Merge bitcoin/bitcoin#21727: refactor: Move more stuff to blockstorage

fa09a9eac8d8ab65ce4064c35a9f21349a644982 style: Add { } to multi-line if (MarcoFalke)
fadafab83379ff10d86ada179c6f9641d19464fe move-only: Move functions to blockstorage (MarcoFalke)
fa7e64d58615fffea91cd64dc4a2790221ceff0a move-only: Move constants to blockstorage (MarcoFalke)
fa247a327fc7c7cea6bc8f93637b8babd3015ffa refactor: Move block storage globals to blockstorage (MarcoFalke)
fa81c30c6f1adac79517c958090db174eb6aeda2 refactor: Move pruning/reindex/importing globals to blockstorage (MarcoFalke)

Pull request description:

  See #21575

ACKs for top commit:
  Sjors:
    ACK fa09a9eac8d8ab65ce4064c35a9f21349a644982
  kiminuo:
    ACK fa09a9e
  laanwj:
    Code review ACK fa09a9eac8d8ab65ce4064c35a9f21349a644982
  promag:
    Code review ACK fa09a9eac8d8ab65ce4064c35a9f21349a644982. Since last review

Tree-SHA512: 2eb6962ff44da6b77f3058fc02ec66ab742e25ae8dcc8ec62b062896571910d43ca7c4bb16fb3ccb5e5245195b8dec6384b6c8d442fa97ca28d93bdff347d677

2 files changed, 365 insertions, 2 deletions

diff --git a/src/node/blockstorage.cpp b/src/node/blockstorage.cpp
index daed6605e8..6c66c565ad 100644
--- a/src/node/blockstorage.cpp
+++ b/src/node/blockstorage.cpp
@@ -6,17 +6,310 @@
 
 #include <chain.h>
 #include <chainparams.h>
+#include <clientversion.h>
+#include <consensus/validation.h>
 #include <flatfile.h>
 #include <fs.h>
+#include <hash.h>
 #include <pow.h>
 #include <shutdown.h>
 #include <signet.h>
 #include <streams.h>
+#include <undo.h>
 #include <util/system.h>
 #include <validation.h>
 
-// From validation. TODO move here
-bool FindBlockPos(FlatFilePos& pos, unsigned int nAddSize, unsigned int nHeight, CChain& active_chain, uint64_t nTime, bool fKnown = false);
+std::atomic_bool fImporting(false);
+std::atomic_bool fReindex(false);
+bool fHavePruned = false;
+bool fPruneMode = false;
+uint64_t nPruneTarget = 0;
+
+// TODO make namespace {
+RecursiveMutex cs_LastBlockFile;
+std::vector<CBlockFileInfo> vinfoBlockFile;
+int nLastBlockFile = 0;
+/** Global flag to indicate we should check to see if there are
+*  block/undo files that should be deleted.  Set on startup
+*  or if we allocate more file space when we're in prune mode
+*/
+bool fCheckForPruning = false;
+
+/** Dirty block index entries. */
+std::set<CBlockIndex*> setDirtyBlockIndex;
+
+/** Dirty block file entries. */
+std::set<int> setDirtyFileInfo;
+// } // namespace
+
+static FILE* OpenUndoFile(const FlatFilePos& pos, bool fReadOnly = false);
+static FlatFileSeq BlockFileSeq();
+static FlatFileSeq UndoFileSeq();
+
+bool IsBlockPruned(const CBlockIndex* pblockindex)
+{
+    return (fHavePruned && !(pblockindex->nStatus & BLOCK_HAVE_DATA) && pblockindex->nTx > 0);
+}
+
+// If we're using -prune with -reindex, then delete block files that will be ignored by the
+// reindex.  Since reindexing works by starting at block file 0 and looping until a blockfile
+// is missing, do the same here to delete any later block files after a gap.  Also delete all
+// rev files since they'll be rewritten by the reindex anyway.  This ensures that vinfoBlockFile
+// is in sync with what's actually on disk by the time we start downloading, so that pruning
+// works correctly.
+void CleanupBlockRevFiles()
+{
+    std::map<std::string, fs::path> mapBlockFiles;
+
+    // Glob all blk?????.dat and rev?????.dat files from the blocks directory.
+    // Remove the rev files immediately and insert the blk file paths into an
+    // ordered map keyed by block file index.
+    LogPrintf("Removing unusable blk?????.dat and rev?????.dat files for -reindex with -prune\n");
+    fs::path blocksdir = gArgs.GetBlocksDirPath();
+    for (fs::directory_iterator it(blocksdir); it != fs::directory_iterator(); it++) {
+        if (fs::is_regular_file(*it) &&
+            it->path().filename().string().length() == 12 &&
+            it->path().filename().string().substr(8,4) == ".dat")
+        {
+            if (it->path().filename().string().substr(0, 3) == "blk") {
+                mapBlockFiles[it->path().filename().string().substr(3, 5)] = it->path();
+            } else if (it->path().filename().string().substr(0, 3) == "rev") {
+                remove(it->path());
+            }
+        }
+    }
+
+    // Remove all block files that aren't part of a contiguous set starting at
+    // zero by walking the ordered map (keys are block file indices) by
+    // keeping a separate counter.  Once we hit a gap (or if 0 doesn't exist)
+    // start removing block files.
+    int nContigCounter = 0;
+    for (const std::pair<const std::string, fs::path>& item : mapBlockFiles) {
+        if (atoi(item.first) == nContigCounter) {
+            nContigCounter++;
+            continue;
+        }
+        remove(item.second);
+    }
+}
+
+std::string CBlockFileInfo::ToString() const
+{
+    return strprintf("CBlockFileInfo(blocks=%u, size=%u, heights=%u...%u, time=%s...%s)", nBlocks, nSize, nHeightFirst, nHeightLast, FormatISO8601Date(nTimeFirst), FormatISO8601Date(nTimeLast));
+}
+
+CBlockFileInfo* GetBlockFileInfo(size_t n)
+{
+    LOCK(cs_LastBlockFile);
+
+    return &vinfoBlockFile.at(n);
+}
+
+static bool UndoWriteToDisk(const CBlockUndo& blockundo, FlatFilePos& pos, const uint256& hashBlock, const CMessageHeader::MessageStartChars& messageStart)
+{
+    // Open history file to append
+    CAutoFile fileout(OpenUndoFile(pos), SER_DISK, CLIENT_VERSION);
+    if (fileout.IsNull()) {
+        return error("%s: OpenUndoFile failed", __func__);
+    }
+
+    // Write index header
+    unsigned int nSize = GetSerializeSize(blockundo, fileout.GetVersion());
+    fileout << messageStart << nSize;
+
+    // Write undo data
+    long fileOutPos = ftell(fileout.Get());
+    if (fileOutPos < 0) {
+        return error("%s: ftell failed", __func__);
+    }
+    pos.nPos = (unsigned int)fileOutPos;
+    fileout << blockundo;
+
+    // calculate & write checksum
+    CHashWriter hasher(SER_GETHASH, PROTOCOL_VERSION);
+    hasher << hashBlock;
+    hasher << blockundo;
+    fileout << hasher.GetHash();
+
+    return true;
+}
+
+bool UndoReadFromDisk(CBlockUndo& blockundo, const CBlockIndex* pindex)
+{
+    FlatFilePos pos = pindex->GetUndoPos();
+    if (pos.IsNull()) {
+        return error("%s: no undo data available", __func__);
+    }
+
+    // Open history file to read
+    CAutoFile filein(OpenUndoFile(pos, true), SER_DISK, CLIENT_VERSION);
+    if (filein.IsNull()) {
+        return error("%s: OpenUndoFile failed", __func__);
+    }
+
+    // Read block
+    uint256 hashChecksum;
+    CHashVerifier<CAutoFile> verifier(&filein); // We need a CHashVerifier as reserializing may lose data
+    try {
+        verifier << pindex->pprev->GetBlockHash();
+        verifier >> blockundo;
+        filein >> hashChecksum;
+    } catch (const std::exception& e) {
+        return error("%s: Deserialize or I/O error - %s", __func__, e.what());
+    }
+
+    // Verify checksum
+    if (hashChecksum != verifier.GetHash()) {
+        return error("%s: Checksum mismatch", __func__);
+    }
+
+    return true;
+}
+
+static void FlushUndoFile(int block_file, bool finalize = false)
+{
+    FlatFilePos undo_pos_old(block_file, vinfoBlockFile[block_file].nUndoSize);
+    if (!UndoFileSeq().Flush(undo_pos_old, finalize)) {
+        AbortNode("Flushing undo file to disk failed. This is likely the result of an I/O error.");
+    }
+}
+
+void FlushBlockFile(bool fFinalize = false, bool finalize_undo = false)
+{
+    LOCK(cs_LastBlockFile);
+    FlatFilePos block_pos_old(nLastBlockFile, vinfoBlockFile[nLastBlockFile].nSize);
+    if (!BlockFileSeq().Flush(block_pos_old, fFinalize)) {
+        AbortNode("Flushing block file to disk failed. This is likely the result of an I/O error.");
+    }
+    // we do not always flush the undo file, as the chain tip may be lagging behind the incoming blocks,
+    // e.g. during IBD or a sync after a node going offline
+    if (!fFinalize || finalize_undo) FlushUndoFile(nLastBlockFile, finalize_undo);
+}
+
+uint64_t CalculateCurrentUsage()
+{
+    LOCK(cs_LastBlockFile);
+
+    uint64_t retval = 0;
+    for (const CBlockFileInfo& file : vinfoBlockFile) {
+        retval += file.nSize + file.nUndoSize;
+    }
+    return retval;
+}
+
+void UnlinkPrunedFiles(const std::set<int>& setFilesToPrune)
+{
+    for (std::set<int>::iterator it = setFilesToPrune.begin(); it != setFilesToPrune.end(); ++it) {
+        FlatFilePos pos(*it, 0);
+        fs::remove(BlockFileSeq().FileName(pos));
+        fs::remove(UndoFileSeq().FileName(pos));
+        LogPrintf("Prune: %s deleted blk/rev (%05u)\n", __func__, *it);
+    }
+}
+
+static FlatFileSeq BlockFileSeq()
+{
+    return FlatFileSeq(gArgs.GetBlocksDirPath(), "blk", gArgs.GetBoolArg("-fastprune", false) ? 0x4000 /* 16kb */ : BLOCKFILE_CHUNK_SIZE);
+}
+
+static FlatFileSeq UndoFileSeq()
+{
+    return FlatFileSeq(gArgs.GetBlocksDirPath(), "rev", UNDOFILE_CHUNK_SIZE);
+}
+
+FILE* OpenBlockFile(const FlatFilePos& pos, bool fReadOnly)
+{
+    return BlockFileSeq().Open(pos, fReadOnly);
+}
+
+/** Open an undo file (rev?????.dat) */
+static FILE* OpenUndoFile(const FlatFilePos& pos, bool fReadOnly)
+{
+    return UndoFileSeq().Open(pos, fReadOnly);
+}
+
+fs::path GetBlockPosFilename(const FlatFilePos& pos)
+{
+    return BlockFileSeq().FileName(pos);
+}
+
+bool FindBlockPos(FlatFilePos& pos, unsigned int nAddSize, unsigned int nHeight, CChain& active_chain, uint64_t nTime, bool fKnown = false)
+{
+    LOCK(cs_LastBlockFile);
+
+    unsigned int nFile = fKnown ? pos.nFile : nLastBlockFile;
+    if (vinfoBlockFile.size() <= nFile) {
+        vinfoBlockFile.resize(nFile + 1);
+    }
+
+    bool finalize_undo = false;
+    if (!fKnown) {
+        while (vinfoBlockFile[nFile].nSize + nAddSize >= (gArgs.GetBoolArg("-fastprune", false) ? 0x10000 /* 64kb */ : MAX_BLOCKFILE_SIZE)) {
+            // when the undo file is keeping up with the block file, we want to flush it explicitly
+            // when it is lagging behind (more blocks arrive than are being connected), we let the
+            // undo block write case handle it
+            assert(std::addressof(::ChainActive()) == std::addressof(active_chain));
+            finalize_undo = (vinfoBlockFile[nFile].nHeightLast == (unsigned int)active_chain.Tip()->nHeight);
+            nFile++;
+            if (vinfoBlockFile.size() <= nFile) {
+                vinfoBlockFile.resize(nFile + 1);
+            }
+        }
+        pos.nFile = nFile;
+        pos.nPos = vinfoBlockFile[nFile].nSize;
+    }
+
+    if ((int)nFile != nLastBlockFile) {
+        if (!fKnown) {
+            LogPrint(BCLog::VALIDATION, "Leaving block file %i: %s\n", nLastBlockFile, vinfoBlockFile[nLastBlockFile].ToString());
+        }
+        FlushBlockFile(!fKnown, finalize_undo);
+        nLastBlockFile = nFile;
+    }
+
+    vinfoBlockFile[nFile].AddBlock(nHeight, nTime);
+    if (fKnown) {
+        vinfoBlockFile[nFile].nSize = std::max(pos.nPos + nAddSize, vinfoBlockFile[nFile].nSize);
+    } else {
+        vinfoBlockFile[nFile].nSize += nAddSize;
+    }
+
+    if (!fKnown) {
+        bool out_of_space;
+        size_t bytes_allocated = BlockFileSeq().Allocate(pos, nAddSize, out_of_space);
+        if (out_of_space) {
+            return AbortNode("Disk space is too low!", _("Disk space is too low!"));
+        }
+        if (bytes_allocated != 0 && fPruneMode) {
+            fCheckForPruning = true;
+        }
+    }
+
+    setDirtyFileInfo.insert(nFile);
+    return true;
+}
+
+static bool FindUndoPos(BlockValidationState& state, int nFile, FlatFilePos& pos, unsigned int nAddSize)
+{
+    pos.nFile = nFile;
+
+    LOCK(cs_LastBlockFile);
+
+    pos.nPos = vinfoBlockFile[nFile].nUndoSize;
+    vinfoBlockFile[nFile].nUndoSize += nAddSize;
+    setDirtyFileInfo.insert(nFile);
+
+    bool out_of_space;
+    size_t bytes_allocated = UndoFileSeq().Allocate(pos, nAddSize, out_of_space);
+    if (out_of_space) {
+        return AbortNode(state, "Disk space is too low!", _("Disk space is too low!"));
+    }
+    if (bytes_allocated != 0 && fPruneMode) {
+        fCheckForPruning = true;
+    }
+
+    return true;
+}
 
 static bool WriteBlockToDisk(const CBlock& block, FlatFilePos& pos, const CMessageHeader::MessageStartChars& messageStart)
 {
@@ -41,6 +334,35 @@ static bool WriteBlockToDisk(const CBlock& block, FlatFilePos& pos, const CMessa
     return true;
 }
 
+bool WriteUndoDataForBlock(const CBlockUndo& blockundo, BlockValidationState& state, CBlockIndex* pindex, const CChainParams& chainparams)
+{
+    // Write undo information to disk
+    if (pindex->GetUndoPos().IsNull()) {
+        FlatFilePos _pos;
+        if (!FindUndoPos(state, pindex->nFile, _pos, ::GetSerializeSize(blockundo, CLIENT_VERSION) + 40)) {
+            return error("ConnectBlock(): FindUndoPos failed");
+        }
+        if (!UndoWriteToDisk(blockundo, _pos, pindex->pprev->GetBlockHash(), chainparams.MessageStart())) {
+            return AbortNode(state, "Failed to write undo data");
+        }
+        // rev files are written in block height order, whereas blk files are written as blocks come in (often out of order)
+        // we want to flush the rev (undo) file once we've written the last block, which is indicated by the last height
+        // in the block file info as below; note that this does not catch the case where the undo writes are keeping up
+        // with the block writes (usually when a synced up node is getting newly mined blocks) -- this case is caught in
+        // the FindBlockPos function
+        if (_pos.nFile < nLastBlockFile && static_cast<uint32_t>(pindex->nHeight) == vinfoBlockFile[_pos.nFile].nHeightLast) {
+            FlushUndoFile(_pos.nFile, true);
+        }
+
+        // update nUndoPos in block index
+        pindex->nUndoPos = _pos.nPos;
+        pindex->nStatus |= BLOCK_HAVE_UNDO;
+        setDirtyBlockIndex.insert(pindex);
+    }
+
+    return true;
+}
+
 bool ReadBlockFromDisk(CBlock& block, const FlatFilePos& pos, const Consensus::Params& consensusParams)
 {
     block.SetNull();
diff --git a/src/node/blockstorage.h b/src/node/blockstorage.h
index 3b546f0719..faf99dea81 100644
--- a/src/node/blockstorage.h
+++ b/src/node/blockstorage.h
@@ -12,7 +12,9 @@
 #include <protocol.h> // For CMessageHeader::MessageStartChars
 
 class ArgsManager;
+class BlockValidationState;
 class CBlock;
+class CBlockFileInfo;
 class CBlockIndex;
 class CBlockUndo;
 class CChain;
@@ -25,6 +27,44 @@ struct Params;
 
 static constexpr bool DEFAULT_STOPAFTERBLOCKIMPORT{false};
 
+/** The pre-allocation chunk size for blk?????.dat files (since 0.8) */
+static const unsigned int BLOCKFILE_CHUNK_SIZE = 0x1000000; // 16 MiB
+/** The pre-allocation chunk size for rev?????.dat files (since 0.8) */
+static const unsigned int UNDOFILE_CHUNK_SIZE = 0x100000; // 1 MiB
+/** The maximum size of a blk?????.dat file (since 0.8) */
+static const unsigned int MAX_BLOCKFILE_SIZE = 0x8000000; // 128 MiB
+
+extern std::atomic_bool fImporting;
+extern std::atomic_bool fReindex;
+/** Pruning-related variables and constants */
+/** True if any block files have ever been pruned. */
+extern bool fHavePruned;
+/** True if we're running in -prune mode. */
+extern bool fPruneMode;
+/** Number of MiB of block files that we're trying to stay below. */
+extern uint64_t nPruneTarget;
+
+//! Check whether the block associated with this index entry is pruned or not.
+bool IsBlockPruned(const CBlockIndex* pblockindex);
+
+void CleanupBlockRevFiles();
+
+/** Open a block file (blk?????.dat) */
+FILE* OpenBlockFile(const FlatFilePos& pos, bool fReadOnly = false);
+/** Translation to a filesystem path */
+fs::path GetBlockPosFilename(const FlatFilePos& pos);
+
+/** Get block file info entry for one block file */
+CBlockFileInfo* GetBlockFileInfo(size_t n);
+
+/** Calculate the amount of disk space the block & undo files currently use */
+uint64_t CalculateCurrentUsage();
+
+/**
+ *  Actually unlink the specified files
+ */
+void UnlinkPrunedFiles(const std::set<int>& setFilesToPrune);
+
 /** Functions for disk access for blocks */
 bool ReadBlockFromDisk(CBlock& block, const FlatFilePos& pos, const Consensus::Params& consensusParams);
 bool ReadBlockFromDisk(CBlock& block, const CBlockIndex* pindex, const Consensus::Params& consensusParams);
@@ -32,6 +72,7 @@ bool ReadRawBlockFromDisk(std::vector<uint8_t>& block, const FlatFilePos& pos, c
 bool ReadRawBlockFromDisk(std::vector<uint8_t>& block, const CBlockIndex* pindex, const CMessageHeader::MessageStartChars& message_start);
 
 bool UndoReadFromDisk(CBlockUndo& blockundo, const CBlockIndex* pindex);
+bool WriteUndoDataForBlock(const CBlockUndo& blockundo, BlockValidationState& state, CBlockIndex* pindex, const CChainParams& chainparams);
 
 FlatFilePos SaveBlockToDisk(const CBlock& block, int nHeight, CChain& active_chain, const CChainParams& chainparams, const FlatFilePos* dbp);