diff options
Diffstat (limited to 'libnetdata/procfile')
| -rw-r--r-- | libnetdata/procfile/Makefile.am | 9 | ||||
| -rw-r--r-- | libnetdata/procfile/Makefile.in | 464 | ||||
| -rw-r--r-- | libnetdata/procfile/README.md | 61 | ||||
| -rw-r--r-- | libnetdata/procfile/procfile.c | 472 | ||||
| -rw-r--r-- | libnetdata/procfile/procfile.h | 106 |
5 files changed, 1112 insertions, 0 deletions
diff --git a/libnetdata/procfile/Makefile.am b/libnetdata/procfile/Makefile.am new file mode 100644 index 00000000..1cb69ed9 --- /dev/null +++ b/libnetdata/procfile/Makefile.am @@ -0,0 +1,9 @@ +# SPDX-License-Identifier: GPL-3.0-or-later + +AUTOMAKE_OPTIONS = subdir-objects +MAINTAINERCLEANFILES = $(srcdir)/Makefile.in + + +dist_noinst_DATA = \ + README.md \ + $(NULL) diff --git a/libnetdata/procfile/Makefile.in b/libnetdata/procfile/Makefile.in new file mode 100644 index 00000000..643e00ba --- /dev/null +++ b/libnetdata/procfile/Makefile.in @@ -0,0 +1,464 @@ +# Makefile.in generated by automake 1.14.1 from Makefile.am. +# @configure_input@ + +# Copyright (C) 1994-2013 Free Software Foundation, Inc. + +# This Makefile.in is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY, to the extent permitted by law; without +# even the implied warranty of MERCHANTABILITY or FITNESS FOR A +# PARTICULAR PURPOSE. + +@SET_MAKE@ + +# SPDX-License-Identifier: GPL-3.0-or-later + +VPATH = @srcdir@ +am__is_gnu_make = test -n '$(MAKEFILE_LIST)' && test -n '$(MAKELEVEL)' +am__make_running_with_option = \ + case $${target_option-} in \ + ?) ;; \ + *) echo "am__make_running_with_option: internal error: invalid" \ + "target option '$${target_option-}' specified" >&2; \ + exit 1;; \ + esac; \ + has_opt=no; \ + sane_makeflags=$$MAKEFLAGS; \ + if $(am__is_gnu_make); then \ + sane_makeflags=$$MFLAGS; \ + else \ + case $$MAKEFLAGS in \ + *\\[\ \ ]*) \ + bs=\\; \ + sane_makeflags=`printf '%s\n' "$$MAKEFLAGS" \ + | sed "s/$$bs$$bs[$$bs $$bs ]*//g"`;; \ + esac; \ + fi; \ + skip_next=no; \ + strip_trailopt () \ + { \ + flg=`printf '%s\n' "$$flg" | sed "s/$$1.*$$//"`; \ + }; \ + for flg in $$sane_makeflags; do \ + test $$skip_next = yes && { skip_next=no; continue; }; \ + case $$flg in \ + *=*|--*) continue;; \ + -*I) strip_trailopt 'I'; skip_next=yes;; \ + -*I?*) strip_trailopt 'I';; \ + -*O) strip_trailopt 'O'; skip_next=yes;; \ + -*O?*) strip_trailopt 'O';; \ + -*l) strip_trailopt 'l'; skip_next=yes;; \ + -*l?*) strip_trailopt 'l';; \ + -[dEDm]) skip_next=yes;; \ + -[JT]) skip_next=yes;; \ + esac; \ + case $$flg in \ + *$$target_option*) has_opt=yes; break;; \ + esac; \ + done; \ + test $$has_opt = yes +am__make_dryrun = (target_option=n; $(am__make_running_with_option)) +am__make_keepgoing = (target_option=k; $(am__make_running_with_option)) +pkgdatadir = $(datadir)/@PACKAGE@ +pkgincludedir = $(includedir)/@PACKAGE@ +pkglibdir = $(libdir)/@PACKAGE@ +pkglibexecdir = $(libexecdir)/@PACKAGE@ +am__cd = CDPATH="$${ZSH_VERSION+.}$(PATH_SEPARATOR)" && cd +install_sh_DATA = $(install_sh) -c -m 644 +install_sh_PROGRAM = $(install_sh) -c +install_sh_SCRIPT = $(install_sh) -c +INSTALL_HEADER = $(INSTALL_DATA) +transform = $(program_transform_name) +NORMAL_INSTALL = : +PRE_INSTALL = : +POST_INSTALL = : +NORMAL_UNINSTALL = : +PRE_UNINSTALL = : +POST_UNINSTALL = : +build_triplet = @build@ +host_triplet = @host@ +subdir = libnetdata/procfile +DIST_COMMON = $(srcdir)/Makefile.in $(srcdir)/Makefile.am \ + $(dist_noinst_DATA) +ACLOCAL_M4 = $(top_srcdir)/aclocal.m4 +am__aclocal_m4_deps = $(top_srcdir)/build/m4/ax_c___atomic.m4 \ + $(top_srcdir)/build/m4/ax_c__generic.m4 \ + $(top_srcdir)/build/m4/ax_c_lto.m4 \ + $(top_srcdir)/build/m4/ax_c_mallinfo.m4 \ + $(top_srcdir)/build/m4/ax_c_mallopt.m4 \ + $(top_srcdir)/build/m4/ax_check_compile_flag.m4 \ + $(top_srcdir)/build/m4/ax_gcc_func_attribute.m4 \ + $(top_srcdir)/build/m4/ax_pthread.m4 \ + $(top_srcdir)/build/m4/jemalloc.m4 \ + $(top_srcdir)/build/m4/tcmalloc.m4 $(top_srcdir)/configure.ac +am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \ + $(ACLOCAL_M4) +mkinstalldirs = $(install_sh) -d +CONFIG_HEADER = $(top_builddir)/config.h +CONFIG_CLEAN_FILES = +CONFIG_CLEAN_VPATH_FILES = +AM_V_P = $(am__v_P_@AM_V@) +am__v_P_ = $(am__v_P_@AM_DEFAULT_V@) +am__v_P_0 = false +am__v_P_1 = : +AM_V_GEN = $(am__v_GEN_@AM_V@) +am__v_GEN_ = $(am__v_GEN_@AM_DEFAULT_V@) +am__v_GEN_0 = @echo " GEN " $@; +am__v_GEN_1 = +AM_V_at = $(am__v_at_@AM_V@) +am__v_at_ = $(am__v_at_@AM_DEFAULT_V@) +am__v_at_0 = @ +am__v_at_1 = +SOURCES = +DIST_SOURCES = +am__can_run_installinfo = \ + case $$AM_UPDATE_INFO_DIR in \ + n|no|NO) false;; \ + *) (install-info --version) >/dev/null 2>&1;; \ + esac +DATA = $(dist_noinst_DATA) +am__tagged_files = $(HEADERS) $(SOURCES) $(TAGS_FILES) $(LISP) +DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST) +ACLOCAL = @ACLOCAL@ +AMTAR = @AMTAR@ +AM_DEFAULT_VERBOSITY = @AM_DEFAULT_VERBOSITY@ +AUTOCONF = @AUTOCONF@ +AUTOHEADER = @AUTOHEADER@ +AUTOMAKE = @AUTOMAKE@ +AWK = @AWK@ +CC = @CC@ +CCDEPMODE = @CCDEPMODE@ +CFLAGS = @CFLAGS@ +CPP = @CPP@ +CPPFLAGS = @CPPFLAGS@ +CYGPATH_W = @CYGPATH_W@ +DEFS = @DEFS@ +DEPDIR = @DEPDIR@ +ECHO_C = @ECHO_C@ +ECHO_N = @ECHO_N@ +ECHO_T = @ECHO_T@ +EGREP = @EGREP@ +EXEEXT = @EXEEXT@ +GREP = @GREP@ +INSTALL = @INSTALL@ +INSTALL_DATA = @INSTALL_DATA@ +INSTALL_PROGRAM = @INSTALL_PROGRAM@ +INSTALL_SCRIPT = @INSTALL_SCRIPT@ +INSTALL_STRIP_PROGRAM = @INSTALL_STRIP_PROGRAM@ +IPMIMONITORING_CFLAGS = @IPMIMONITORING_CFLAGS@ +IPMIMONITORING_LIBS = @IPMIMONITORING_LIBS@ +LDFLAGS = @LDFLAGS@ +LIBCAP_CFLAGS = @LIBCAP_CFLAGS@ +LIBCAP_LIBS = @LIBCAP_LIBS@ +LIBMNL_CFLAGS = @LIBMNL_CFLAGS@ +LIBMNL_LIBS = @LIBMNL_LIBS@ +LIBOBJS = @LIBOBJS@ +LIBS = @LIBS@ +LTLIBOBJS = @LTLIBOBJS@ +MAINT = @MAINT@ +MAKEINFO = @MAKEINFO@ +MATH_CFLAGS = @MATH_CFLAGS@ +MATH_LIBS = @MATH_LIBS@ +MKDIR_P = @MKDIR_P@ +NFACCT_CFLAGS = @NFACCT_CFLAGS@ +NFACCT_LIBS = @NFACCT_LIBS@ +OBJEXT = @OBJEXT@ +OPTIONAL_IPMIMONITORING_CFLAGS = @OPTIONAL_IPMIMONITORING_CFLAGS@ +OPTIONAL_IPMIMONITORING_LIBS = @OPTIONAL_IPMIMONITORING_LIBS@ +OPTIONAL_LIBCAP_CFLAGS = @OPTIONAL_LIBCAP_CFLAGS@ +OPTIONAL_LIBCAP_LIBS = @OPTIONAL_LIBCAP_LIBS@ +OPTIONAL_MATH_CLFAGS = @OPTIONAL_MATH_CLFAGS@ +OPTIONAL_MATH_LIBS = @OPTIONAL_MATH_LIBS@ +OPTIONAL_NFACCT_CLFAGS = @OPTIONAL_NFACCT_CLFAGS@ +OPTIONAL_NFACCT_LIBS = @OPTIONAL_NFACCT_LIBS@ +OPTIONAL_UUID_CLFAGS = @OPTIONAL_UUID_CLFAGS@ +OPTIONAL_UUID_LIBS = @OPTIONAL_UUID_LIBS@ +OPTIONAL_ZLIB_CLFAGS = @OPTIONAL_ZLIB_CLFAGS@ +OPTIONAL_ZLIB_LIBS = @OPTIONAL_ZLIB_LIBS@ +PACKAGE = @PACKAGE@ +PACKAGE_BUGREPORT = @PACKAGE_BUGREPORT@ +PACKAGE_NAME = @PACKAGE_NAME@ +PACKAGE_RPM_RELEASE = @PACKAGE_RPM_RELEASE@ +PACKAGE_RPM_VERSION = @PACKAGE_RPM_VERSION@ +PACKAGE_STRING = @PACKAGE_STRING@ +PACKAGE_TARNAME = @PACKAGE_TARNAME@ +PACKAGE_URL = @PACKAGE_URL@ +PACKAGE_VERSION = @PACKAGE_VERSION@ +PATH_SEPARATOR = @PATH_SEPARATOR@ +PKG_CONFIG = @PKG_CONFIG@ +PKG_CONFIG_LIBDIR = @PKG_CONFIG_LIBDIR@ +PKG_CONFIG_PATH = @PKG_CONFIG_PATH@ +PTHREAD_CC = @PTHREAD_CC@ +PTHREAD_CFLAGS = @PTHREAD_CFLAGS@ +PTHREAD_LIBS = @PTHREAD_LIBS@ +SET_MAKE = @SET_MAKE@ +SHELL = @SHELL@ +SSE_CANDIDATE = @SSE_CANDIDATE@ +STRIP = @STRIP@ +UUID_CFLAGS = @UUID_CFLAGS@ +UUID_LIBS = @UUID_LIBS@ +VERSION = @VERSION@ +ZLIB_CFLAGS = @ZLIB_CFLAGS@ +ZLIB_LIBS = @ZLIB_LIBS@ +abs_builddir = @abs_builddir@ +abs_srcdir = @abs_srcdir@ +abs_top_builddir = @abs_top_builddir@ +abs_top_srcdir = @abs_top_srcdir@ +ac_ct_CC = @ac_ct_CC@ +am__include = @am__include@ +am__leading_dot = @am__leading_dot@ +am__quote = @am__quote@ +am__tar = @am__tar@ +am__untar = @am__untar@ +ax_pthread_config = @ax_pthread_config@ +bindir = @bindir@ +build = @build@ +build_alias = @build_alias@ +build_cpu = @build_cpu@ +build_os = @build_os@ +build_target = @build_target@ +build_vendor = @build_vendor@ +builddir = @builddir@ +cachedir = @cachedir@ +chartsdir = @chartsdir@ +configdir = @configdir@ +datadir = @datadir@ +datarootdir = @datarootdir@ +docdir = @docdir@ +dvidir = @dvidir@ +exec_prefix = @exec_prefix@ +has_jemalloc = @has_jemalloc@ +has_tcmalloc = @has_tcmalloc@ +host = @host@ +host_alias = @host_alias@ +host_cpu = @host_cpu@ +host_os = @host_os@ +host_vendor = @host_vendor@ +htmldir = @htmldir@ +includedir = @includedir@ +infodir = @infodir@ +install_sh = @install_sh@ +libconfigdir = @libconfigdir@ +libdir = @libdir@ +libexecdir = @libexecdir@ +localedir = @localedir@ +localstatedir = @localstatedir@ +logdir = @logdir@ +mandir = @mandir@ +mkdir_p = @mkdir_p@ +nodedir = @nodedir@ +oldincludedir = @oldincludedir@ +pdfdir = @pdfdir@ +pluginsdir = @pluginsdir@ +prefix = @prefix@ +program_transform_name = @program_transform_name@ +psdir = @psdir@ +pythondir = @pythondir@ +registrydir = @registrydir@ +sbindir = @sbindir@ +sharedstatedir = @sharedstatedir@ +srcdir = @srcdir@ +sysconfdir = @sysconfdir@ +target_alias = @target_alias@ +top_build_prefix = @top_build_prefix@ +top_builddir = @top_builddir@ +top_srcdir = @top_srcdir@ +varlibdir = @varlibdir@ +webdir = @webdir@ +AUTOMAKE_OPTIONS = subdir-objects +MAINTAINERCLEANFILES = $(srcdir)/Makefile.in +dist_noinst_DATA = \ + README.md \ + $(NULL) + +all: all-am + +.SUFFIXES: +$(srcdir)/Makefile.in: @MAINTAINER_MODE_TRUE@ $(srcdir)/Makefile.am $(am__configure_deps) + @for dep in $?; do \ + case '$(am__configure_deps)' in \ + *$$dep*) \ + ( cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh ) \ + && { if test -f $@; then exit 0; else break; fi; }; \ + exit 1;; \ + esac; \ + done; \ + echo ' cd $(top_srcdir) && $(AUTOMAKE) --gnu libnetdata/procfile/Makefile'; \ + $(am__cd) $(top_srcdir) && \ + $(AUTOMAKE) --gnu libnetdata/procfile/Makefile +.PRECIOUS: Makefile +Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status + @case '$?' in \ + *config.status*) \ + cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh;; \ + *) \ + echo ' cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe)'; \ + cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe);; \ + esac; + +$(top_builddir)/config.status: $(top_srcdir)/configure $(CONFIG_STATUS_DEPENDENCIES) + cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh + +$(top_srcdir)/configure: @MAINTAINER_MODE_TRUE@ $(am__configure_deps) + cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh +$(ACLOCAL_M4): @MAINTAINER_MODE_TRUE@ $(am__aclocal_m4_deps) + cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh +$(am__aclocal_m4_deps): +tags TAGS: + +ctags CTAGS: + +cscope cscopelist: + + +distdir: $(DISTFILES) + @srcdirstrip=`echo "$(srcdir)" | sed 's/[].[^$$\\*]/\\\\&/g'`; \ + topsrcdirstrip=`echo "$(top_srcdir)" | sed 's/[].[^$$\\*]/\\\\&/g'`; \ + list='$(DISTFILES)'; \ + dist_files=`for file in $$list; do echo $$file; done | \ + sed -e "s|^$$srcdirstrip/||;t" \ + -e "s|^$$topsrcdirstrip/|$(top_builddir)/|;t"`; \ + case $$dist_files in \ + */*) $(MKDIR_P) `echo "$$dist_files" | \ + sed '/\//!d;s|^|$(distdir)/|;s,/[^/]*$$,,' | \ + sort -u` ;; \ + esac; \ + for file in $$dist_files; do \ + if test -f $$file || test -d $$file; then d=.; else d=$(srcdir); fi; \ + if test -d $$d/$$file; then \ + dir=`echo "/$$file" | sed -e 's,/[^/]*$$,,'`; \ + if test -d "$(distdir)/$$file"; then \ + find "$(distdir)/$$file" -type d ! -perm -700 -exec chmod u+rwx {} \;; \ + fi; \ + if test -d $(srcdir)/$$file && test $$d != $(srcdir); then \ + cp -fpR $(srcdir)/$$file "$(distdir)$$dir" || exit 1; \ + find "$(distdir)/$$file" -type d ! -perm -700 -exec chmod u+rwx {} \;; \ + fi; \ + cp -fpR $$d/$$file "$(distdir)$$dir" || exit 1; \ + else \ + test -f "$(distdir)/$$file" \ + || cp -p $$d/$$file "$(distdir)/$$file" \ + || exit 1; \ + fi; \ + done +check-am: all-am +check: check-am +all-am: Makefile $(DATA) +installdirs: +install: install-am +install-exec: install-exec-am +install-data: install-data-am +uninstall: uninstall-am + +install-am: all-am + @$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am + +installcheck: installcheck-am +install-strip: + if test -z '$(STRIP)'; then \ + $(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \ + install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \ + install; \ + else \ + $(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \ + install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \ + "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'" install; \ + fi +mostlyclean-generic: + +clean-generic: + +distclean-generic: + -test -z "$(CONFIG_CLEAN_FILES)" || rm -f $(CONFIG_CLEAN_FILES) + -test . = "$(srcdir)" || test -z "$(CONFIG_CLEAN_VPATH_FILES)" || rm -f $(CONFIG_CLEAN_VPATH_FILES) + +maintainer-clean-generic: + @echo "This command is intended for maintainers to use" + @echo "it deletes files that may require special tools to rebuild." + -test -z "$(MAINTAINERCLEANFILES)" || rm -f $(MAINTAINERCLEANFILES) +clean: clean-am + +clean-am: clean-generic mostlyclean-am + +distclean: distclean-am + -rm -f Makefile +distclean-am: clean-am distclean-generic + +dvi: dvi-am + +dvi-am: + +html: html-am + +html-am: + +info: info-am + +info-am: + +install-data-am: + +install-dvi: install-dvi-am + +install-dvi-am: + +install-exec-am: + +install-html: install-html-am + +install-html-am: + +install-info: install-info-am + +install-info-am: + +install-man: + +install-pdf: install-pdf-am + +install-pdf-am: + +install-ps: install-ps-am + +install-ps-am: + +installcheck-am: + +maintainer-clean: maintainer-clean-am + -rm -f Makefile +maintainer-clean-am: distclean-am maintainer-clean-generic + +mostlyclean: mostlyclean-am + +mostlyclean-am: mostlyclean-generic + +pdf: pdf-am + +pdf-am: + +ps: ps-am + +ps-am: + +uninstall-am: + +.MAKE: install-am install-strip + +.PHONY: all all-am check check-am clean clean-generic cscopelist-am \ + ctags-am distclean distclean-generic distdir dvi dvi-am html \ + html-am info info-am install install-am install-data \ + install-data-am install-dvi install-dvi-am install-exec \ + install-exec-am install-html install-html-am install-info \ + install-info-am install-man install-pdf install-pdf-am \ + install-ps install-ps-am install-strip installcheck \ + installcheck-am installdirs maintainer-clean \ + maintainer-clean-generic mostlyclean mostlyclean-generic pdf \ + pdf-am ps ps-am tags-am uninstall uninstall-am + + +# Tell versions [3.59,3.63) of GNU make to not export all variables. +# Otherwise a system limit (for SysV at least) may be exceeded. +.NOEXPORT: diff --git a/libnetdata/procfile/README.md b/libnetdata/procfile/README.md new file mode 100644 index 00000000..279885f9 --- /dev/null +++ b/libnetdata/procfile/README.md @@ -0,0 +1,61 @@ + +# PROCFILE + +procfile is a library for reading text data files (i.e `/proc` files) in the fastest possible way. + +## How it works + +The library automatically adapts (through the iterations) its memory so that each file +is read with single `read()` call. + +Then the library splits the file into words, using the supplied separators. +The library also supported quoted words (i.e. strings within of which the separators are ignored). + +### Initialization + +Initially the caller: + +- calls `procfile_open()` to open the file and allocate the structures needed. + +### Iterations + +For each iteration, the caller: + +- calls `procfile_readall()` to read updated contents. + This call also rewinds (`lseek()` to 0) before reading it. + + For every file, a [BUFFER](../buffer/) is used that is automatically adjusted to fit + the entire file contents of the file. So the file is read with a single `read()` call + (providing atomicity / consistency when the data are read from the kernel). + + Once the data are read, 2 arrays of pointers are updated: + + - a `words` array, pointing to each word in the data read + - a `lines` array, pointing to the first word for each line + + This is highly optimized. Both arrays are automatically adjusted to + fit all contents and are updated in a single pass on the data. + + The library provides a number of macros: + + - `procfile_lines()` returns the # of lines read + - `procfile_linewords()` returns the # of words in the given line + - `procfile_word()` returns a pointer the given word # + - `procfile_line()` returns a pointer to the first word of the given line # + - `procfile_lineword()` returns a pointer to the given word # of the given line # + +### Cleanup + +When the caller exits: + +- calls `procfile_free()` to close the file and free all memory used. + +### Performance + +- a **raspberry Pi 1** (the oldest single core one) can process 5.000+ `/proc` files per second. +- a **J1900 Celeron** processor can process 23.000+ `/proc` files per second per core. + +To achieve this kind of performance, the library tries to work in batches so that the code +and the data are inside the processor's caches. + +This library is extensively used in netdata and its plugins. diff --git a/libnetdata/procfile/procfile.c b/libnetdata/procfile/procfile.c new file mode 100644 index 00000000..4a812baa --- /dev/null +++ b/libnetdata/procfile/procfile.c @@ -0,0 +1,472 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "../libnetdata.h" + +#define PF_PREFIX "PROCFILE" + +#define PFWORDS_INCREASE_STEP 200 +#define PFLINES_INCREASE_STEP 10 +#define PROCFILE_INCREMENT_BUFFER 512 + +int procfile_open_flags = O_RDONLY; + +int procfile_adaptive_initial_allocation = 0; + +// if adaptive allocation is set, these store the +// max values we have seen so far +size_t procfile_max_lines = PFLINES_INCREASE_STEP; +size_t procfile_max_words = PFWORDS_INCREASE_STEP; +size_t procfile_max_allocation = PROCFILE_INCREMENT_BUFFER; + + +// ---------------------------------------------------------------------------- + +char *procfile_filename(procfile *ff) { + if(ff->filename[0]) return ff->filename; + + char buffer[FILENAME_MAX + 1]; + snprintfz(buffer, FILENAME_MAX, "/proc/self/fd/%d", ff->fd); + + ssize_t l = readlink(buffer, ff->filename, FILENAME_MAX); + if(unlikely(l == -1)) + snprintfz(ff->filename, FILENAME_MAX, "unknown filename for fd %d", ff->fd); + else + ff->filename[l] = '\0'; + + // on non-linux systems, something like this will be needed + // fcntl(ff->fd, F_GETPATH, ff->filename) + + return ff->filename; +} + +// ---------------------------------------------------------------------------- +// An array of words + +static inline void pfwords_add(procfile *ff, char *str) { + // debug(D_PROCFILE, PF_PREFIX ": adding word No %d: '%s'", fw->len, str); + + pfwords *fw = ff->words; + if(unlikely(fw->len == fw->size)) { + // debug(D_PROCFILE, PF_PREFIX ": expanding words"); + + ff->words = fw = reallocz(fw, sizeof(pfwords) + (fw->size + PFWORDS_INCREASE_STEP) * sizeof(char *)); + fw->size += PFWORDS_INCREASE_STEP; + } + + fw->words[fw->len++] = str; +} + +NEVERNULL +static inline pfwords *pfwords_new(void) { + // debug(D_PROCFILE, PF_PREFIX ": initializing words"); + + size_t size = (procfile_adaptive_initial_allocation) ? procfile_max_words : PFWORDS_INCREASE_STEP; + + pfwords *new = mallocz(sizeof(pfwords) + size * sizeof(char *)); + new->len = 0; + new->size = size; + return new; +} + +static inline void pfwords_reset(pfwords *fw) { + // debug(D_PROCFILE, PF_PREFIX ": reseting words"); + fw->len = 0; +} + +static inline void pfwords_free(pfwords *fw) { + // debug(D_PROCFILE, PF_PREFIX ": freeing words"); + + freez(fw); +} + + +// ---------------------------------------------------------------------------- +// An array of lines + +NEVERNULL +static inline size_t *pflines_add(procfile *ff) { + // debug(D_PROCFILE, PF_PREFIX ": adding line %d at word %d", fl->len, first_word); + + pflines *fl = ff->lines; + if(unlikely(fl->len == fl->size)) { + // debug(D_PROCFILE, PF_PREFIX ": expanding lines"); + + ff->lines = fl = reallocz(fl, sizeof(pflines) + (fl->size + PFLINES_INCREASE_STEP) * sizeof(ffline)); + fl->size += PFLINES_INCREASE_STEP; + } + + ffline *ffl = &fl->lines[fl->len++]; + ffl->words = 0; + ffl->first = ff->words->len; + + return &ffl->words; +} + +NEVERNULL +static inline pflines *pflines_new(void) { + // debug(D_PROCFILE, PF_PREFIX ": initializing lines"); + + size_t size = (unlikely(procfile_adaptive_initial_allocation)) ? procfile_max_words : PFLINES_INCREASE_STEP; + + pflines *new = mallocz(sizeof(pflines) + size * sizeof(ffline)); + new->len = 0; + new->size = size; + return new; +} + +static inline void pflines_reset(pflines *fl) { + // debug(D_PROCFILE, PF_PREFIX ": reseting lines"); + + fl->len = 0; +} + +static inline void pflines_free(pflines *fl) { + // debug(D_PROCFILE, PF_PREFIX ": freeing lines"); + + freez(fl); +} + + +// ---------------------------------------------------------------------------- +// The procfile + +void procfile_close(procfile *ff) { + if(unlikely(!ff)) return; + + debug(D_PROCFILE, PF_PREFIX ": Closing file '%s'", procfile_filename(ff)); + + if(likely(ff->lines)) pflines_free(ff->lines); + if(likely(ff->words)) pfwords_free(ff->words); + + if(likely(ff->fd != -1)) close(ff->fd); + freez(ff); +} + +NOINLINE +static void procfile_parser(procfile *ff) { + // debug(D_PROCFILE, PF_PREFIX ": Parsing file '%s'", ff->filename); + + char *s = ff->data // our current position + , *e = &ff->data[ff->len] // the terminating null + , *t = ff->data; // the first character of a word (or quoted / parenthesized string) + + // the look up array to find our type of character + PF_CHAR_TYPE *separators = ff->separators; + + char quote = 0; // the quote character - only when in quoted string + size_t opened = 0; // counts the number of open parenthesis + + size_t *line_words = pflines_add(ff); + + while(s < e) { + PF_CHAR_TYPE ct = separators[(unsigned char)(*s)]; + + // this is faster than a switch() + // read more here: http://lazarenko.me/switch/ + if(likely(ct == PF_CHAR_IS_WORD)) { + s++; + } + else if(likely(ct == PF_CHAR_IS_SEPARATOR)) { + if(!quote && !opened) { + if (s != t) { + // separator, but we have word before it + *s = '\0'; + pfwords_add(ff, t); + (*line_words)++; + t = ++s; + } + else { + // separator at the beginning + // skip it + t = ++s; + } + } + else { + // we are inside a quote or parenthesized string + s++; + } + } + else if(likely(ct == PF_CHAR_IS_NEWLINE)) { + // end of line + + *s = '\0'; + pfwords_add(ff, t); + (*line_words)++; + t = ++s; + + // debug(D_PROCFILE, PF_PREFIX ": ended line %d with %d words", l, ff->lines->lines[l].words); + + line_words = pflines_add(ff); + } + else if(likely(ct == PF_CHAR_IS_QUOTE)) { + if(unlikely(!quote && s == t)) { + // quote opened at the beginning + quote = *s; + t = ++s; + } + else if(unlikely(quote && quote == *s)) { + // quote closed + quote = 0; + + *s = '\0'; + pfwords_add(ff, t); + (*line_words)++; + t = ++s; + } + else + s++; + } + else if(likely(ct == PF_CHAR_IS_OPEN)) { + if(s == t) { + opened++; + t = ++s; + } + else if(opened) { + opened++; + s++; + } + else + s++; + } + else if(likely(ct == PF_CHAR_IS_CLOSE)) { + if(opened) { + opened--; + + if(!opened) { + *s = '\0'; + pfwords_add(ff, t); + (*line_words)++; + t = ++s; + } + else + s++; + } + else + s++; + } + else + fatal("Internal Error: procfile_readall() does not handle all the cases."); + } + + if(likely(s > t && t < e)) { + // the last word + if(unlikely(ff->len >= ff->size)) { + // we are going to loose the last byte + s = &ff->data[ff->size - 1]; + } + + *s = '\0'; + pfwords_add(ff, t); + (*line_words)++; + // t = ++s; + } +} + +procfile *procfile_readall(procfile *ff) { + // debug(D_PROCFILE, PF_PREFIX ": Reading file '%s'.", ff->filename); + + ff->len = 0; // zero the used size + ssize_t r = 1; // read at least once + while(r > 0) { + ssize_t s = ff->len; + ssize_t x = ff->size - s; + + if(unlikely(!x)) { + debug(D_PROCFILE, PF_PREFIX ": Expanding data buffer for file '%s'.", procfile_filename(ff)); + ff = reallocz(ff, sizeof(procfile) + ff->size + PROCFILE_INCREMENT_BUFFER); + ff->size += PROCFILE_INCREMENT_BUFFER; + } + + debug(D_PROCFILE, "Reading file '%s', from position %zd with length %zd", procfile_filename(ff), s, (ssize_t)(ff->size - s)); + r = read(ff->fd, &ff->data[s], ff->size - s); + if(unlikely(r == -1)) { + if(unlikely(!(ff->flags & PROCFILE_FLAG_NO_ERROR_ON_FILE_IO))) error(PF_PREFIX ": Cannot read from file '%s' on fd %d", procfile_filename(ff), ff->fd); + procfile_close(ff); + return NULL; + } + + ff->len += r; + } + + // debug(D_PROCFILE, "Rewinding file '%s'", ff->filename); + if(unlikely(lseek(ff->fd, 0, SEEK_SET) == -1)) { + if(unlikely(!(ff->flags & PROCFILE_FLAG_NO_ERROR_ON_FILE_IO))) error(PF_PREFIX ": Cannot rewind on file '%s'.", procfile_filename(ff)); + procfile_close(ff); + return NULL; + } + + pflines_reset(ff->lines); + pfwords_reset(ff->words); + procfile_parser(ff); + + if(unlikely(procfile_adaptive_initial_allocation)) { + if(unlikely(ff->len > procfile_max_allocation)) procfile_max_allocation = ff->len; + if(unlikely(ff->lines->len > procfile_max_lines)) procfile_max_lines = ff->lines->len; + if(unlikely(ff->words->len > procfile_max_words)) procfile_max_words = ff->words->len; + } + + // debug(D_PROCFILE, "File '%s' updated.", ff->filename); + return ff; +} + +NOINLINE +static void procfile_set_separators(procfile *ff, const char *separators) { + static PF_CHAR_TYPE def[256]; + static char initilized = 0; + + if(unlikely(!initilized)) { + // this is thread safe + // if initialized is zero, multiple threads may be executing + // this code at the same time, setting in def[] the exact same values + int i = 256; + while(i--) { + if(unlikely(i == '\n' || i == '\r')) + def[i] = PF_CHAR_IS_NEWLINE; + + else if(unlikely(isspace(i) || !isprint(i))) + def[i] = PF_CHAR_IS_SEPARATOR; + + else + def[i] = PF_CHAR_IS_WORD; + } + + initilized = 1; + } + + // copy the default + PF_CHAR_TYPE *ffs = ff->separators, *ffd = def, *ffe = &def[256]; + while(ffd != ffe) + *ffs++ = *ffd++; + + // set the separators + if(unlikely(!separators)) + separators = " \t=|"; + + ffs = ff->separators; + const char *s = separators; + while(*s) + ffs[(int)*s++] = PF_CHAR_IS_SEPARATOR; +} + +void procfile_set_quotes(procfile *ff, const char *quotes) { + PF_CHAR_TYPE *ffs = ff->separators; + + // remove all quotes + int i = 256; + while(i--) + if(unlikely(ffs[i] == PF_CHAR_IS_QUOTE)) + ffs[i] = PF_CHAR_IS_WORD; + + // if nothing given, return + if(unlikely(!quotes || !*quotes)) + return; + + // set the quotes + const char *s = quotes; + while(*s) + ffs[(int)*s++] = PF_CHAR_IS_QUOTE; +} + +void procfile_set_open_close(procfile *ff, const char *open, const char *close) { + PF_CHAR_TYPE *ffs = ff->separators; + + // remove all open/close + int i = 256; + while(i--) + if(unlikely(ffs[i] == PF_CHAR_IS_OPEN || ffs[i] == PF_CHAR_IS_CLOSE)) + ffs[i] = PF_CHAR_IS_WORD; + + // if nothing given, return + if(unlikely(!open || !*open || !close || !*close)) + return; + + // set the openings + const char *s = open; + while(*s) + ffs[(int)*s++] = PF_CHAR_IS_OPEN; + + // set the closings + s = close; + while(*s) + ffs[(int)*s++] = PF_CHAR_IS_CLOSE; +} + +procfile *procfile_open(const char *filename, const char *separators, uint32_t flags) { + debug(D_PROCFILE, PF_PREFIX ": Opening file '%s'", filename); + + int fd = open(filename, procfile_open_flags, 0666); + if(unlikely(fd == -1)) { + if(unlikely(!(flags & PROCFILE_FLAG_NO_ERROR_ON_FILE_IO))) error(PF_PREFIX ": Cannot open file '%s'", filename); + return NULL; + } + + // info("PROCFILE: opened '%s' on fd %d", filename, fd); + + size_t size = (unlikely(procfile_adaptive_initial_allocation)) ? procfile_max_allocation : PROCFILE_INCREMENT_BUFFER; + procfile *ff = mallocz(sizeof(procfile) + size); + + //strncpyz(ff->filename, filename, FILENAME_MAX); + ff->filename[0] = '\0'; + + ff->fd = fd; + ff->size = size; + ff->len = 0; + ff->flags = flags; + + ff->lines = pflines_new(); + ff->words = pfwords_new(); + + procfile_set_separators(ff, separators); + + debug(D_PROCFILE, "File '%s' opened.", filename); + return ff; +} + +procfile *procfile_reopen(procfile *ff, const char *filename, const char *separators, uint32_t flags) { + if(unlikely(!ff)) return procfile_open(filename, separators, flags); + + if(likely(ff->fd != -1)) { + // info("PROCFILE: closing fd %d", ff->fd); + close(ff->fd); + } + + ff->fd = open(filename, procfile_open_flags, 0666); + if(unlikely(ff->fd == -1)) { + procfile_close(ff); + return NULL; + } + + // info("PROCFILE: opened '%s' on fd %d", filename, ff->fd); + + //strncpyz(ff->filename, filename, FILENAME_MAX); + ff->filename[0] = '\0'; + ff->flags = flags; + + // do not do the separators again if NULL is given + if(likely(separators)) procfile_set_separators(ff, separators); + + return ff; +} + +// ---------------------------------------------------------------------------- +// example parsing of procfile data + +void procfile_print(procfile *ff) { + size_t lines = procfile_lines(ff), l; + char *s; + (void)s; + + debug(D_PROCFILE, "File '%s' with %zu lines and %zu words", procfile_filename(ff), ff->lines->len, ff->words->len); + + for(l = 0; likely(l < lines) ;l++) { + size_t words = procfile_linewords(ff, l); + + debug(D_PROCFILE, " line %zu starts at word %zu and has %zu words", l, ff->lines->lines[l].first, ff->lines->lines[l].words); + + size_t w; + for(w = 0; likely(w < words) ;w++) { + s = procfile_lineword(ff, l, w); + debug(D_PROCFILE, " [%zu.%zu] '%s'", l, w, s); + } + } +} diff --git a/libnetdata/procfile/procfile.h b/libnetdata/procfile/procfile.h new file mode 100644 index 00000000..b107358a --- /dev/null +++ b/libnetdata/procfile/procfile.h @@ -0,0 +1,106 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#ifndef NETDATA_PROCFILE_H +#define NETDATA_PROCFILE_H 1 + +#include "../libnetdata.h" + +// ---------------------------------------------------------------------------- +// An array of words + +typedef struct { + size_t len; // used entries + size_t size; // capacity + char *words[]; // array of pointers +} pfwords; + + +// ---------------------------------------------------------------------------- +// An array of lines + +typedef struct { + size_t words; // how many words this line has + size_t first; // the id of the first word of this line + // in the words array +} ffline; + +typedef struct { + size_t len; // used entries + size_t size; // capacity + ffline lines[]; // array of lines +} pflines; + + +// ---------------------------------------------------------------------------- +// The procfile + +#define PROCFILE_FLAG_DEFAULT 0x00000000 +#define PROCFILE_FLAG_NO_ERROR_ON_FILE_IO 0x00000001 + +typedef enum procfile_separator { + PF_CHAR_IS_SEPARATOR, + PF_CHAR_IS_NEWLINE, + PF_CHAR_IS_WORD, + PF_CHAR_IS_QUOTE, + PF_CHAR_IS_OPEN, + PF_CHAR_IS_CLOSE +} PF_CHAR_TYPE; + +typedef struct { + char filename[FILENAME_MAX + 1]; // not populated until profile_filename() is called + + uint32_t flags; + int fd; // the file desriptor + size_t len; // the bytes we have placed into data + size_t size; // the bytes we have allocated for data + pflines *lines; + pfwords *words; + PF_CHAR_TYPE separators[256]; + char data[]; // allocated buffer to keep file contents +} procfile; + +// close the proc file and free all related memory +extern void procfile_close(procfile *ff); + +// (re)read and parse the proc file +extern procfile *procfile_readall(procfile *ff); + +// open a /proc or /sys file +extern procfile *procfile_open(const char *filename, const char *separators, uint32_t flags); + +// re-open a file +// if separators == NULL, the last separators are used +extern procfile *procfile_reopen(procfile *ff, const char *filename, const char *separators, uint32_t flags); + +// example walk-through a procfile parsed file +extern void procfile_print(procfile *ff); + +extern void procfile_set_quotes(procfile *ff, const char *quotes); +extern void procfile_set_open_close(procfile *ff, const char *open, const char *close); + +extern char *procfile_filename(procfile *ff); + +// ---------------------------------------------------------------------------- + +// set to the O_XXXX flags, to have procfile_open and procfile_reopen use them when opening proc files +extern int procfile_open_flags; + +// set this to 1, to have procfile adapt its initial buffer allocation to the max allocation used so far +extern int procfile_adaptive_initial_allocation; + +// return the number of lines present +#define procfile_lines(ff) ((ff)->lines->len) + +// return the number of words of the Nth line +#define procfile_linewords(ff, line) (((line) < procfile_lines(ff)) ? (ff)->lines->lines[(line)].words : 0) + +// return the Nth word of the file, or empty string +#define procfile_word(ff, word) (((word) < (ff)->words->len) ? (ff)->words->words[(word)] : "") + +// return the first word of the Nth line, or empty string +#define procfile_line(ff, line) (((line) < procfile_lines(ff)) ? procfile_word((ff), (ff)->lines->lines[(line)].first) : "") + +// return the Nth word of the current line +#define procfile_lineword(ff, line, word) (((line) < procfile_lines(ff) && (word) < procfile_linewords((ff), (line))) ? procfile_word((ff), (ff)->lines->lines[(line)].first + (word)) : "") + +#endif /* NETDATA_PROCFILE_H */ |