Add setting to warn about copying/hashing large paths

This is useful for diagnosing whether an evaluation is copying large
paths to the store. Example:

   $ nix build .#packages.x86_64-linux.default --large-path-warning-threshold 1000000
   warning: copied large path '/home/eelco/Dev/nix-master/' to the store (6271792 bytes)
   warning: copied large path '«github:NixOS/nixpkgs/b550fe4b4776908ac2a861124307045f8e717c8e?narHash=sha256-7kkJQd4rZ%2BvFrzWu8sTRtta5D1kBG0LSRYAfhtmMlSo%3D»/' to the store (155263768 bytes)
   warning: copied large path '«github:libgit2/libgit2/45fd9ed7ae1a9b74b957ef4f337bc3c8b3df01b5?narHash=sha256-oX4Z3S9WtJlwvj0uH9HlYcWv%2Bx1hqp8mhXl7HsLu2f0%3D»/' to the store (22175416 bytes)
   warning: copied large path '/nix/store/z985088mcd6w23qwdlirsinnyzayagki-source' to the store (5885872 bytes)

perl/lib/Nix/Store.xs

@@ -258,7 +258,7 @@ hashPath(char * algo, int base32, char * path)
         try {
             Hash h = hashPath(
                 PosixSourceAccessor::createAtRoot(path),
-                FileIngestionMethod::Recursive, parseHashAlgo(algo));
+                FileIngestionMethod::Recursive, parseHashAlgo(algo)).first;
             auto s = h.to_string(base32 ? HashFormat::Nix32 : HashFormat::Base16, false);
             XPUSHs(sv_2mortal(newSVpv(s.c_str(), 0)));
         } catch (Error & e) {

src/libstore/binary-cache-store.cc

@@ -453,7 +453,7 @@ StorePath BinaryCacheStore::addToStore(
        non-recursive+sha256 so we can just use the default
        implementation of this method in terms of addToStoreFromDump. */
 
-    auto h = hashPath(path, method.getFileIngestionMethod(), hashAlgo, filter);
+    auto h = hashPath(path, method.getFileIngestionMethod(), hashAlgo, filter).first;
 
     auto source = sinkToSource([&](Sink & sink) {
         path.dumpPath(sink, filter);

src/libstore/globals.hh

@@ -1262,6 +1262,16 @@ public:
           store paths of the latest Nix release.
         )"
     };
+
+    Setting<uint64_t> largePathWarningThreshold{
+        this,
+        std::numeric_limits<uint64_t>::max(),
+        "large-path-warning-threshold",
+        R"(
+          Warn when copying a path larger than this number of bytes to the Nix store
+          (as determined by its NAR serialisation).
+        )"
+    };
 };
 
 

src/libstore/local-store.cc

@@ -1272,7 +1272,7 @@ StorePath LocalStore::addToStoreFromDump(
             ? dumpHash
             : hashPath(
                 PosixSourceAccessor::createAtRoot(tempPath),
-                hashMethod.getFileIngestionMethod(), hashAlgo),
+                hashMethod.getFileIngestionMethod(), hashAlgo).first,
         {
             .others = references,
             // caller is not capable of creating a self-reference, because this is content-addressed without modulus
@@ -1412,7 +1412,7 @@ bool LocalStore::verifyStore(bool checkContents, RepairFlag repair)
             PosixSourceAccessor accessor;
             std::string hash = hashPath(
                 PosixSourceAccessor::createAtRoot(link.path()),
-                FileIngestionMethod::Recursive, HashAlgorithm::SHA256).to_string(HashFormat::Nix32, false);
+                FileIngestionMethod::Recursive, HashAlgorithm::SHA256).first.to_string(HashFormat::Nix32, false);
             if (hash != name.string()) {
                 printError("link '%s' was modified! expected hash '%s', got '%s'",
                     link.path(), name, hash);

src/libstore/store-api.cc

@@ -169,7 +169,9 @@ std::pair<StorePath, Hash> StoreDirConfig::computeStorePath(
     const StorePathSet & references,
     PathFilter & filter) const
 {
-    auto h = hashPath(path, method.getFileIngestionMethod(), hashAlgo, filter);
+    auto [h, size] = hashPath(path, method.getFileIngestionMethod(), hashAlgo, filter);
+    if (size && *size >= settings.largePathWarningThreshold)
+        warn("hashed large path '%s' (%d bytes)", path, *size);
     return {
         makeFixedOutputPathFromCA(
             name,
@@ -210,7 +212,11 @@ StorePath Store::addToStore(
     auto source = sinkToSource([&](Sink & sink) {
         dumpPath(path, sink, fsm, filter);
     });
-    return addToStoreFromDump(*source, name, fsm, method, hashAlgo, references, repair);
+    LengthSource lengthSource(*source);
+    auto storePath = addToStoreFromDump(lengthSource, name, fsm, method, hashAlgo, references, repair);
+    if (lengthSource.total >= settings.largePathWarningThreshold)
+        warn("copied large path '%s' to the store (%d bytes)", path, lengthSource.total);
+    return storePath;
 }
 
 void Store::addMultipleToStore(

src/libstore/unix/build/worker.cc

@@ -529,9 +529,9 @@ bool Worker::pathContentsGood(const StorePath & path)
     if (!pathExists(store.printStorePath(path)))
         res = false;
     else {
-        Hash current = hashPath(
+        auto current = hashPath(
             {store.getFSAccessor(), CanonPath(store.printStorePath(path))},
-            FileIngestionMethod::Recursive, info->narHash.algo);
+            FileIngestionMethod::Recursive, info->narHash.algo).first;
         Hash nullHash(HashAlgorithm::SHA256);
         res = info->narHash == nullHash || info->narHash == current;
     }

src/libutil/file-content-address.cc

@@ -112,17 +112,19 @@ HashResult hashPath(
 }
 
 
-Hash hashPath(
+std::pair<Hash, std::optional<uint64_t>> hashPath(
     const SourcePath & path,
     FileIngestionMethod method, HashAlgorithm ht,
     PathFilter & filter)
 {
     switch (method) {
     case FileIngestionMethod::Flat:
-    case FileIngestionMethod::Recursive:
-        return hashPath(path, (FileSerialisationMethod) method, ht, filter).first;
+    case FileIngestionMethod::Recursive: {
+        auto res = hashPath(path, (FileSerialisationMethod) method, ht, filter);
+        return {res.first, {res.second}};
+    }
     case FileIngestionMethod::Git:
-        return git::dumpHash(ht, path, filter).hash;
+        return {git::dumpHash(ht, path, filter).hash, std::nullopt};
     }
     assert(false);
 }

src/libutil/file-content-address.hh

@@ -132,14 +132,15 @@ std::string_view renderFileIngestionMethod(FileIngestionMethod method);
 
 /**
  * Compute the hash of the given file system object according to the
- * given method.
+ * given method, and for some ingestion methods, the size of the
+ * serialisation.
  *
  * Unlike the other `hashPath`, this works on an arbitrary
  * `FileIngestionMethod` instead of `FileSerialisationMethod`, but
- * doesn't return the size as this is this is not a both simple and
+ * may not return the size as this is this is not a both simple and
  * useful defined for a merkle format.
  */
-Hash hashPath(
+std::pair<Hash, std::optional<uint64_t>> hashPath(
     const SourcePath & path,
     FileIngestionMethod method, HashAlgorithm ha,
     PathFilter & filter = defaultPathFilter);

src/libutil/serialise.hh

@@ -283,6 +283,26 @@ struct LengthSink : Sink
     }
 };
 
+/**
+ * A wrapper source that counts the number of bytes read from it.
+ */
+struct LengthSource : Source
+{
+    Source & next;
+
+    LengthSource(Source & next) : next(next)
+    { }
+
+    uint64_t total = 0;
+
+    size_t read(char * data, size_t len) override
+    {
+        auto n = next.read(data, len);
+        total += n;
+        return n;
+    }
+};
+
 /**
  * Convert a function into a sink.
  */