From 04f8a1483362212f33f97c13472ded4121a18a86 Mon Sep 17 00:00:00 2001 From: Jade Lovelace Date: Fri, 23 Aug 2024 16:33:48 -0700 Subject: tree-wide: shuffle headers around for about 30s compile time This didn't really feel so worth it afterwards, but I did untangle a bunch of stuff that should not have been tangled. The general gist of this change is that variant bullshit was causing a bunch of compile time, and it seems like the only way to deal with variant induced compile time is to keep variant types out of headers. Explicit template instantiation seems to do nothing for them. I also seem to have gotten some back-end time improvement from explicitly instantiating regex, but I don't know why. There is no corresponding front-end time improvement from it: regex is still at the top of the sinners list. **** Templates that took longest to instantiate: 15231 ms: std::basic_regex::_M_compile (28 times, avg 543 ms) 15066 ms: std::__detail::_Compiler>::_Compiler (28 times, avg 538 ms) 12571 ms: std::__detail::_Compiler>::_M_disjunction (28 times, avg 448 ms) 12454 ms: std::__detail::_Compiler>::_M_alternative (28 times, avg 444 ms) 12225 ms: std::__detail::_Compiler>::_M_term (28 times, avg 436 ms) 11363 ms: nlohmann::basic_json<>::parse (21 times, avg 541 ms) 10628 ms: nlohmann::basic_json<>::basic_json (109 times, avg 97 ms) 10134 ms: std::__detail::_Compiler>::_M_atom (28 times, avg 361 ms) Back-end time before messing with the regex: **** Function sets that took longest to compile / optimize: 8076 ms: void boost::io::detail::put<$>(boost::io::detail::put_holder<$> cons... (177 times, avg 45 ms) 4382 ms: std::_Rb_tree<$>::_M_erase(std::_Rb_tree_node<$>*) (1247 times, avg 3 ms) 3137 ms: boost::stacktrace::detail::to_string_impl_base(std::__cxx11::basic_string<$>&, ch... (177 times, avg 16 ms) 2304 ms: std::_Rb_tree<$>::_M_get_insert_hint_unique_pos(std::_Rb_tree_const_... (210 times, avg 10 ms) 2116 ms: bool std::__detail::_Compiler<$>::_M_expression_term<$>(std::__detai... (112 times, avg 18 ms) 2051 ms: std::_Rb_tree_iterator<$> std::_Rb_tree<$>::_M_emplace_hint_unique<$... (244 times, avg 8 ms) 2037 ms: toml::result<$> toml::detail::sequence<$>::invoke<$>(toml::detail::l... (93 times, avg 21 ms) 1928 ms: std::__detail::_Compiler<$>::_M_quantifier() (28 times, avg 68 ms) 1859 ms: nlohmann::json_abi_v3_11_3::detail::serializer<$>::dump(nlohmann::js... (41 times, avg 45 ms) 1824 ms: std::_Function_handler<$>::_M_manager(std::_Any_data&, std::_Any_dat... (973 times, avg 1 ms) 1810 ms: std::__detail::_BracketMatcher<$>::_BracketMatcher(std::__detail::_B... (112 times, avg 16 ms) 1793 ms: nix::fetchers::GitInputScheme::fetch(nix::ref<$>, nix::fetchers::Inp... (1 times, avg 1793 ms) 1759 ms: std::_Rb_tree<$>::_M_get_insert_unique_pos(std::__cxx11::basic_strin... (281 times, avg 6 ms) 1722 ms: bool nlohmann::json_abi_v3_11_3::detail::parser<$>::sax_parse_intern... (19 times, avg 90 ms) 1677 ms: boost::io::basic_altstringbuf<$>::overflow(int) (194 times, avg 8 ms) 1674 ms: std::__cxx11::basic_string<$>::_M_mutate(unsigned long, unsigned lon... (249 times, avg 6 ms) 1660 ms: std::_Rb_tree_node<$>* std::_Rb_tree<$>::_M_copy<$>(std::_Rb_tree_no... (304 times, avg 5 ms) 1599 ms: bool nlohmann::json_abi_v3_11_3::detail::parser<$>::sax_parse_intern... (19 times, avg 84 ms) 1568 ms: void std::__detail::_Compiler<$>::_M_insert_bracket_matcher<$>(bool) (112 times, avg 14 ms) 1541 ms: std::__shared_ptr<$>::~__shared_ptr() (531 times, avg 2 ms) 1539 ms: nlohmann::json_abi_v3_11_3::detail::serializer<$>::dump_escaped(std:... (41 times, avg 37 ms) 1471 ms: void std::__detail::_Compiler<$>::_M_insert_character_class_matcher<... (112 times, avg 13 ms) After messing with the regex (notice std::__detail::_Compiler vanishes here, but I don't know why): **** Function sets that took longest to compile / optimize: 8054 ms: void boost::io::detail::put<$>(boost::io::detail::put_holder<$> cons... (177 times, avg 45 ms) 4313 ms: std::_Rb_tree<$>::_M_erase(std::_Rb_tree_node<$>*) (1217 times, avg 3 ms) 3259 ms: boost::stacktrace::detail::to_string_impl_base(std::__cxx11::basic_string<$>&, ch... (177 times, avg 17 ms) 2314 ms: std::_Rb_tree<$>::_M_get_insert_hint_unique_pos(std::_Rb_tree_const_... (207 times, avg 11 ms) 1923 ms: std::_Rb_tree_iterator<$> std::_Rb_tree<$>::_M_emplace_hint_unique<$... (216 times, avg 8 ms) 1817 ms: bool nlohmann::json_abi_v3_11_3::detail::parser<$>::sax_parse_intern... (18 times, avg 100 ms) 1816 ms: toml::result<$> toml::detail::sequence<$>::invoke<$>(toml::detail::l... (93 times, avg 19 ms) 1788 ms: nlohmann::json_abi_v3_11_3::detail::serializer<$>::dump(nlohmann::js... (40 times, avg 44 ms) 1749 ms: std::_Rb_tree<$>::_M_get_insert_unique_pos(std::__cxx11::basic_strin... (278 times, avg 6 ms) 1724 ms: std::__cxx11::basic_string<$>::_M_mutate(unsigned long, unsigned lon... (248 times, avg 6 ms) 1697 ms: boost::io::basic_altstringbuf<$>::overflow(int) (194 times, avg 8 ms) 1684 ms: nix::fetchers::GitInputScheme::fetch(nix::ref<$>, nix::fetchers::Inp... (1 times, avg 1684 ms) 1680 ms: std::_Rb_tree_node<$>* std::_Rb_tree<$>::_M_copy<$>(std::_Rb_tree_no... (303 times, avg 5 ms) 1589 ms: bool nlohmann::json_abi_v3_11_3::detail::parser<$>::sax_parse_intern... (18 times, avg 88 ms) 1483 ms: non-virtual thunk to boost::wrapexcept<$>::~wrapexcept() (181 times, avg 8 ms) 1447 ms: nlohmann::json_abi_v3_11_3::detail::serializer<$>::dump_escaped(std:... (40 times, avg 36 ms) 1441 ms: std::__shared_ptr<$>::~__shared_ptr() (496 times, avg 2 ms) 1420 ms: boost::stacktrace::basic_stacktrace<$>::init(unsigned long, unsigned... (137 times, avg 10 ms) 1396 ms: boost::basic_format<$>::~basic_format() (194 times, avg 7 ms) 1290 ms: std::__cxx11::basic_string<$>::_M_replace_cold(char*, unsigned long,... (231 times, avg 5 ms) 1258 ms: std::vector<$>::~vector() (354 times, avg 3 ms) 1222 ms: std::__cxx11::basic_string<$>::_M_replace(unsigned long, unsigned lo... (231 times, avg 5 ms) 1194 ms: std::_Rb_tree<$>::_M_get_insert_hint_unique_pos(std::_Rb_tree_const_... (49 times, avg 24 ms) 1186 ms: bool tao::pegtl::internal::sor<$>::match<$>(std::integer_sequence<$>... (1 times, avg 1186 ms) 1149 ms: std::__detail::_Executor<$>::_M_dfs(std::__detail::_Executor<$>::_Ma... (70 times, avg 16 ms) 1123 ms: toml::detail::sequence<$>::invoke(toml::detail::location&) (69 times, avg 16 ms) 1110 ms: nlohmann::json_abi_v3_11_3::basic_json<$>::json_value::destroy(nlohm... (55 times, avg 20 ms) 1079 ms: std::_Function_handler<$>::_M_manager(std::_Any_data&, std::_Any_dat... (541 times, avg 1 ms) 1033 ms: nlohmann::json_abi_v3_11_3::detail::lexer<$>::scan_number() (20 times, avg 51 ms) Change-Id: I10af282bcd4fc39c2d3caae3453e599e4639c70b --- src/libutil/args.cc | 5 +-- src/libutil/args.hh | 2 ++ src/libutil/backed-string-view.hh | 69 +++++++++++++++++++++++++++++++++++++ src/libutil/error.cc | 1 + src/libutil/file-system.cc | 1 + src/libutil/hash.cc | 1 + src/libutil/meson.build | 1 + src/libutil/processes.cc | 1 + src/libutil/regex.cc | 3 ++ src/libutil/serialise.cc | 22 +++++++++++- src/libutil/serialise.hh | 7 ++-- src/libutil/source-path.cc | 1 + src/libutil/strings.hh | 13 ------- src/libutil/types.hh | 72 ++------------------------------------- 14 files changed, 110 insertions(+), 89 deletions(-) create mode 100644 src/libutil/backed-string-view.hh (limited to 'src/libutil') diff --git a/src/libutil/args.cc b/src/libutil/args.cc index 1342e7c6a..edcab23ac 100644 --- a/src/libutil/args.cc +++ b/src/libutil/args.cc @@ -1,10 +1,11 @@ #include "args.hh" #include "args/root.hh" #include "hash.hh" -#include "json-utils.hh" +#include "strings.hh" +#include "json-utils.hh" // IWYU pragma: keep (instances) #include "environment-variables.hh" -#include "experimental-features-json.hh" +#include "experimental-features-json.hh" // IWYU pragma: keep (instances) #include "logging.hh" #include diff --git a/src/libutil/args.hh b/src/libutil/args.hh index 5fdbaba7e..e2bac6415 100644 --- a/src/libutil/args.hh +++ b/src/libutil/args.hh @@ -3,6 +3,8 @@ #include "experimental-features.hh" #include "types.hh" +#include "ref.hh" + #include #include #include diff --git a/src/libutil/backed-string-view.hh b/src/libutil/backed-string-view.hh new file mode 100644 index 000000000..96136331c --- /dev/null +++ b/src/libutil/backed-string-view.hh @@ -0,0 +1,69 @@ +#pragma once +/// @file String view that can be either owned or borrowed. +#include +#include +#include + +/** + * This wants to be a little bit like rust's Cow type. + * Some parts of the evaluator benefit greatly from being able to reuse + * existing allocations for strings, but have to be able to also use + * newly allocated storage for values. + * + * We do not define implicit conversions, even with ref qualifiers, + * since those can easily become ambiguous to the reader and can degrade + * into copying behaviour we want to avoid. + */ +class BackedStringView { +private: + std::variant data; + + /** + * Needed to introduce a temporary since operator-> must return + * a pointer. Without this we'd need to store the view object + * even when we already own a string. + */ + class Ptr { + private: + std::string_view view; + public: + Ptr(std::string_view view): view(view) {} + const std::string_view * operator->() const { return &view; } + }; + +public: + BackedStringView(std::string && s): data(std::move(s)) {} + BackedStringView(std::string_view sv): data(sv) {} + template + BackedStringView(const char (& lit)[N]): data(std::string_view(lit)) {} + + BackedStringView(const BackedStringView &) = delete; + BackedStringView & operator=(const BackedStringView &) = delete; + + /** + * We only want move operations defined since the sole purpose of + * this type is to avoid copies. + */ + BackedStringView(BackedStringView && other) = default; + BackedStringView & operator=(BackedStringView && other) = default; + + bool isOwned() const + { + return std::holds_alternative(data); + } + + std::string toOwned() && + { + return isOwned() + ? std::move(std::get(data)) + : std::string(std::get(data)); + } + + std::string_view operator*() const + { + return isOwned() + ? std::get(data) + : std::get(data); + } + Ptr operator->() const { return Ptr(**this); } +}; diff --git a/src/libutil/error.cc b/src/libutil/error.cc index e5d6a9fa8..a7cbfbfd0 100644 --- a/src/libutil/error.cc +++ b/src/libutil/error.cc @@ -3,6 +3,7 @@ #include "logging.hh" #include "position.hh" #include "terminal.hh" +#include "strings.hh" #include #include diff --git a/src/libutil/file-system.cc b/src/libutil/file-system.cc index 631cf076b..1d266067e 100644 --- a/src/libutil/file-system.cc +++ b/src/libutil/file-system.cc @@ -10,6 +10,7 @@ #include "logging.hh" #include "serialise.hh" #include "signals.hh" +#include "strings.hh" #include "types.hh" #include "users.hh" diff --git a/src/libutil/hash.cc b/src/libutil/hash.cc index f05d4aa98..d383e9802 100644 --- a/src/libutil/hash.cc +++ b/src/libutil/hash.cc @@ -10,6 +10,7 @@ #include "charptr-cast.hh" #include "logging.hh" #include "split.hh" +#include "strings.hh" #include #include diff --git a/src/libutil/meson.build b/src/libutil/meson.build index e7f986363..6566f7f46 100644 --- a/src/libutil/meson.build +++ b/src/libutil/meson.build @@ -53,6 +53,7 @@ libutil_headers = files( 'archive.hh', 'args/root.hh', 'args.hh', + 'backed-string-view.hh', 'box_ptr.hh', 'canon-path.hh', 'cgroup.hh', diff --git a/src/libutil/processes.cc b/src/libutil/processes.cc index 61e1ad556..eec592221 100644 --- a/src/libutil/processes.cc +++ b/src/libutil/processes.cc @@ -3,6 +3,7 @@ #include "finally.hh" #include "logging.hh" #include "processes.hh" +#include "strings.hh" #include "serialise.hh" #include "signals.hh" diff --git a/src/libutil/regex.cc b/src/libutil/regex.cc index a9e6c6bee..a12d13550 100644 --- a/src/libutil/regex.cc +++ b/src/libutil/regex.cc @@ -1,6 +1,9 @@ #include #include +// Declared as extern in precompiled-headers.hh +template class std::basic_regex; + namespace nix::regex { std::string quoteRegexChars(const std::string & raw) { diff --git a/src/libutil/serialise.cc b/src/libutil/serialise.cc index 4eda1b7e7..f509fedff 100644 --- a/src/libutil/serialise.cc +++ b/src/libutil/serialise.cc @@ -9,6 +9,21 @@ namespace nix { +namespace { +/** + * Convert a little-endian integer to host order. + */ +template +T readLittleEndian(unsigned char * p) +{ + T x = 0; + for (size_t i = 0; i < sizeof(x); ++i, ++p) { + x |= ((T) *p) << (i * 8); + } + return x; +} +} + template T readNum(Source & source) { @@ -152,7 +167,7 @@ size_t FdSource::readUnbuffered(char * data, size_t len) n = ::read(fd, data, len); } while (n == -1 && errno == EINTR); if (n == -1) { _good = false; throw SysError("reading from file"); } - if (n == 0) { _good = false; throw EndOfFile(std::string(*endOfFileError)); } + if (n == 0) { _good = false; throw EndOfFile(endOfFileError()); } read += n; return n; } @@ -163,6 +178,11 @@ bool FdSource::good() return _good; } +std::string FdSource::endOfFileError() const +{ + return specialEndOfFileError.has_value() ? *specialEndOfFileError : "unexpected end-of-file"; +} + size_t StringSource::read(char * data, size_t len) { diff --git a/src/libutil/serialise.hh b/src/libutil/serialise.hh index 9ad8018d0..612658b2d 100644 --- a/src/libutil/serialise.hh +++ b/src/libutil/serialise.hh @@ -1,12 +1,10 @@ #pragma once ///@file -#include #include #include "charptr-cast.hh" #include "generator.hh" -#include "strings.hh" #include "types.hh" #include "file-descriptor.hh" @@ -153,7 +151,10 @@ struct FdSource : BufferedSource { int fd; size_t read = 0; - BackedStringView endOfFileError{"unexpected end-of-file"}; + /** Defaults to "unexpected end-of-file" */ + std::optional specialEndOfFileError; + + std::string endOfFileError() const; FdSource() : fd(-1) { } FdSource(int fd) : fd(fd) { } diff --git a/src/libutil/source-path.cc b/src/libutil/source-path.cc index cfaac20c0..782005ef1 100644 --- a/src/libutil/source-path.cc +++ b/src/libutil/source-path.cc @@ -1,4 +1,5 @@ #include "source-path.hh" +#include "strings.hh" namespace nix { diff --git a/src/libutil/strings.hh b/src/libutil/strings.hh index 7330e2063..ebafab9ad 100644 --- a/src/libutil/strings.hh +++ b/src/libutil/strings.hh @@ -164,19 +164,6 @@ template std::optional string2Float(const std::string_view s); -/** - * Convert a little-endian integer to host order. - */ -template -T readLittleEndian(unsigned char * p) -{ - T x = 0; - for (size_t i = 0; i < sizeof(x); ++i, ++p) { - x |= ((T) *p) << (i * 8); - } - return x; -} - /** * Convert a string to lower case. */ diff --git a/src/libutil/types.hh b/src/libutil/types.hh index 13cb062fb..66c41fe59 100644 --- a/src/libutil/types.hh +++ b/src/libutil/types.hh @@ -1,17 +1,15 @@ #pragma once ///@file -#include "ref.hh" - #include #include #include #include -#include +#include #include -#include #include #include +#include // IWYU pragma: keep (this is used literally everywhere) namespace nix { @@ -166,70 +164,4 @@ constexpr auto enumerate(T && iterable) template struct overloaded : Ts... { using Ts::operator()...; }; template overloaded(Ts...) -> overloaded; - - -/** - * This wants to be a little bit like rust's Cow type. - * Some parts of the evaluator benefit greatly from being able to reuse - * existing allocations for strings, but have to be able to also use - * newly allocated storage for values. - * - * We do not define implicit conversions, even with ref qualifiers, - * since those can easily become ambiguous to the reader and can degrade - * into copying behaviour we want to avoid. - */ -class BackedStringView { -private: - std::variant data; - - /** - * Needed to introduce a temporary since operator-> must return - * a pointer. Without this we'd need to store the view object - * even when we already own a string. - */ - class Ptr { - private: - std::string_view view; - public: - Ptr(std::string_view view): view(view) {} - const std::string_view * operator->() const { return &view; } - }; - -public: - BackedStringView(std::string && s): data(std::move(s)) {} - BackedStringView(std::string_view sv): data(sv) {} - template - BackedStringView(const char (& lit)[N]): data(std::string_view(lit)) {} - - BackedStringView(const BackedStringView &) = delete; - BackedStringView & operator=(const BackedStringView &) = delete; - - /** - * We only want move operations defined since the sole purpose of - * this type is to avoid copies. - */ - BackedStringView(BackedStringView && other) = default; - BackedStringView & operator=(BackedStringView && other) = default; - - bool isOwned() const - { - return std::holds_alternative(data); - } - - std::string toOwned() && - { - return isOwned() - ? std::move(std::get(data)) - : std::string(std::get(data)); - } - - std::string_view operator*() const - { - return isOwned() - ? std::get(data) - : std::get(data); - } - Ptr operator->() const { return Ptr(**this); } -}; - } -- cgit v1.2.3