mirror of
https://git.in.rschanz.org/ryan77627/guix.git
synced 2024-12-27 14:52:05 -05:00
472a0e82a5
Files smaller than 8 KiB typically represent ~70% of the entries in /gnu/store/.links but only contribute to ~4% of the space savings afforded by deduplication. Not considering these files for deduplication speeds up file insertion in the store and, more importantly, leaves 'removeUnusedLinks' with fewer entries to traverse, thereby speeding it up proportionally. Partly fixes <https://issues.guix.gnu.org/24937>. * config-daemon.ac: Remove symlink hard link check and CAN_LINK_SYMLINK definition. * guix/store/deduplication.scm (%deduplication-minimum-size): New variable. (deduplicate)[loop]: Do not recurse when FILE's size is below %DEDUPLICATION-MINIMUM-SIZE. (dump-port): New procedure. (dump-file/deduplicate)[hash]: Turn into... [dump-and-compute-hash]: ... this thunk. Call 'deduplicate' only when SIZE is greater than %DEDUPLICATION-MINIMUM-SIZE; otherwise call 'dump-port'. * nix/libstore/gc.cc (LocalStore::removeUnusedLinks): Drop files where st.st_size < deduplicationMinSize. * nix/libstore/local-store.hh (deduplicationMinSize): New declaration. * nix/libstore/optimise-store.cc (deduplicationMinSize): New variable. (LocalStore::optimisePath_): Return when PATH is a symlink or smaller than 'deduplicationMinSize'. * tests/derivations.scm ("identical files are deduplicated"): Produce files bigger than %DEDUPLICATION-MINIMUM-SIZE. * tests/nar.scm ("restore-file-set with directories (signed, valid)"): Likewise. * tests/store-deduplication.scm ("deduplicate, below %deduplication-minimum-size"): New test. ("deduplicate", "deduplicate, ENOSPC"): Produce files bigger than %DEDUPLICATION-MINIMUM-SIZE. * tests/store.scm ("substitute, deduplication"): Likewise.
298 lines
8.6 KiB
C++
298 lines
8.6 KiB
C++
#pragma once
|
|
|
|
#include "sqlite.hh"
|
|
#include <string>
|
|
#include <unordered_set>
|
|
|
|
#include "pathlocks.hh"
|
|
#include "store-api.hh"
|
|
#include "util.hh"
|
|
|
|
|
|
namespace nix {
|
|
|
|
|
|
/* Nix store and database schema version. Version 1 (or 0) was Nix <=
|
|
0.7. Version 2 was Nix 0.8 and 0.9. Version 3 is Nix 0.10.
|
|
Version 4 is Nix 0.11. Version 5 is Nix 0.12-0.16. Version 6 is
|
|
Nix 1.0. Version 7 is Nix 1.3. Guix has always used version 7. */
|
|
const int nixSchemaVersion = 7;
|
|
|
|
|
|
extern string drvsLogDir;
|
|
|
|
|
|
struct Derivation;
|
|
|
|
|
|
struct OptimiseStats
|
|
{
|
|
unsigned long filesLinked;
|
|
unsigned long long bytesFreed;
|
|
unsigned long long blocksFreed;
|
|
OptimiseStats()
|
|
{
|
|
filesLinked = 0;
|
|
bytesFreed = blocksFreed = 0;
|
|
}
|
|
};
|
|
|
|
|
|
class LocalStore : public StoreAPI
|
|
{
|
|
private:
|
|
/* The currently running substituter or empty. */
|
|
std::shared_ptr<Agent> runningSubstituter;
|
|
|
|
/* Ensure the substituter is running and return it. */
|
|
std::shared_ptr<Agent> substituter();
|
|
|
|
Path linksDir;
|
|
|
|
public:
|
|
|
|
/* Initialise the local store, upgrading the schema if
|
|
necessary. */
|
|
LocalStore(bool reserveSpace = true);
|
|
|
|
~LocalStore();
|
|
|
|
/* Implementations of abstract store API methods. */
|
|
|
|
bool isValidPath(const Path & path);
|
|
|
|
PathSet queryValidPaths(const PathSet & paths);
|
|
|
|
PathSet queryAllValidPaths();
|
|
|
|
ValidPathInfo queryPathInfo(const Path & path);
|
|
|
|
Hash queryPathHash(const Path & path);
|
|
|
|
void queryReferences(const Path & path, PathSet & references);
|
|
|
|
void queryReferrers(const Path & path, PathSet & referrers);
|
|
|
|
Path queryDeriver(const Path & path);
|
|
|
|
PathSet queryValidDerivers(const Path & path);
|
|
|
|
PathSet queryDerivationOutputs(const Path & path);
|
|
|
|
StringSet queryDerivationOutputNames(const Path & path);
|
|
|
|
Path queryPathFromHashPart(const string & hashPart);
|
|
|
|
PathSet querySubstitutablePaths(const PathSet & paths);
|
|
|
|
void querySubstitutablePathInfos(PathSet & paths,
|
|
SubstitutablePathInfos & infos);
|
|
|
|
void querySubstitutablePathInfos(const PathSet & paths,
|
|
SubstitutablePathInfos & infos);
|
|
|
|
Path addToStore(const string & name, const Path & srcPath,
|
|
bool recursive = true, HashType hashAlgo = htSHA256,
|
|
PathFilter & filter = defaultPathFilter, bool repair = false);
|
|
|
|
/* Like addToStore(), but the contents of the path are contained
|
|
in `dump', which is either a NAR serialisation (if recursive ==
|
|
true) or simply the contents of a regular file (if recursive ==
|
|
false). */
|
|
Path addToStoreFromDump(const string & dump, const string & name,
|
|
bool recursive = true, HashType hashAlgo = htSHA256, bool repair = false);
|
|
|
|
Path addTextToStore(const string & name, const string & s,
|
|
const PathSet & references, bool repair = false);
|
|
|
|
void exportPath(const Path & path, bool sign,
|
|
Sink & sink);
|
|
|
|
Paths importPaths(bool requireSignature, Source & source);
|
|
|
|
void buildPaths(const PathSet & paths, BuildMode buildMode);
|
|
|
|
void ensurePath(const Path & path);
|
|
|
|
void addTempRoot(const Path & path);
|
|
|
|
void addIndirectRoot(const Path & path);
|
|
|
|
void syncWithGC();
|
|
|
|
Roots findRoots();
|
|
|
|
void collectGarbage(const GCOptions & options, GCResults & results);
|
|
|
|
/* Optimise the disk space usage of the Nix store by hard-linking
|
|
files with the same contents. */
|
|
void optimiseStore(OptimiseStats & stats);
|
|
|
|
/* Generic variant of the above method. */
|
|
void optimiseStore();
|
|
|
|
/* Optimise a single store path. */
|
|
void optimisePath(const Path & path);
|
|
|
|
/* Check the integrity of the Nix store. Returns true if errors
|
|
remain. */
|
|
bool verifyStore(bool checkContents, bool repair);
|
|
|
|
/* Register the validity of a path, i.e., that `path' exists, that
|
|
the paths referenced by it exists, and in the case of an output
|
|
path of a derivation, that it has been produced by a successful
|
|
execution of the derivation (or something equivalent). Also
|
|
register the hash of the file system contents of the path. The
|
|
hash must be a SHA-256 hash. */
|
|
void registerValidPath(const ValidPathInfo & info);
|
|
|
|
void registerValidPaths(const ValidPathInfos & infos);
|
|
|
|
/* Register that the build of a derivation with output `path' has
|
|
failed. */
|
|
void registerFailedPath(const Path & path);
|
|
|
|
/* Query whether `path' previously failed to build. */
|
|
bool hasPathFailed(const Path & path);
|
|
|
|
PathSet queryFailedPaths();
|
|
|
|
void clearFailedPaths(const PathSet & paths);
|
|
|
|
void vacuumDB();
|
|
|
|
/* Repair the contents of the given path by redownloading it using
|
|
a substituter (if available). */
|
|
void repairPath(const Path & path);
|
|
|
|
/* Check whether the given valid path exists and has the right
|
|
contents. */
|
|
bool pathContentsGood(const Path & path);
|
|
|
|
void markContentsGood(const Path & path);
|
|
|
|
void createUser(const std::string & userName, uid_t userId);
|
|
|
|
private:
|
|
|
|
Path schemaPath;
|
|
|
|
/* Lock file used for upgrading. */
|
|
AutoCloseFD globalLock;
|
|
|
|
/* The SQLite database object. */
|
|
SQLite db;
|
|
|
|
/* Some precompiled SQLite statements. */
|
|
SQLiteStmt stmtRegisterValidPath;
|
|
SQLiteStmt stmtUpdatePathInfo;
|
|
SQLiteStmt stmtAddReference;
|
|
SQLiteStmt stmtQueryPathInfo;
|
|
SQLiteStmt stmtQueryReferences;
|
|
SQLiteStmt stmtQueryReferrers;
|
|
SQLiteStmt stmtInvalidatePath;
|
|
SQLiteStmt stmtRegisterFailedPath;
|
|
SQLiteStmt stmtHasPathFailed;
|
|
SQLiteStmt stmtQueryFailedPaths;
|
|
SQLiteStmt stmtClearFailedPath;
|
|
SQLiteStmt stmtAddDerivationOutput;
|
|
SQLiteStmt stmtQueryValidDerivers;
|
|
SQLiteStmt stmtQueryDerivationOutputs;
|
|
SQLiteStmt stmtQueryPathFromHashPart;
|
|
SQLiteStmt stmtQueryValidPaths;
|
|
|
|
/* Cache for pathContentsGood(). */
|
|
std::map<Path, bool> pathContentsGoodCache;
|
|
|
|
/* The file to which we write our temporary roots. */
|
|
Path fnTempRoots;
|
|
AutoCloseFD fdTempRoots;
|
|
|
|
int getSchema();
|
|
|
|
void openDB(bool create);
|
|
|
|
void makeStoreWritable();
|
|
|
|
uint64_t queryValidPathId(const Path & path);
|
|
|
|
uint64_t addValidPath(const ValidPathInfo & info, bool checkOutputs = true);
|
|
|
|
void addReference(uint64_t referrer, uint64_t reference);
|
|
|
|
void appendReferrer(const Path & from, const Path & to, bool lock);
|
|
|
|
void rewriteReferrers(const Path & path, bool purge, PathSet referrers);
|
|
|
|
void invalidatePath(const Path & path);
|
|
|
|
/* Delete a path from the Nix store. */
|
|
void invalidatePathChecked(const Path & path);
|
|
|
|
void verifyPath(const Path & path, const PathSet & store,
|
|
PathSet & done, PathSet & validPaths, bool repair, bool & errors);
|
|
|
|
void updatePathInfo(const ValidPathInfo & info);
|
|
|
|
struct GCState;
|
|
|
|
void deleteGarbage(GCState & state, const Path & path);
|
|
|
|
void tryToDelete(GCState & state, const Path & path);
|
|
|
|
bool canReachRoot(GCState & state, PathSet & visited, const Path & path);
|
|
|
|
void deletePathRecursive(GCState & state, const Path & path);
|
|
|
|
bool isActiveTempFile(const GCState & state,
|
|
const Path & path, const string & suffix);
|
|
|
|
int openGCLock(LockType lockType);
|
|
|
|
void removeUnusedLinks(const GCState & state);
|
|
|
|
string getLineFromSubstituter(Agent & run);
|
|
|
|
template<class T> T getIntLineFromSubstituter(Agent & run);
|
|
|
|
Path createTempDirInStore();
|
|
|
|
Path importPath(bool requireSignature, Source & source);
|
|
|
|
void checkDerivationOutputs(const Path & drvPath, const Derivation & drv);
|
|
|
|
typedef std::unordered_set<ino_t> InodeHash;
|
|
|
|
InodeHash loadInodeHash();
|
|
Strings readDirectoryIgnoringInodes(const Path & path, const InodeHash & inodeHash);
|
|
void optimisePath_(OptimiseStats & stats, const Path & path, InodeHash & inodeHash);
|
|
|
|
// Internal versions that are not wrapped in retry_sqlite.
|
|
bool isValidPath_(const Path & path);
|
|
void queryReferrers_(const Path & path, PathSet & referrers);
|
|
};
|
|
|
|
|
|
typedef std::pair<dev_t, ino_t> Inode;
|
|
typedef set<Inode> InodesSeen;
|
|
|
|
|
|
/* "Fix", or canonicalise, the meta-data of the files in a store path
|
|
after it has been built. In particular:
|
|
- the last modification date on each file is set to 1 (i.e.,
|
|
00:00:01 1/1/1970 UTC)
|
|
- the permissions are set of 444 or 555 (i.e., read-only with or
|
|
without execute permission; setuid bits etc. are cleared)
|
|
- the owner and group are set to the Nix user and group, if we're
|
|
running as root. */
|
|
void canonicalisePathMetaData(const Path & path, uid_t fromUid, InodesSeen & inodesSeen);
|
|
void canonicalisePathMetaData(const Path & path, uid_t fromUid);
|
|
|
|
void canonicaliseTimestampAndPermissions(const Path & path);
|
|
|
|
MakeError(PathInUse, Error);
|
|
|
|
/* Size below which a file is not considered for deduplication. */
|
|
extern const size_t deduplicationMinSize;
|
|
|
|
}
|