merge: !7 fix/block-fetch-failover into deploy/all-2026-08-24

1 files changed, 43 insertions, 2 deletions

diff --git a/src/net.h b/src/net.h
index 600922a..fc48d0b 100644
--- a/src/net.h
+++ b/src/net.h
@@ -23,6 +23,12 @@ enum
 
 
 
+// Defined in main.cpp. True while this node is tracking the tip rather than
+// still catching up, measured off the age of our own best block -- see there
+// for why that and not a peer-reported height. Declared here because net.h is
+// parsed before main.h and CNode::AskFor needs it.
+bool IsBlockFetchNearTip();
+
 bool GetMyExternalIP(unsigned int& ipRet);
 CNode* ConnectNodeBtf(const string& strBtfAddr);
 CNode* ConnectNodeBtfResolved(const string& strBtfAddr, const string& strMeeting,
@@ -89,6 +95,15 @@ static const int          BTF_RECV_TIMEOUT_SECS    = 30 * 60;
 static const int          BTF_SEND_STALL_SECS      = 10 * 60;
 static const int          BTF_HANDSHAKE_GRACE_SECS = 60;
 
+// How long a requested block gets before it is asked for again, in seconds.
+// Used twice: CNode::AskFor spaces the queued per-announcer block retries this
+// far apart instead of the two minutes transactions get, and the failover
+// sweep in main.cpp re-issues a getdata to a different peer once a sent
+// request has gone unanswered this long. A block body is at most 1 MB and
+// somebody demonstrably has it -- they announced it -- so on this timescale
+// "not here yet" means "not coming from that peer", not "still in transit".
+static const int          BLOCK_FETCH_RETRY_SECS   = 15;
+
 // A serialized object cannot be larger than MAX_SIZE, so no valid network
 // message needs the old 256 MB header allowance. Keep the wire cap aligned with
 // what the deserializer can accept. How long a peer may sit on a partial
@@ -795,8 +810,34 @@ public:
         static int64 nLastTime;
         nLastTime = nNow = max(nNow, ++nLastTime);
 
-        // Each retry is 2 minutes after the last
-        nRequestTime = max(nRequestTime + 2 * 60 * 1000000, nNow);
+        // Each retry is 2 minutes after the last -- and because nRequestTime
+        // is shared across peers, the same spacing is what strings requests
+        // for one inv across its announcers. For transactions that is pacing;
+        // for a new block it was the stall of issue #33: nine peers announce
+        // the block, the first one asked does not serve it, and the ninth
+        // candidate is not even asked until sixteen minutes in, with the pool
+        // mining on the stale tip the whole time.
+        //
+        // Blocks retry on the fetch timescale, but only while we are at the
+        // tip. That is where the stall costs something -- the pool keeps
+        // handing out jobs against a dead tip -- and it is also where the
+        // spacing is nearly free: one block is in flight, and its body has
+        // almost always arrived before the second announcer's turn comes
+        // round, so AlreadyHave drops the duplicate before a getdata is sent.
+        //
+        // While catching up neither half holds. A peer working through a
+        // 500-deep queue can be minutes away from block N without anything
+        // being wrong, so at 15s the second announcer is asked at +15s, the
+        // third at +30s, and the bulk download arrives once per announcer --
+        // up to eight times over. Nothing caps that: the eight-entry cap is on
+        // mapBlockFetch, which is a different mechanism from this spacing.
+        // Two minutes is the right number there, and it is what this line did
+        // before. Failover at the tip does not depend on this being 15s in any
+        // case: mapBlockFetch re-issues a stalled getdata to the next peer on
+        // its own timer, which is what actually fixes #33.
+        bool fFast = (inv.type == MSG_BLOCK && IsBlockFetchNearTip());
+        int64 nRetryUsecs = (fFast ? BLOCK_FETCH_RETRY_SECS : 2 * 60) * 1000000LL;
+        nRequestTime = max(nRequestTime + nRetryUsecs, nNow);
         mapAskFor.insert(make_pair(nRequestTime, inv));
     }