guix/config-daemon.ac
Ludovic Courtès 472a0e82a5
daemon: Do not deduplicate files smaller than 8 KiB.
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.
2021-11-16 14:34:28 +01:00

143 lines
4.3 KiB
Text

dnl -*- Autoconf -*- fragment for the C++ daemon.
AC_MSG_CHECKING([whether to build daemon])
AC_MSG_RESULT([$guix_build_daemon])
dnl C++ environment. This macro must be used unconditionnaly.
AC_PROG_CXX
AM_PROG_AR
AC_LANG([C++])
if test "x$guix_build_daemon" = "xyes"; then
GUIX_ASSERT_CXX11
AC_PROG_RANLIB
AC_CONFIG_HEADERS([nix/config.h])
dnl Use 64-bit file system calls so that we can support files > 2 GiB.
AC_SYS_LARGEFILE
dnl Look for zlib, a required dependency.
AC_CHECK_LIB([z], [gzdopen], [true],
[AC_MSG_ERROR([Guix requires zlib. See http://www.zlib.net/.])])
AC_CHECK_HEADERS([zlib.h], [true],
[AC_MSG_ERROR([Guix requires zlib. See http://www.zlib.net/.])])
dnl Look for libbz2, an optional dependency.
AC_CHECK_LIB([bz2], [BZ2_bzWriteOpen], [HAVE_LIBBZ2=yes], [HAVE_LIBBZ2=no])
if test "x$HAVE_LIBBZ2" = xyes; then
AC_CHECK_HEADERS([bzlib.h])
HAVE_LIBBZ2="$ac_cv_header_bzlib_h"
fi
dnl Look for SQLite, a required dependency.
PKG_CHECK_MODULES([SQLITE3], [sqlite3 >= 3.6.19])
AC_DEFINE_UNQUOTED([SYSTEM], ["$guix_system"],
[Guix host system type--i.e., platform and OS kernel tuple.])
case "$LIBGCRYPT_PREFIX" in
no)
LIBGCRYPT_CFLAGS=""
;;
*)
LIBGCRYPT_CFLAGS="-I$LIBGCRYPT_PREFIX/include"
;;
esac
case "$LIBGCRYPT_LIBDIR" in
no | "")
LIBGCRYPT_LIBS="-lgcrypt"
;;
*)
LIBGCRYPT_LIBS="-L$LIBGCRYPT_LIBDIR -lgcrypt"
;;
esac
AC_SUBST([LIBGCRYPT_CFLAGS])
AC_SUBST([LIBGCRYPT_LIBS])
save_CFLAGS="$CFLAGS"
save_LDFLAGS="$LDFLAGS"
CFLAGS="$CFLAGS $LIBGCRYPT_CFLAGS"
LDFLAGS="$LDFLAGS $LIBGCRYPT_LDFLAGS"
have_gcrypt=yes
AC_CHECK_LIB([gcrypt], [gcry_md_open], [:], [have_gcrypt=no])
AC_CHECK_HEADER([gcrypt.h], [:], [have_gcrypt=no])
if test "x$have_gcrypt" != "xyes"; then
AC_MSG_ERROR([GNU libgcrypt not found; please install it.])
fi
CFLAGS="$save_CFLAGS"
LDFLAGS="$save_LDFLAGS"
dnl Chroot support.
AC_CHECK_FUNCS([chroot unshare])
AC_CHECK_HEADERS([sched.h sys/param.h sys/mount.h sys/syscall.h])
if test "x$ac_cv_func_chroot" != "xyes"; then
AC_MSG_ERROR(['chroot' function missing, bailing out])
fi
dnl lutimes and lchown: used when canonicalizing store items.
dnl posix_fallocate: used when extracting archives.
dnl vfork: to speed up spawning of helper programs.
dnl `--> now disabled because of unpredictable behavior:
dnl see <http://lists.gnu.org/archive/html/guix-devel/2014-05/msg00036.html>
dnl and Nix commit f794465c (Nov. 2012).
dnl sched_setaffinity: to improve RPC locality.
dnl statvfs: to detect disk-full conditions.
dnl strsignal: for error reporting.
dnl statx: fine-grain 'stat' call, new in glibc 2.28.
AC_CHECK_FUNCS([lutimes lchown posix_fallocate sched_setaffinity \
statvfs nanosleep strsignal statx])
dnl Check for <locale>.
AC_LANG_PUSH(C++)
AC_CHECK_HEADERS([locale])
AC_LANG_POP(C++)
dnl Check whether we have the `personality' syscall, which allows us
dnl to do i686-linux builds on x86_64-linux machines.
AC_CHECK_HEADERS([sys/personality.h])
dnl Determine the appropriate default list of substitute URLs (GnuTLS
dnl is required so we can default to 'https'.)
guix_substitute_urls="https://ci.guix.gnu.org https://bordeaux.guix.gnu.org"
AC_MSG_CHECKING([for default substitute URLs])
AC_MSG_RESULT([$guix_substitute_urls])
AC_DEFINE_UNQUOTED([GUIX_SUBSTITUTE_URLS], ["$guix_substitute_urls"],
[Default list of substitute URLs used by 'guix-daemon'.])
dnl Check for Guile-SSH, which is required by 'guix offload'.
GUIX_CHECK_GUILE_SSH
case "x$guix_cv_have_recent_guile_ssh" in
xyes)
guix_build_daemon_offload="yes"
AC_DEFINE([HAVE_DAEMON_OFFLOAD_HOOK], [1],
[Define if the daemon's 'offload' build hook is being built (requires Guile-SSH).])
;;
*)
guix_build_daemon_offload="no"
;;
esac
dnl Temporary directory used to store the daemon's data.
GUIX_TEST_ROOT_DIRECTORY
GUIX_TEST_ROOT="$ac_cv_guix_test_root"
AC_SUBST([GUIX_TEST_ROOT])
GUIX_CHECK_LOCALSTATEDIR
fi
AM_CONDITIONAL([HAVE_LIBBZ2], [test "x$HAVE_LIBBZ2" = "xyes"])
AM_CONDITIONAL([BUILD_DAEMON], [test "x$guix_build_daemon" = "xyes"])
AM_CONDITIONAL([BUILD_DAEMON_OFFLOAD], \
[test "x$guix_build_daemon" = "xyes" \
&& test "x$guix_build_daemon_offload" = "xyes"])