mirror of
https://github.com/postgres/postgres.git
synced 2026-04-02 15:57:24 -04:00
afb0d0712f
Previously, ScanKeywordLookup was passed an array of string pointers. This had some performance deficiencies: the strings themselves might be scattered all over the place depending on the compiler (and some quick checking shows that at least with gcc-on-Linux, they indeed weren't reliably close together). That led to very cache-unfriendly behavior as the binary search touched strings in many different pages. Also, depending on the platform, the string pointers might need to be adjusted at program start, so that they couldn't be simple constant data. And the ScanKeyword struct had been designed with an eye to 32-bit machines originally; on 64-bit it requires 16 bytes per keyword, making it even more cache-unfriendly. Redesign so that the keyword strings themselves are allocated consecutively (as part of one big char-string constant), thereby eliminating the touch-lots-of-unrelated-pages syndrome. And get rid of the ScanKeyword array in favor of three separate arrays: uint16 offsets into the keyword array, uint16 token codes, and uint8 keyword categories. That reduces the overhead per keyword to 5 bytes instead of 16 (even less in programs that only need one of the token codes and categories); moreover, the binary search only touches the offsets array, further reducing its cache footprint. This also lets us put the token codes somewhere else than the keyword strings are, which avoids some unpleasant build dependencies. While we're at it, wrap the data used by ScanKeywordLookup into a struct that can be treated as an opaque type by most callers. That doesn't change things much right now, but it will make it less painful to switch to a hash-based lookup method, as is being discussed in the mailing list thread. Most of the change here is associated with adding a generator script that can build the new data structure from the same list-of-PG_KEYWORD header representation we used before. The PG_KEYWORD lists that plpgsql and ecpg used to embed in their scanner .c files have to be moved into headers, and the Makefiles have to be taught to invoke the generator script. This work is also necessary if we're to consider hash-based lookup, since the generator script is what would be responsible for constructing a hash table. Aside from saving a few kilobytes in each program that includes the keyword table, this seems to speed up raw parsing (flex+bison) by a few percent. So it's worth doing even as it stands, though we think we can gain even more with a follow-on patch to switch to hash-based lookup. John Naylor, with further hacking by me Discussion: https://postgr.es/m/CAJVSVGXdFVU2sgym89XPL=Lv1zOS5=EHHQ8XWNzFL=mTXkKMLw@mail.gmail.com
134 lines
4.7 KiB
Makefile
134 lines
4.7 KiB
Makefile
#-------------------------------------------------------------------------
|
|
#
|
|
# Makefile
|
|
# Makefile for src/common
|
|
#
|
|
# These files are used by the Postgres backend, and also by frontend
|
|
# programs. These files provide common functionality that isn't directly
|
|
# concerned with portability and thus doesn't belong in src/port.
|
|
#
|
|
# This makefile generates three outputs:
|
|
#
|
|
# libpgcommon.a - contains object files with FRONTEND defined,
|
|
# for use by client applications
|
|
#
|
|
# libpgcommon_shlib.a - contains object files with FRONTEND defined,
|
|
# built suitably for use in shared libraries; for use
|
|
# by frontend libraries
|
|
#
|
|
# libpgcommon_srv.a - contains object files without FRONTEND defined,
|
|
# for use only by the backend
|
|
#
|
|
# IDENTIFICATION
|
|
# src/common/Makefile
|
|
#
|
|
#-------------------------------------------------------------------------
|
|
|
|
subdir = src/common
|
|
top_builddir = ../..
|
|
include $(top_builddir)/src/Makefile.global
|
|
|
|
# don't include subdirectory-path-dependent -I and -L switches
|
|
STD_CPPFLAGS := $(filter-out -I$(top_srcdir)/src/include -I$(top_builddir)/src/include,$(CPPFLAGS))
|
|
STD_LDFLAGS := $(filter-out -L$(top_builddir)/src/common -L$(top_builddir)/src/port,$(LDFLAGS))
|
|
override CPPFLAGS += -DVAL_CONFIGURE="\"$(configure_args)\""
|
|
override CPPFLAGS += -DVAL_CC="\"$(CC)\""
|
|
override CPPFLAGS += -DVAL_CPPFLAGS="\"$(STD_CPPFLAGS)\""
|
|
override CPPFLAGS += -DVAL_CFLAGS="\"$(CFLAGS)\""
|
|
override CPPFLAGS += -DVAL_CFLAGS_SL="\"$(CFLAGS_SL)\""
|
|
override CPPFLAGS += -DVAL_LDFLAGS="\"$(STD_LDFLAGS)\""
|
|
override CPPFLAGS += -DVAL_LDFLAGS_EX="\"$(LDFLAGS_EX)\""
|
|
override CPPFLAGS += -DVAL_LDFLAGS_SL="\"$(LDFLAGS_SL)\""
|
|
override CPPFLAGS += -DVAL_LIBS="\"$(LIBS)\""
|
|
|
|
override CPPFLAGS := -DFRONTEND -I. -I$(top_srcdir)/src/common $(CPPFLAGS)
|
|
LIBS += $(PTHREAD_LIBS)
|
|
|
|
OBJS_COMMON = base64.o config_info.o controldata_utils.o exec.o file_perm.o \
|
|
ip.o keywords.o kwlookup.o link-canary.o md5.o pg_lzcompress.o \
|
|
pgfnames.o psprintf.o relpath.o \
|
|
rmtree.o saslprep.o scram-common.o string.o unicode_norm.o \
|
|
username.o wait_error.o
|
|
|
|
ifeq ($(with_openssl),yes)
|
|
OBJS_COMMON += sha2_openssl.o
|
|
else
|
|
OBJS_COMMON += sha2.o
|
|
endif
|
|
|
|
# A few files are currently only built for frontend, not server
|
|
OBJS_FRONTEND = $(OBJS_COMMON) fe_memutils.o file_utils.o restricted_token.o
|
|
|
|
# foo.o, foo_shlib.o, and foo_srv.o are all built from foo.c
|
|
OBJS_SHLIB = $(OBJS_FRONTEND:%.o=%_shlib.o)
|
|
OBJS_SRV = $(OBJS_COMMON:%.o=%_srv.o)
|
|
|
|
all: libpgcommon.a libpgcommon_shlib.a libpgcommon_srv.a
|
|
|
|
distprep: kwlist_d.h
|
|
|
|
# libpgcommon is needed by some contrib
|
|
install: all installdirs
|
|
$(INSTALL_STLIB) libpgcommon.a '$(DESTDIR)$(libdir)/libpgcommon.a'
|
|
$(INSTALL_STLIB) libpgcommon_shlib.a '$(DESTDIR)$(libdir)/libpgcommon_shlib.a'
|
|
|
|
installdirs:
|
|
$(MKDIR_P) '$(DESTDIR)$(libdir)'
|
|
|
|
uninstall:
|
|
rm -f '$(DESTDIR)$(libdir)/libpgcommon.a'
|
|
rm -f '$(DESTDIR)$(libdir)/libpgcommon_shlib.a'
|
|
|
|
libpgcommon.a: $(OBJS_FRONTEND)
|
|
rm -f $@
|
|
$(AR) $(AROPT) $@ $^
|
|
|
|
#
|
|
# Shared library versions of object files
|
|
#
|
|
|
|
libpgcommon_shlib.a: $(OBJS_SHLIB)
|
|
rm -f $@
|
|
$(AR) $(AROPT) $@ $^
|
|
|
|
# Because this uses its own compilation rule, it doesn't use the
|
|
# dependency tracking logic from Makefile.global. To make sure that
|
|
# dependency tracking works anyway for the *_shlib.o files, depend on
|
|
# their *.o siblings as well, which do have proper dependencies. It's
|
|
# a hack that might fail someday if there is a *_shlib.o without a
|
|
# corresponding *.o, but there seems little reason for that.
|
|
%_shlib.o: %.c %.o
|
|
$(CC) $(CFLAGS) $(CFLAGS_SL) $(CPPFLAGS) -c $< -o $@
|
|
|
|
#
|
|
# Server versions of object files
|
|
#
|
|
|
|
libpgcommon_srv.a: $(OBJS_SRV)
|
|
rm -f $@
|
|
$(AR) $(AROPT) $@ $^
|
|
|
|
# Because this uses its own compilation rule, it doesn't use the
|
|
# dependency tracking logic from Makefile.global. To make sure that
|
|
# dependency tracking works anyway for the *_srv.o files, depend on
|
|
# their *.o siblings as well, which do have proper dependencies. It's
|
|
# a hack that might fail someday if there is a *_srv.o without a
|
|
# corresponding *.o, but it works for now.
|
|
%_srv.o: %.c %.o
|
|
$(CC) $(CFLAGS) $(subst -DFRONTEND,, $(CPPFLAGS)) -c $< -o $@
|
|
|
|
# generate SQL keyword lookup table to be included into keywords*.o.
|
|
kwlist_d.h: $(top_srcdir)/src/include/parser/kwlist.h $(top_srcdir)/src/tools/gen_keywordlist.pl
|
|
$(PERL) $(top_srcdir)/src/tools/gen_keywordlist.pl --extern $<
|
|
|
|
# Dependencies of keywords*.o need to be managed explicitly to make sure
|
|
# that you don't get broken parsing code, even in a non-enable-depend build.
|
|
keywords.o keywords_shlib.o keywords_srv.o: kwlist_d.h
|
|
|
|
# kwlist_d.h is in the distribution tarball, so it is not cleaned here.
|
|
clean distclean:
|
|
rm -f libpgcommon.a libpgcommon_shlib.a libpgcommon_srv.a
|
|
rm -f $(OBJS_FRONTEND) $(OBJS_SHLIB) $(OBJS_SRV)
|
|
|
|
maintainer-clean: distclean
|
|
rm -f kwlist_d.h
|