init: add utxo snapshot detection

Add functionality for activating a snapshot-based chainstate if one is
detected on-disk.

Also cautiously initialize chainstate cache usages so that we don't
somehow blow past our cache allowances during initialization, then
rebalance at the end of init.

Co-authored-by: Russell Yanofsky <[email protected]>

Author: jamesob

src/node/chainstate.cpp

@@ -48,10 +48,15 @@ ChainstateLoadResult LoadChainstate(ChainstateManager& chainman, const CacheSize
     }
 
     LOCK(cs_main);
-    chainman.InitializeChainstate(options.mempool);
     chainman.m_total_coinstip_cache = cache_sizes.coins;
     chainman.m_total_coinsdb_cache = cache_sizes.coins_db;
 
+    // Load the fully validated chainstate.
+    chainman.InitializeChainstate(options.mempool);
+
+    // Load a chain created from a UTXO snapshot, if any exist.
+    chainman.DetectSnapshotChainstate(options.mempool);
+
     auto& pblocktree{chainman.m_blockman.m_block_tree_db};
     // new CBlockTreeDB tries to delete the existing file, which
     // fails if it's still open from the previous loop. Close it first:
@@ -98,12 +103,20 @@ ChainstateLoadResult LoadChainstate(ChainstateManager& chainman, const CacheSize
         return {ChainstateLoadStatus::FAILURE, _("Error initializing block database")};
     }
 
+    // Conservative value which is arbitrarily chosen, as it will ultimately be changed
+    // by a call to `chainman.MaybeRebalanceCaches()`. We just need to make sure
+    // that the sum of the two caches (40%) does not exceed the allowable amount
+    // during this temporary initialization state.
+    double init_cache_fraction = 0.2;
+
     // At this point we're either in reindex or we've loaded a useful
     // block tree into BlockIndex()!
 
     for (Chainstate* chainstate : chainman.GetAll()) {
+        LogPrintf("Initializing chainstate %s\n", chainstate->ToString());
+
         chainstate->InitCoinsDB(
-            /*cache_size_bytes=*/cache_sizes.coins_db,
+            /*cache_size_bytes=*/chainman.m_total_coinsdb_cache * init_cache_fraction,
             /*in_memory=*/options.coins_db_in_memory,
             /*should_wipe=*/options.reindex || options.reindex_chainstate);
 
@@ -125,7 +138,7 @@ ChainstateLoadResult LoadChainstate(ChainstateManager& chainman, const CacheSize
         }
 
         // The on-disk coinsdb is now in a good state, create the cache
-        chainstate->InitCoinsCache(cache_sizes.coins);
+        chainstate->InitCoinsCache(chainman.m_total_coinstip_cache * init_cache_fraction);
         assert(chainstate->CanFlushToDisk());
 
         if (!is_coinsview_empty(chainstate)) {
@@ -146,6 +159,11 @@ ChainstateLoadResult LoadChainstate(ChainstateManager& chainman, const CacheSize
         };
     }
 
+    // Now that chainstates are loaded and we're able to flush to
+    // disk, rebalance the coins caches to desired levels based
+    // on the condition of each chainstate.
+    chainman.MaybeRebalanceCaches();
+
     return {ChainstateLoadStatus::SUCCESS, {}};
 }
 

src/node/utxo_snapshot.cpp

@@ -8,6 +8,7 @@
 #include <logging.h>
 #include <streams.h>
 #include <uint256.h>
+#include <util/system.h>
 #include <validation.h>
 
 #include <cstdio>
@@ -76,4 +77,15 @@ std::optional<uint256> ReadSnapshotBaseBlockhash(fs::path chaindir)
     return base_blockhash;
 }
 
+std::optional<fs::path> FindSnapshotChainstateDir()
+{
+    fs::path possible_dir =
+        gArgs.GetDataDirNet() / fs::u8path(strprintf("chainstate%s", SNAPSHOT_CHAINSTATE_SUFFIX));
+
+    if (fs::exists(possible_dir)) {
+        return possible_dir;
+    }
+    return std::nullopt;
+}
+
 } // namespace node

src/node/utxo_snapshot.h

@@ -58,8 +58,14 @@ bool WriteSnapshotBaseBlockhash(Chainstate& snapshot_chainstate)
 std::optional<uint256> ReadSnapshotBaseBlockhash(fs::path chaindir)
     EXCLUSIVE_LOCKS_REQUIRED(::cs_main);
 
+//! Suffix appended to the chainstate (leveldb) dir when created based upon
+//! a snapshot.
 constexpr std::string_view SNAPSHOT_CHAINSTATE_SUFFIX = "_snapshot";
 
+
+//! Return a path to the snapshot-based chainstate dir, if one exists.
+std::optional<fs::path> FindSnapshotChainstateDir();
+
 } // namespace node
 
 #endif // BITCOIN_NODE_UTXO_SNAPSHOT_H

src/test/validation_chainstatemanager_tests.cpp

@@ -63,7 +63,7 @@ BOOST_AUTO_TEST_CASE(chainstatemanager)
     // Create a snapshot-based chainstate.
     //
     const uint256 snapshot_blockhash = GetRandHash();
-    Chainstate& c2 = WITH_LOCK(::cs_main, return manager.InitializeChainstate(
+    Chainstate& c2 = WITH_LOCK(::cs_main, return manager.ActivateExistingSnapshot(
         &mempool, snapshot_blockhash));
     chainstates.push_back(&c2);
 
@@ -133,7 +133,7 @@ BOOST_AUTO_TEST_CASE(chainstatemanager_rebalance_caches)
 
     // Create a snapshot-based chainstate.
     //
-    Chainstate& c2 = WITH_LOCK(cs_main, return manager.InitializeChainstate(&mempool, GetRandHash()));
+    Chainstate& c2 = WITH_LOCK(cs_main, return manager.ActivateExistingSnapshot(&mempool, GetRandHash()));
     chainstates.push_back(&c2);
     c2.InitCoinsDB(
         /*cache_size_bytes=*/1 << 23, /*in_memory=*/true, /*should_wipe=*/false);
@@ -383,7 +383,7 @@ BOOST_FIXTURE_TEST_CASE(chainstatemanager_loadblockindex, TestChain100Setup)
     BOOST_CHECK_EQUAL(expected_assumed_valid, num_assumed_valid);
 
     Chainstate& cs2 = WITH_LOCK(::cs_main,
-        return chainman.InitializeChainstate(&mempool, GetRandHash()));
+        return chainman.ActivateExistingSnapshot(&mempool, GetRandHash()));
 
     reload_all_block_indexes();
 

src/validation.cpp

@@ -4744,28 +4744,15 @@ std::vector<Chainstate*> ChainstateManager::GetAll()
     return out;
 }
 
-Chainstate& ChainstateManager::InitializeChainstate(
-    CTxMemPool* mempool, const std::optional<uint256>& snapshot_blockhash)
+Chainstate& ChainstateManager::InitializeChainstate(CTxMemPool* mempool)
 {
     AssertLockHeld(::cs_main);
-    bool is_snapshot = snapshot_blockhash.has_value();
-    std::unique_ptr<Chainstate>& to_modify =
-        is_snapshot ? m_snapshot_chainstate : m_ibd_chainstate;
+    assert(!m_ibd_chainstate);
+    assert(!m_active_chainstate);
 
-    if (to_modify) {
-        throw std::logic_error("should not be overwriting a chainstate");
-    }
-    to_modify.reset(new Chainstate(mempool, m_blockman, *this, snapshot_blockhash));
-
-    // Snapshot chainstates and initial IBD chaintates always become active.
-    if (is_snapshot || (!is_snapshot && !m_active_chainstate)) {
-        LogPrintf("Switching active chainstate to %s\n", to_modify->ToString());
-        m_active_chainstate = to_modify.get();
-    } else {
-        throw std::logic_error("unexpected chainstate activation");
-    }
-
-    return *to_modify;
+    m_ibd_chainstate = std::make_unique<Chainstate>(mempool, m_blockman, *this);
+    m_active_chainstate = m_ibd_chainstate.get();
+    return *m_active_chainstate;
 }
 
 const AssumeutxoData* ExpectedAssumeutxo(
@@ -5134,3 +5121,31 @@ ChainstateManager::~ChainstateManager()
         i.clear();
     }
 }
+
+bool ChainstateManager::DetectSnapshotChainstate(CTxMemPool* mempool)
+{
+    assert(!m_snapshot_chainstate);
+    std::optional<fs::path> path = node::FindSnapshotChainstateDir();
+    if (!path) {
+        return false;
+    }
+    std::optional<uint256> base_blockhash = node::ReadSnapshotBaseBlockhash(*path);
+    if (!base_blockhash) {
+        return false;
+    }
+    LogPrintf("[snapshot] detected active snapshot chainstate (%s) - loading\n",
+        fs::PathToString(*path));
+
+    this->ActivateExistingSnapshot(mempool, *base_blockhash);
+    return true;
+}
+
+Chainstate& ChainstateManager::ActivateExistingSnapshot(CTxMemPool* mempool, uint256 base_blockhash)
+{
+    assert(!m_snapshot_chainstate);
+    m_snapshot_chainstate =
+        std::make_unique<Chainstate>(mempool, m_blockman, *this, base_blockhash);
+    LogPrintf("[snapshot] switching active chainstate to %s\n", m_snapshot_chainstate->ToString());
+    m_active_chainstate = m_snapshot_chainstate.get();
+    return *m_snapshot_chainstate;
+}

src/validation.h

@@ -929,17 +929,11 @@ class ChainstateManager
     //! coins databases. This will be split somehow across chainstates.
     int64_t m_total_coinsdb_cache{0};
 
-    //! Instantiate a new chainstate and assign it based upon whether it is
-    //! from a snapshot.
+    //! Instantiate a new chainstate.
     //!
     //! @param[in] mempool              The mempool to pass to the chainstate
     //                                  constructor
-    //! @param[in] snapshot_blockhash   If given, signify that this chainstate
-    //!                                 is based on a snapshot.
-    Chainstate& InitializeChainstate(
-        CTxMemPool* mempool,
-        const std::optional<uint256>& snapshot_blockhash = std::nullopt)
-        LIFETIMEBOUND EXCLUSIVE_LOCKS_REQUIRED(::cs_main);
+    Chainstate& InitializeChainstate(CTxMemPool* mempool) EXCLUSIVE_LOCKS_REQUIRED(::cs_main);
 
     //! Get all chainstates currently being used.
     std::vector<Chainstate*> GetAll();
@@ -1053,6 +1047,15 @@ class ChainstateManager
      *  information. */
     void ReportHeadersPresync(const arith_uint256& work, int64_t height, int64_t timestamp);
 
+    //! When starting up, search the datadir for a chainstate based on a UTXO
+    //! snapshot that is in the process of being validated.
+    bool DetectSnapshotChainstate(CTxMemPool* mempool) EXCLUSIVE_LOCKS_REQUIRED(::cs_main);
+
+    //! Switch the active chainstate to one based on a UTXO snapshot that was loaded
+    //! previously.
+    Chainstate& ActivateExistingSnapshot(CTxMemPool* mempool, uint256 base_blockhash)
+        EXCLUSIVE_LOCKS_REQUIRED(::cs_main);
+
     ~ChainstateManager();
 };
 

test/functional/feature_init.py

@@ -55,7 +55,6 @@ def check_clean_start():
             b'Loading P2P addresses',
             b'Loading banlist',
             b'Loading block index',
-            b'Switching active chainstate',
             b'Checking all blk files are present',
             b'Loaded best chain:',
             b'init message: Verifying blocks',