Merge #12653: Allow to optional specify the directory for the blocks storage

a192636 -blocksdir: keep blockindex leveldb database in datadir (Jonas Schnelli)
f38e4fd QA: Add -blocksdir test (Jonas Schnelli)
386a6b6 Allow to optional specify the directory for the blocks storage (Jonas Schnelli)

Pull request description:

  Since the actual block files taking up more and more space, it may be desirable to have them stored in a different location then the data directory (use case: SSD for chainstate, etc., HD for blocks).

  This PR adds a `-blocksdir` option that allows one to keep the blockfiles and the blockindex external from the data directory (instead of creating symlinks).

  I fist had an option to keep the blockindex within the datadir, but seems to make no sense since accessing the index will (always) lead to access (r/w) the block files.

Tree-SHA512: f8b9e1a681679eac25076dc30e45e6e12d4b2d9ac4be907cbea928a75af081dbcb0f1dd3e97169ab975f73d0bd15824c00c2a34638f3b284b39017171fce2409

src/init.cpp

@@ -333,6 +333,7 @@ std::string HelpMessage(HelpMessageMode mode)
     strUsage += HelpMessageOpt("-version", _("Print version and exit"));
     strUsage += HelpMessageOpt("-alertnotify=<cmd>", _("Execute command when a relevant alert is received or we see a really long fork (%s in cmd is replaced by message)"));
     strUsage +=HelpMessageOpt("-assumevalid=<hex>", strprintf(_("If this block is in the chain assume that it and its ancestors are valid and potentially skip their script verification (0 to verify all, default: %s, testnet: %s)"), defaultChainParams->GetConsensus().defaultAssumeValid.GetHex(), testnetChainParams->GetConsensus().defaultAssumeValid.GetHex()));
+    strUsage += HelpMessageOpt("-blocksdir=<dir>", _("Specify blocks directory (default: <datadir>/blocks)"));
     strUsage += HelpMessageOpt("-blocknotify=<cmd>", _("Execute command when the best block changes (%s in cmd is replaced by block hash)"));
     strUsage += HelpMessageOpt("-blockreconstructionextratxn=<n>", strprintf(_("Extra transactions to keep in memory for compact block reconstructions (default: %u)"), DEFAULT_BLOCK_RECONSTRUCTION_EXTRA_TXN));
     if (showDebug)
@@ -594,7 +595,7 @@ void CleanupBlockRevFiles()
     // 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 = GetDataDir() / "blocks";
+    fs::path blocksdir = GetBlocksDir();
     for (fs::directory_iterator it(blocksdir); it != fs::directory_iterator(); it++) {
         if (fs::is_regular_file(*it) &&
             it->path().filename().string().length() == 12 &&
@@ -897,6 +898,10 @@ bool AppInitParameterInteraction()
 
     // also see: InitParameterInteraction()
 
+    if (!fs::is_directory(GetBlocksDir(false))) {
+        return InitError(strprintf(_("Specified blocks directory \"%s\" does not exist.\n"), gArgs.GetArg("-blocksdir", "").c_str()));
+    }
+
     // if using block pruning, then disallow txindex
     if (gArgs.GetArg("-prune", 0)) {
         if (gArgs.GetBoolArg("-txindex", DEFAULT_TXINDEX))
@@ -1622,7 +1627,7 @@ bool AppInitMain()
 
     // ********************************************************* Step 10: import blocks
 
-    if (!CheckDiskSpace())
+    if (!CheckDiskSpace() && !CheckDiskSpace(0, true))
         return false;
 
     // Either install a handler to notify us when genesis activates, or set fHaveGenesis directly.

src/qt/bitcoin.cpp

@@ -623,7 +623,7 @@ int main(int argc, char *argv[])
     if (!Intro::pickDataDirectory())
         return EXIT_SUCCESS;
 
-    /// 6. Determine availability of data directory and parse bitcoin.conf
+    /// 6. Determine availability of data and blocks directory and parse bitcoin.conf
     /// - Do not call GetDataDir(true) before this step finishes
     if (!fs::is_directory(GetDataDir(false)))
     {

src/txdb.cpp

@@ -147,7 +147,7 @@ size_t CCoinsViewDB::EstimateSize() const
     return db.EstimateSize(DB_COIN, (char)(DB_COIN+1));
 }
 
-CBlockTreeDB::CBlockTreeDB(size_t nCacheSize, bool fMemory, bool fWipe) : CDBWrapper(GetDataDir() / "blocks" / "index", nCacheSize, fMemory, fWipe) {
+CBlockTreeDB::CBlockTreeDB(size_t nCacheSize, bool fMemory, bool fWipe) : CDBWrapper(gArgs.IsArgSet("-blocksdir") ? GetDataDir() / "blocks" / "index" : GetBlocksDir() / "index", nCacheSize, fMemory, fWipe) {
 }
 
 bool CBlockTreeDB::ReadBlockFileInfo(int nFile, CBlockFileInfo &info) {

src/util.cpp

@@ -613,10 +613,41 @@ fs::path GetDefaultDataDir()
 #endif
 }
 
+static fs::path g_blocks_path_cached;
+static fs::path g_blocks_path_cache_net_specific;
 static fs::path pathCached;
 static fs::path pathCachedNetSpecific;
 static CCriticalSection csPathCached;
 
+const fs::path &GetBlocksDir(bool fNetSpecific)
+{
+
+    LOCK(csPathCached);
+
+    fs::path &path = fNetSpecific ? g_blocks_path_cache_net_specific : g_blocks_path_cached;
+
+    // This can be called during exceptions by LogPrintf(), so we cache the
+    // value so we don't have to do memory allocations after that.
+    if (!path.empty())
+        return path;
+
+    if (gArgs.IsArgSet("-blocksdir")) {
+        path = fs::system_complete(gArgs.GetArg("-blocksdir", ""));
+        if (!fs::is_directory(path)) {
+            path = "";
+            return path;
+        }
+    } else {
+        path = GetDataDir(false);
+    }
+    if (fNetSpecific)
+        path /= BaseParams().DataDir();
+
+    path /= "blocks";
+    fs::create_directories(path);
+    return path;
+}
+
 const fs::path &GetDataDir(bool fNetSpecific)
 {
 
@@ -655,6 +686,8 @@ void ClearDatadirCache()
 
     pathCached = fs::path();
     pathCachedNetSpecific = fs::path();
+    g_blocks_path_cached = fs::path();
+    g_blocks_path_cache_net_specific = fs::path();
 }
 
 fs::path GetConfigFile(const std::string& confPath)

src/util.h

@@ -183,6 +183,7 @@ void ReleaseDirectoryLocks();
 
 bool TryCreateDirectories(const fs::path& p);
 fs::path GetDefaultDataDir();
+const fs::path &GetBlocksDir(bool fNetSpecific = true);
 const fs::path &GetDataDir(bool fNetSpecific = true);
 void ClearDatadirCache();
 fs::path GetConfigFile(const std::string& confPath);

src/validation.cpp

@@ -2108,7 +2108,7 @@ bool static FlushStateToDisk(const CChainParams& chainparams, CValidationState &
         // Write blocks and block index to disk.
         if (fDoFullFlush || fPeriodicWrite) {
             // Depend on nMinDiskSpace to ensure we can write block index
-            if (!CheckDiskSpace(0))
+            if (!CheckDiskSpace(0, true))
                 return state.Error("out of disk space");
             // First make sure all block and undo data is flushed to disk.
             FlushBlockFile();
@@ -2953,7 +2953,7 @@ static bool FindBlockPos(CDiskBlockPos &pos, unsigned int nAddSize, unsigned int
         if (nNewChunks > nOldChunks) {
             if (fPruneMode)
                 fCheckForPruning = true;
-            if (CheckDiskSpace(nNewChunks * BLOCKFILE_CHUNK_SIZE - pos.nPos)) {
+            if (CheckDiskSpace(nNewChunks * BLOCKFILE_CHUNK_SIZE - pos.nPos, true)) {
                 FILE *file = OpenBlockFile(pos);
                 if (file) {
                     LogPrintf("Pre-allocating up to position 0x%x in blk%05u.dat\n", nNewChunks * BLOCKFILE_CHUNK_SIZE, pos.nFile);
@@ -2986,7 +2986,7 @@ static bool FindUndoPos(CValidationState &state, int nFile, CDiskBlockPos &pos,
     if (nNewChunks > nOldChunks) {
         if (fPruneMode)
             fCheckForPruning = true;
-        if (CheckDiskSpace(nNewChunks * UNDOFILE_CHUNK_SIZE - pos.nPos)) {
+        if (CheckDiskSpace(nNewChunks * UNDOFILE_CHUNK_SIZE - pos.nPos, true)) {
             FILE *file = OpenUndoFile(pos);
             if (file) {
                 LogPrintf("Pre-allocating up to position 0x%x in rev%05u.dat\n", nNewChunks * UNDOFILE_CHUNK_SIZE, pos.nFile);
@@ -3661,9 +3661,9 @@ static void FindFilesToPrune(std::set<int>& setFilesToPrune, uint64_t nPruneAfte
            nLastBlockWeCanPrune, count);
 }
 
-bool CheckDiskSpace(uint64_t nAdditionalBytes)
+bool CheckDiskSpace(uint64_t nAdditionalBytes, bool blocks_dir)
 {
-    uint64_t nFreeBytesAvailable = fs::space(GetDataDir()).available;
+    uint64_t nFreeBytesAvailable = fs::space(blocks_dir ? GetBlocksDir() : GetDataDir()).available;
 
     // Check for nMinDiskSpace bytes (currently 50MB)
     if (nFreeBytesAvailable < nMinDiskSpace + nAdditionalBytes)
@@ -3706,7 +3706,7 @@ static FILE* OpenUndoFile(const CDiskBlockPos &pos, bool fReadOnly) {
 
 fs::path GetBlockPosFilename(const CDiskBlockPos &pos, const char *prefix)
 {
-    return GetDataDir() / "blocks" / strprintf("%s%05u.dat", prefix, pos.nFile);
+    return GetBlocksDir() / strprintf("%s%05u.dat", prefix, pos.nFile);
 }
 
 CBlockIndex * CChainState::InsertBlockIndex(const uint256& hash)

src/validation.h

@@ -254,7 +254,7 @@ bool ProcessNewBlock(const CChainParams& chainparams, const std::shared_ptr<cons
 bool ProcessNewBlockHeaders(const std::vector<CBlockHeader>& block, CValidationState& state, const CChainParams& chainparams, const CBlockIndex** ppindex=nullptr, CBlockHeader *first_invalid=nullptr);
 
 /** Check whether enough disk space is available for an incoming block */
-bool CheckDiskSpace(uint64_t nAdditionalBytes = 0);
+bool CheckDiskSpace(uint64_t nAdditionalBytes = 0, bool blocks_dir = false);
 /** Open a block file (blk?????.dat) */
 FILE* OpenBlockFile(const CDiskBlockPos &pos, bool fReadOnly = false);
 /** Translation to a filesystem path */

test/functional/feature_blocksdir.py

@@ -0,0 +1,34 @@
+#!/usr/bin/env python3
+# Copyright (c) 2018 The Bitcoin Core developers
+# Distributed under the MIT software license, see the accompanying
+# file COPYING or http://www.opensource.org/licenses/mit-license.php.
+"""Test the blocksdir option.
+"""
+
+from test_framework.test_framework import BitcoinTestFramework, initialize_datadir
+
+import shutil
+import os
+
+class BlocksdirTest(BitcoinTestFramework):
+    def set_test_params(self):
+        self.setup_clean_chain = True
+        self.num_nodes = 1
+
+    def run_test(self):
+        self.stop_node(0)
+        node0path = os.path.join(self.options.tmpdir, "node0")
+        shutil.rmtree(node0path)
+        initialize_datadir(self.options.tmpdir, 0)
+        self.log.info("Starting with non exiting blocksdir ...")
+        self.assert_start_raises_init_error(0, ["-blocksdir="+self.options.tmpdir+ "/blocksdir"], "Specified blocks director")
+        os.mkdir(self.options.tmpdir+ "/blocksdir")
+        self.log.info("Starting with exiting blocksdir ...")
+        self.start_node(0, ["-blocksdir="+self.options.tmpdir+ "/blocksdir"])
+        self.log.info("mining blocks..")
+        self.nodes[0].generate(10)
+        assert(os.path.isfile(os.path.join(self.options.tmpdir, "blocksdir", "regtest", "blocks", "blk00000.dat")))
+        assert(os.path.isdir(os.path.join(self.options.tmpdir, "node0", "regtest", "blocks", "index")))
+
+if __name__ == '__main__':
+    BlocksdirTest().main()

test/functional/test_runner.py

@@ -136,6 +136,7 @@ BASE_SCRIPTS= [
     'p2p_unrequested_blocks.py',
     'feature_logging.py',
     'p2p_node_network_limited.py',
+    'feature_blocksdir.py',
     'feature_config_args.py',
     # Don't append tests at the end to avoid merge conflicts
     # Put them in a random line within the section that fits their approximate run-time