[review] Use libxxhash for hashing, if present
Commit Message
Christian Biesinger has uploaded a new patch set version (#2).
Change URL: https://gnutoolchain-gerrit.osci.io/r/c/binutils-gdb/+/39
......................................................................
Use libxxhash for hashing, if present
XXHash is faster than htab_hash_string:
------------------------------------------------------------
Benchmark Time CPU Iterations
------------------------------------------------------------
BM_xxh3 11 ns 11 ns 65887249
BM_xxh32 19 ns 19 ns 36511877
BM_xxh64 16 ns 16 ns 42964585
BM_hash_string 182 ns 182 ns 3853125
BM_iterative_hash 77 ns 77 ns 9087638
Unfortunately, XXH3 is still experimental (see
https://github.com/Cyan4973/xxHash#user-content-new-experimental-hash-algorithm)
However, regular XXH64 is still a lot faster than
htab_hash_string per my benchmark above. I used the
following string for the benchmark:
static constexpr char str[] = "_ZZZL13make_gdb_typeP7gdbarchP10tdesc_typeEN16gdb_type_creator19make_gdb_type_flagsEPK22tdesc_type_with_fieldsE19__PRETTY_FUNCTION__";
htab_hash_string is currently 4.35% + 7.98% (rehashing) of gdb
startup when attaching to Chrome's content_shell.
An additional 5.21% is spent in msymbol_hash, which does not use
this hash function. Unfortunately, since it has to lowercase the
string, it can't use this hash function.
BM_msymbol_hash 52 ns 52 ns 13281495
It may be worth investigating if strlen+XXHash is still faster than
htab_hash_string, which would make it easier to use in more places.
Debian ships xxhash as libxxhash{0,-dev}. Fedora ships it as xxhash-devel.
gdb/ChangeLog:
2019-09-27 Christian Biesinger <cbiesinger@google.com>
* Makefile.in: Link with libxxhash.
* config.in: Regenerate.
* configure: Regenerate.
* configure.ac: Search for libxxhash.
* utils.c (fast_hash): Use xxhash if present.
Change-Id: Icab218388b9f829522ed3977f04301ae6d4fc4ca
---
M gdb/Makefile.in
M gdb/config.in
M gdb/configure
M gdb/configure.ac
M gdb/utils.c
5 files changed, 529 insertions(+), 2 deletions(-)
@@ -187,10 +187,14 @@
# Where is lzma? This will be empty if lzma was not available.
LIBLZMA = @LIBLZMA@
-# Where is libbabeltrace? This will be empty if lbabeltrace was not
+# Where is libbabeltrace? This will be empty if libbabeltrace was not
# available.
LIBBABELTRACE = @LIBBABELTRACE@
+# Where is libxxhash? This will be empty if libxxhash was not
+# available.
+LIBXXHASH = @LIBXXHASH@
+
# Where is libipt? This will be empty if libipt was not available.
LIBIPT = @LIBIPT@
@@ -597,7 +601,7 @@
@LIBS@ @GUILE_LIBS@ @PYTHON_LIBS@ \
$(LIBEXPAT) $(LIBLZMA) $(LIBBABELTRACE) $(LIBIPT) \
$(LIBIBERTY) $(WIN32LIBS) $(LIBGNU) $(LIBICONV) $(LIBMPFR) \
- $(SRCHIGH_LIBS)
+ $(SRCHIGH_LIBS) $(LIBXXHASH)
CDEPS = $(NAT_CDEPS) $(SIM) $(BFD) $(READLINE_DEPS) $(LIBCTF) \
$(OPCODES) $(INTL_DEPS) $(LIBIBERTY) $(CONFIG_DEPS) $(LIBGNU)
@@ -255,6 +255,9 @@
/* Define to 1 if you have the <libunwind-ia64.h> header file. */
#undef HAVE_LIBUNWIND_IA64_H
+/* Define if you have the xxhash library. */
+#undef HAVE_LIBXXHASH
+
/* Define to 1 if you have the <linux/elf.h> header file. */
#undef HAVE_LINUX_ELF_H
@@ -627,6 +627,9 @@
GDB_TRANSFORM_NAME
XSLTPROC
GDB_NM_FILE
+LTLIBXXHASH
+LIBXXHASH
+HAVE_LIBXXHASH
LTLIBBABELTRACE
LIBBABELTRACE
HAVE_LIBBABELTRACE
@@ -897,6 +900,8 @@
enable_gdbserver
with_babeltrace
with_libbabeltrace_prefix
+with_xxhash
+with_libxxhash_prefix
enable_unit_tests
'
ac_precious_vars='build_alias
@@ -1627,6 +1632,9 @@
--with-babeltrace include babeltrace support (auto/yes/no)
--with-libbabeltrace-prefix[=DIR] search for libbabeltrace in DIR/include and DIR/lib
--without-libbabeltrace-prefix don't search for libbabeltrace in includedir and libdir
+ --with-xxhash use libxxhash for hashing (faster) (auto/yes/no)
+ --with-libxxhash-prefix[=DIR] search for libxxhash in DIR/include and DIR/lib
+ --without-libxxhash-prefix don't search for libxxhash in includedir and libdir
Some influential environment variables:
CC C compiler command
@@ -17556,6 +17564,491 @@
fi
fi
+# Check for xxhash
+
+# Check whether --with-xxhash was given.
+if test "${with_xxhash+set}" = set; then :
+ withval=$with_xxhash;
+else
+ with_xxhash=auto
+fi
+
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether to use xxhash" >&5
+$as_echo_n "checking whether to use xxhash... " >&6; }
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $with_xxhash" >&5
+$as_echo "$with_xxhash" >&6; }
+
+if test "x$with_xxhash" != "xno"; then
+
+
+
+
+
+
+
+
+ use_additional=yes
+
+ acl_save_prefix="$prefix"
+ prefix="$acl_final_prefix"
+ acl_save_exec_prefix="$exec_prefix"
+ exec_prefix="$acl_final_exec_prefix"
+
+ eval additional_includedir=\"$includedir\"
+ eval additional_libdir=\"$libdir\"
+
+ exec_prefix="$acl_save_exec_prefix"
+ prefix="$acl_save_prefix"
+
+
+# Check whether --with-libxxhash-prefix was given.
+if test "${with_libxxhash_prefix+set}" = set; then :
+ withval=$with_libxxhash_prefix;
+ if test "X$withval" = "Xno"; then
+ use_additional=no
+ else
+ if test "X$withval" = "X"; then
+
+ acl_save_prefix="$prefix"
+ prefix="$acl_final_prefix"
+ acl_save_exec_prefix="$exec_prefix"
+ exec_prefix="$acl_final_exec_prefix"
+
+ eval additional_includedir=\"$includedir\"
+ eval additional_libdir=\"$libdir\"
+
+ exec_prefix="$acl_save_exec_prefix"
+ prefix="$acl_save_prefix"
+
+ else
+ additional_includedir="$withval/include"
+ additional_libdir="$withval/lib"
+ fi
+ fi
+
+fi
+
+ LIBXXHASH=
+ LTLIBXXHASH=
+ INCXXHASH=
+ rpathdirs=
+ ltrpathdirs=
+ names_already_handled=
+ names_next_round='xxhash '
+ while test -n "$names_next_round"; do
+ names_this_round="$names_next_round"
+ names_next_round=
+ for name in $names_this_round; do
+ already_handled=
+ for n in $names_already_handled; do
+ if test "$n" = "$name"; then
+ already_handled=yes
+ break
+ fi
+ done
+ if test -z "$already_handled"; then
+ names_already_handled="$names_already_handled $name"
+ uppername=`echo "$name" | sed -e 'y|abcdefghijklmnopqrstuvwxyz./-|ABCDEFGHIJKLMNOPQRSTUVWXYZ___|'`
+ eval value=\"\$HAVE_LIB$uppername\"
+ if test -n "$value"; then
+ if test "$value" = yes; then
+ eval value=\"\$LIB$uppername\"
+ test -z "$value" || LIBXXHASH="${LIBXXHASH}${LIBXXHASH:+ }$value"
+ eval value=\"\$LTLIB$uppername\"
+ test -z "$value" || LTLIBXXHASH="${LTLIBXXHASH}${LTLIBXXHASH:+ }$value"
+ else
+ :
+ fi
+ else
+ found_dir=
+ found_la=
+ found_so=
+ found_a=
+ if test $use_additional = yes; then
+ if test -n "$shlibext" && test -f "$additional_libdir/lib$name.$shlibext"; then
+ found_dir="$additional_libdir"
+ found_so="$additional_libdir/lib$name.$shlibext"
+ if test -f "$additional_libdir/lib$name.la"; then
+ found_la="$additional_libdir/lib$name.la"
+ fi
+ else
+ if test -f "$additional_libdir/lib$name.$libext"; then
+ found_dir="$additional_libdir"
+ found_a="$additional_libdir/lib$name.$libext"
+ if test -f "$additional_libdir/lib$name.la"; then
+ found_la="$additional_libdir/lib$name.la"
+ fi
+ fi
+ fi
+ fi
+ if test "X$found_dir" = "X"; then
+ for x in $LDFLAGS $LTLIBXXHASH; do
+
+ acl_save_prefix="$prefix"
+ prefix="$acl_final_prefix"
+ acl_save_exec_prefix="$exec_prefix"
+ exec_prefix="$acl_final_exec_prefix"
+ eval x=\"$x\"
+ exec_prefix="$acl_save_exec_prefix"
+ prefix="$acl_save_prefix"
+
+ case "$x" in
+ -L*)
+ dir=`echo "X$x" | sed -e 's/^X-L//'`
+ if test -n "$shlibext" && test -f "$dir/lib$name.$shlibext"; then
+ found_dir="$dir"
+ found_so="$dir/lib$name.$shlibext"
+ if test -f "$dir/lib$name.la"; then
+ found_la="$dir/lib$name.la"
+ fi
+ else
+ if test -f "$dir/lib$name.$libext"; then
+ found_dir="$dir"
+ found_a="$dir/lib$name.$libext"
+ if test -f "$dir/lib$name.la"; then
+ found_la="$dir/lib$name.la"
+ fi
+ fi
+ fi
+ ;;
+ esac
+ if test "X$found_dir" != "X"; then
+ break
+ fi
+ done
+ fi
+ if test "X$found_dir" != "X"; then
+ LTLIBXXHASH="${LTLIBXXHASH}${LTLIBXXHASH:+ }-L$found_dir -l$name"
+ if test "X$found_so" != "X"; then
+ if test "$enable_rpath" = no || test "X$found_dir" = "X/usr/lib"; then
+ LIBXXHASH="${LIBXXHASH}${LIBXXHASH:+ }$found_so"
+ else
+ haveit=
+ for x in $ltrpathdirs; do
+ if test "X$x" = "X$found_dir"; then
+ haveit=yes
+ break
+ fi
+ done
+ if test -z "$haveit"; then
+ ltrpathdirs="$ltrpathdirs $found_dir"
+ fi
+ if test "$hardcode_direct" = yes; then
+ LIBXXHASH="${LIBXXHASH}${LIBXXHASH:+ }$found_so"
+ else
+ if test -n "$hardcode_libdir_flag_spec" && test "$hardcode_minus_L" = no; then
+ LIBXXHASH="${LIBXXHASH}${LIBXXHASH:+ }$found_so"
+ haveit=
+ for x in $rpathdirs; do
+ if test "X$x" = "X$found_dir"; then
+ haveit=yes
+ break
+ fi
+ done
+ if test -z "$haveit"; then
+ rpathdirs="$rpathdirs $found_dir"
+ fi
+ else
+ haveit=
+ for x in $LDFLAGS $LIBXXHASH; do
+
+ acl_save_prefix="$prefix"
+ prefix="$acl_final_prefix"
+ acl_save_exec_prefix="$exec_prefix"
+ exec_prefix="$acl_final_exec_prefix"
+ eval x=\"$x\"
+ exec_prefix="$acl_save_exec_prefix"
+ prefix="$acl_save_prefix"
+
+ if test "X$x" = "X-L$found_dir"; then
+ haveit=yes
+ break
+ fi
+ done
+ if test -z "$haveit"; then
+ LIBXXHASH="${LIBXXHASH}${LIBXXHASH:+ }-L$found_dir"
+ fi
+ if test "$hardcode_minus_L" != no; then
+ LIBXXHASH="${LIBXXHASH}${LIBXXHASH:+ }$found_so"
+ else
+ LIBXXHASH="${LIBXXHASH}${LIBXXHASH:+ }-l$name"
+ fi
+ fi
+ fi
+ fi
+ else
+ if test "X$found_a" != "X"; then
+ LIBXXHASH="${LIBXXHASH}${LIBXXHASH:+ }$found_a"
+ else
+ LIBXXHASH="${LIBXXHASH}${LIBXXHASH:+ }-L$found_dir -l$name"
+ fi
+ fi
+ additional_includedir=
+ case "$found_dir" in
+ */lib | */lib/)
+ basedir=`echo "X$found_dir" | sed -e 's,^X,,' -e 's,/lib/*$,,'`
+ additional_includedir="$basedir/include"
+ ;;
+ esac
+ if test "X$additional_includedir" != "X"; then
+ if test "X$additional_includedir" != "X/usr/include"; then
+ haveit=
+ if test "X$additional_includedir" = "X/usr/local/include"; then
+ if test -n "$GCC"; then
+ case $host_os in
+ linux*) haveit=yes;;
+ esac
+ fi
+ fi
+ if test -z "$haveit"; then
+ for x in $CPPFLAGS $INCXXHASH; do
+
+ acl_save_prefix="$prefix"
+ prefix="$acl_final_prefix"
+ acl_save_exec_prefix="$exec_prefix"
+ exec_prefix="$acl_final_exec_prefix"
+ eval x=\"$x\"
+ exec_prefix="$acl_save_exec_prefix"
+ prefix="$acl_save_prefix"
+
+ if test "X$x" = "X-I$additional_includedir"; then
+ haveit=yes
+ break
+ fi
+ done
+ if test -z "$haveit"; then
+ if test -d "$additional_includedir"; then
+ INCXXHASH="${INCXXHASH}${INCXXHASH:+ }-I$additional_includedir"
+ fi
+ fi
+ fi
+ fi
+ fi
+ if test -n "$found_la"; then
+ save_libdir="$libdir"
+ case "$found_la" in
+ */* | *\\*) . "$found_la" ;;
+ *) . "./$found_la" ;;
+ esac
+ libdir="$save_libdir"
+ for dep in $dependency_libs; do
+ case "$dep" in
+ -L*)
+ additional_libdir=`echo "X$dep" | sed -e 's/^X-L//'`
+ if test "X$additional_libdir" != "X/usr/lib"; then
+ haveit=
+ if test "X$additional_libdir" = "X/usr/local/lib"; then
+ if test -n "$GCC"; then
+ case $host_os in
+ linux*) haveit=yes;;
+ esac
+ fi
+ fi
+ if test -z "$haveit"; then
+ haveit=
+ for x in $LDFLAGS $LIBXXHASH; do
+
+ acl_save_prefix="$prefix"
+ prefix="$acl_final_prefix"
+ acl_save_exec_prefix="$exec_prefix"
+ exec_prefix="$acl_final_exec_prefix"
+ eval x=\"$x\"
+ exec_prefix="$acl_save_exec_prefix"
+ prefix="$acl_save_prefix"
+
+ if test "X$x" = "X-L$additional_libdir"; then
+ haveit=yes
+ break
+ fi
+ done
+ if test -z "$haveit"; then
+ if test -d "$additional_libdir"; then
+ LIBXXHASH="${LIBXXHASH}${LIBXXHASH:+ }-L$additional_libdir"
+ fi
+ fi
+ haveit=
+ for x in $LDFLAGS $LTLIBXXHASH; do
+
+ acl_save_prefix="$prefix"
+ prefix="$acl_final_prefix"
+ acl_save_exec_prefix="$exec_prefix"
+ exec_prefix="$acl_final_exec_prefix"
+ eval x=\"$x\"
+ exec_prefix="$acl_save_exec_prefix"
+ prefix="$acl_save_prefix"
+
+ if test "X$x" = "X-L$additional_libdir"; then
+ haveit=yes
+ break
+ fi
+ done
+ if test -z "$haveit"; then
+ if test -d "$additional_libdir"; then
+ LTLIBXXHASH="${LTLIBXXHASH}${LTLIBXXHASH:+ }-L$additional_libdir"
+ fi
+ fi
+ fi
+ fi
+ ;;
+ -R*)
+ dir=`echo "X$dep" | sed -e 's/^X-R//'`
+ if test "$enable_rpath" != no; then
+ haveit=
+ for x in $rpathdirs; do
+ if test "X$x" = "X$dir"; then
+ haveit=yes
+ break
+ fi
+ done
+ if test -z "$haveit"; then
+ rpathdirs="$rpathdirs $dir"
+ fi
+ haveit=
+ for x in $ltrpathdirs; do
+ if test "X$x" = "X$dir"; then
+ haveit=yes
+ break
+ fi
+ done
+ if test -z "$haveit"; then
+ ltrpathdirs="$ltrpathdirs $dir"
+ fi
+ fi
+ ;;
+ -l*)
+ names_next_round="$names_next_round "`echo "X$dep" | sed -e 's/^X-l//'`
+ ;;
+ *.la)
+ names_next_round="$names_next_round "`echo "X$dep" | sed -e 's,^X.*/,,' -e 's,^lib,,' -e 's,\.la$,,'`
+ ;;
+ *)
+ LIBXXHASH="${LIBXXHASH}${LIBXXHASH:+ }$dep"
+ LTLIBXXHASH="${LTLIBXXHASH}${LTLIBXXHASH:+ }$dep"
+ ;;
+ esac
+ done
+ fi
+ else
+ LIBXXHASH="${LIBXXHASH}${LIBXXHASH:+ }-l$name"
+ LTLIBXXHASH="${LTLIBXXHASH}${LTLIBXXHASH:+ }-l$name"
+ fi
+ fi
+ fi
+ done
+ done
+ if test "X$rpathdirs" != "X"; then
+ if test -n "$hardcode_libdir_separator"; then
+ alldirs=
+ for found_dir in $rpathdirs; do
+ alldirs="${alldirs}${alldirs:+$hardcode_libdir_separator}$found_dir"
+ done
+ acl_save_libdir="$libdir"
+ libdir="$alldirs"
+ eval flag=\"$hardcode_libdir_flag_spec\"
+ libdir="$acl_save_libdir"
+ LIBXXHASH="${LIBXXHASH}${LIBXXHASH:+ }$flag"
+ else
+ for found_dir in $rpathdirs; do
+ acl_save_libdir="$libdir"
+ libdir="$found_dir"
+ eval flag=\"$hardcode_libdir_flag_spec\"
+ libdir="$acl_save_libdir"
+ LIBXXHASH="${LIBXXHASH}${LIBXXHASH:+ }$flag"
+ done
+ fi
+ fi
+ if test "X$ltrpathdirs" != "X"; then
+ for found_dir in $ltrpathdirs; do
+ LTLIBXXHASH="${LTLIBXXHASH}${LTLIBXXHASH:+ }-R$found_dir"
+ done
+ fi
+
+
+ ac_save_CPPFLAGS="$CPPFLAGS"
+
+ for element in $INCXXHASH; do
+ haveit=
+ for x in $CPPFLAGS; do
+
+ acl_save_prefix="$prefix"
+ prefix="$acl_final_prefix"
+ acl_save_exec_prefix="$exec_prefix"
+ exec_prefix="$acl_final_exec_prefix"
+ eval x=\"$x\"
+ exec_prefix="$acl_save_exec_prefix"
+ prefix="$acl_save_prefix"
+
+ if test "X$x" = "X$element"; then
+ haveit=yes
+ break
+ fi
+ done
+ if test -z "$haveit"; then
+ CPPFLAGS="${CPPFLAGS}${CPPFLAGS:+ }$element"
+ fi
+ done
+
+
+ { $as_echo "$as_me:${as_lineno-$LINENO}: checking for libxxhash" >&5
+$as_echo_n "checking for libxxhash... " >&6; }
+if ${ac_cv_libxxhash+:} false; then :
+ $as_echo_n "(cached) " >&6
+else
+
+ ac_save_LIBS="$LIBS"
+ LIBS="$LIBS $LIBXXHASH"
+ cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h. */
+#include <xxhash.h>
+int
+main ()
+{
+XXH32("foo", 3, 0);
+
+ ;
+ return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+ ac_cv_libxxhash=yes
+else
+ ac_cv_libxxhash=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+ conftest$ac_exeext conftest.$ac_ext
+ LIBS="$ac_save_LIBS"
+
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_libxxhash" >&5
+$as_echo "$ac_cv_libxxhash" >&6; }
+ if test "$ac_cv_libxxhash" = yes; then
+ HAVE_LIBXXHASH=yes
+
+$as_echo "#define HAVE_LIBXXHASH 1" >>confdefs.h
+
+ { $as_echo "$as_me:${as_lineno-$LINENO}: checking how to link with libxxhash" >&5
+$as_echo_n "checking how to link with libxxhash... " >&6; }
+ { $as_echo "$as_me:${as_lineno-$LINENO}: result: $LIBXXHASH" >&5
+$as_echo "$LIBXXHASH" >&6; }
+ else
+ HAVE_LIBXXHASH=no
+ CPPFLAGS="$ac_save_CPPFLAGS"
+ LIBXXHASH=
+ LTLIBXXHASH=
+ fi
+
+
+
+
+
+
+ if test "$HAVE_XXHASH" != yes; then
+ if test "$with_xxhash" = yes; then
+ as_fn_error $? "xxhash is missing or unusable" "$LINENO" 5
+ fi
+ fi
+fi
+
# If nativefile (NAT_FILE) is not set in configure.nat, we link to an
# empty version.
@@ -2217,6 +2217,25 @@
fi
fi
+# Check for xxhash
+AC_ARG_WITH(xxhash,
+ AC_HELP_STRING([--with-xxhash], [use libxxhash for hashing (faster) (auto/yes/no)]),
+ [], [with_xxhash=auto])
+AC_MSG_CHECKING([whether to use xxhash])
+AC_MSG_RESULT([$with_xxhash])
+
+if test "x$with_xxhash" != "xno"; then
+ AC_LIB_HAVE_LINKFLAGS([xxhash], [],
+ [#include <xxhash.h>],
+ [XXH32("foo", 3, 0);
+ ])
+ if test "$HAVE_XXHASH" != yes; then
+ if test "$with_xxhash" = yes; then
+ AC_MSG_ERROR([xxhash is missing or unusable])
+ fi
+ fi
+fi
+
# If nativefile (NAT_FILE) is not set in configure.nat, we link to an
# empty version.
@@ -36,6 +36,10 @@
#include <pc.h>
#endif
+#ifdef HAVE_LIBXXHASH
+#include <xxhash.h>
+#endif
+
#include <signal.h>
#include "gdbcmd.h"
#include "serial.h"
@@ -3441,7 +3445,11 @@
unsigned int
fast_hash (const char* str, size_t len)
{
+#ifdef HAVE_LIBXXHASH
+ return XXH64 (str, len, 0);
+#else
return iterative_hash (str, len, 0);
+#endif
}
void