
The pool announced no successful registration at all, and retried
failures at one flat line, so "is this pool registered where its
descriptor says" had no answer. So:
- Advertise the relay after registering at it, not before. The
optimistic order published a meeting node we were not yet listed at,
and a miner resolving the descriptor inside that window spent its
dial on a relay holding no registration for us. ThreadBtfAccept has
always ordered it this way; the pool had not.
- Log the relay registration succeeds at, name the pin when one is in
force, and name each discovered relay the pin excludes.
- Escalate when a pinned relay keeps refusing: a pin has no fallback,
so an unregistered pin means the pool is unreachable, and that now
says so instead of scrolling past.
- Refuse to advertise a non-pinned relay in BtfSetActiveRelay. No
caller can reach it today, but the descriptor is the one thing a
miner obeys, so the invariant is enforced at the sink rather than
retrusted to every future caller.
Does not touch the registration-consumption race: the pool still gives
up its registration on each pairing and re-registers after wrap-and-push.
Moving the advertise call inside that loop does not widen the window, it
only stops the descriptor naming a relay we never reached.
Diffstat (limited to 'src/rpc.cpp')
| -rw-r--r-- | src/rpc.cpp | 61 |
1 files changed, 52 insertions, 9 deletions
diff --git a/src/rpc.cpp b/src/rpc.cpp index a4b53ca..a3560ff 100644 --- a/src/rpc.cpp +++ b/src/rpc.cpp | |||
| @@ -4947,13 +4947,19 @@ static void AcceptOneFn(void* arg) | |||
| 4947 | std::string host = relay.substr(0, colon); | 4947 | std::string host = relay.substr(0, colon); |
| 4948 | int port = atoi(relay.substr(colon + 1).c_str()); | 4948 | int port = atoi(relay.substr(colon + 1).c_str()); |
| 4949 | 4949 | ||
| 4950 | LogPrint("pool", "[pool] accept thread started for relay %s\n", relay.c_str()); | 4950 | LogPrint("pool", "[pool] accept thread started for relay %s%s\n", relay.c_str(), |
| 4951 | fBtfRelayPinned ? " (/rvrelay pin)" : ""); | ||
| 4952 | |||
| 4953 | // Registration health for this relay. A pin has no fallback, so a pin that | ||
| 4954 | // never registers means the pool is simply unreachable -- and that has to | ||
| 4955 | // be loud. The 2026-07-30 incident went unnoticed because this loop logged | ||
| 4956 | // failures at one flat line and success not at all, so "which relay is this | ||
| 4957 | // pool actually registered at" could not be answered from the log. | ||
| 4958 | int nConsecFail = 0; | ||
| 4959 | int64 nFirstFail = 0; | ||
| 4960 | bool fEverRegistered = false; | ||
| 4951 | 4961 | ||
| 4952 | while (!fShutdown && gPoolRunning) { | 4962 | while (!fShutdown && gPoolRunning) { |
| 4953 | // Advertise this relay as the pool's meeting node BEFORE registering, | ||
| 4954 | // so that miners which resolve our descriptor find a relay where the | ||
| 4955 | // pool (not the node's peer-accept) holds the registration. | ||
| 4956 | BtfSetActiveRelay(relay); | ||
| 4957 | // Returns as soon as the relay lists us -- registered, not yet paired. | 4963 | // Returns as soon as the relay lists us -- registered, not yet paired. |
| 4958 | btf::RvSocket rv = btf::RvServiceRegister(host.c_str(), (unsigned short)port, pk); | 4964 | btf::RvSocket rv = btf::RvServiceRegister(host.c_str(), (unsigned short)port, pk); |
| 4959 | 4965 | ||
| @@ -4962,12 +4968,36 @@ static void AcceptOneFn(void* arg) | |||
| 4962 | break; | 4968 | break; |
| 4963 | } | 4969 | } |
| 4964 | if (rv == btf::RV_INVALID) { | 4970 | if (rv == btf::RV_INVALID) { |
| 4965 | LogPrint("pool", "[pool] relay %s: RvServiceRegister failed" | 4971 | nConsecFail++; |
| 4966 | " -- backing off 30s before retry\n", relay.c_str()); | 4972 | if (nFirstFail == 0) nFirstFail = GetTime(); |
| 4973 | LogPrint("pool", "[pool] relay %s: registration failed (attempt %d," | ||
| 4974 | " failing for %llds) -- backing off 30s before retry\n", | ||
| 4975 | relay.c_str(), nConsecFail, (long long)(GetTime() - nFirstFail)); | ||
| 4976 | if (fBtfRelayPinned && (nConsecFail == 3 || nConsecFail % 10 == 0)) | ||
| 4977 | LogPrint("pool", "[pool] WARNING: pinned relay %s refused registration" | ||
| 4978 | " %d times running (%llds); /rvrelay leaves no fallback, so" | ||
| 4979 | " miners cannot reach this pool%s\n", | ||
| 4980 | relay.c_str(), nConsecFail, (long long)(GetTime() - nFirstFail), | ||
| 4981 | fEverRegistered ? "" : " -- it has never registered once"); | ||
| 4967 | for (int i = 0; i < 30 && !fShutdown && gPoolRunning; i++) Sleep(1000); | 4982 | for (int i = 0; i < 30 && !fShutdown && gPoolRunning; i++) Sleep(1000); |
| 4968 | continue; | 4983 | continue; |
| 4969 | } | 4984 | } |
| 4970 | 4985 | ||
| 4986 | // Advertise THIS relay only now. Setting it before the call published a | ||
| 4987 | // meeting node we were not yet listed at, so a miner resolving the | ||
| 4988 | // descriptor inside that window burned its dial on a relay holding no | ||
| 4989 | // registration for us. net.cpp's peer-accept has always ordered it this | ||
| 4990 | // way round; the pool had not. | ||
| 4991 | BtfSetActiveRelay(relay); | ||
| 4992 | if (!fEverRegistered || nConsecFail > 0) | ||
| 4993 | LogPrint("pool", "[pool] registered at relay %s%s%s -- advertising it as" | ||
| 4994 | " the pool's meeting node\n", relay.c_str(), | ||
| 4995 | fBtfRelayPinned ? " (/rvrelay pin)" : "", | ||
| 4996 | nConsecFail > 0 ? ", recovered" : ""); | ||
| 4997 | fEverRegistered = true; | ||
| 4998 | nConsecFail = 0; | ||
| 4999 | nFirstFail = 0; | ||
| 5000 | |||
| 4971 | // Block for a miner to actually arrive. RvServiceRegister used to do | 5001 | // Block for a miner to actually arrive. RvServiceRegister used to do |
| 4972 | // this itself and returned with the relay's 0x01 pairing byte already | 5002 | // this itself and returned with the relay's 0x01 pairing byte already |
| 4973 | // consumed; it no longer does. Without waiting here, BtfServiceWrap | 5003 | // consumed; it no longer does. Without waiting here, BtfServiceWrap |
| @@ -5022,9 +5052,21 @@ static void AcceptLoopFn(void*) | |||
| 5022 | LogPrint("pool", "[pool] .btf identity ready after %ds\n", waitSecs * 2); | 5052 | LogPrint("pool", "[pool] .btf identity ready after %ds\n", waitSecs * 2); |
| 5023 | 5053 | ||
| 5024 | std::set<std::string> spawned; // relays we've already started a thread for | 5054 | std::set<std::string> spawned; // relays we've already started a thread for |
| 5055 | std::set<std::string> skipped; // discovered relays the pin excluded, logged once each | ||
| 5025 | 5056 | ||
| 5026 | while (!fShutdown && gPoolRunning) { | 5057 | while (!fShutdown && gPoolRunning) { |
| 5058 | // BtfAllRelays() already honours the pin: with /rvrelay set it returns | ||
| 5059 | // vBtfMeetingRelays alone, so no thread is ever spawned for a | ||
| 5060 | // discovered relay. Name the ones it drops -- a pool registering at a | ||
| 5061 | // stranger's relay is exactly the thing that should not be silent. | ||
| 5027 | vector<string> relays = BtfAllRelays(); | 5062 | vector<string> relays = BtfAllRelays(); |
| 5063 | if (fBtfRelayPinned) { | ||
| 5064 | for (const string& r : BtfDiscoveredRelays()) | ||
| 5065 | if (std::find(relays.begin(), relays.end(), r) == relays.end() && | ||
| 5066 | skipped.insert(r).second) | ||
| 5067 | LogPrint("pool", "[pool] not registering at discovered relay %s" | ||
| 5068 | " -- /rvrelay pins the relay list\n", r.c_str()); | ||
| 5069 | } | ||
| 5028 | if (relays.empty()) { | 5070 | if (relays.empty()) { |
| 5029 | LogPrint("pool", "[pool] no relays available -- miners cannot connect yet\n"); | 5071 | LogPrint("pool", "[pool] no relays available -- miners cannot connect yet\n"); |
| 5030 | } else { | 5072 | } else { |
| @@ -5040,8 +5082,9 @@ static void AcceptLoopFn(void*) | |||
| 5040 | relay.c_str()); | 5082 | relay.c_str()); |
| 5041 | } else { | 5083 | } else { |
| 5042 | spawned.insert(relay); | 5084 | spawned.insert(relay); |
| 5043 | LogPrint("pool", "[pool] accept thread spawned for relay %s" | 5085 | LogPrint("pool", "[pool] accept thread spawned for relay %s%s" |
| 5044 | " (%zu total)\n", relay.c_str(), spawned.size()); | 5086 | " (%zu total)\n", relay.c_str(), |
| 5087 | fBtfRelayPinned ? " (/rvrelay pin)" : "", spawned.size()); | ||
| 5045 | } | 5088 | } |
| 5046 | } | 5089 | } |
| 5047 | } | 5090 | } |