Files
lix/src/libutil/processes.cc
T
Jade LovelaceandRebecca Turner 04f8a14833 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<char>::_M_compile (28 times, avg 543 ms)
 15066 ms: std::__detail::_Compiler<std::regex_traits<char>>::_Compiler (28 times, avg 538 ms)
 12571 ms: std::__detail::_Compiler<std::regex_traits<char>>::_M_disjunction (28 times, avg 448 ms)
 12454 ms: std::__detail::_Compiler<std::regex_traits<char>>::_M_alternative (28 times, avg 444 ms)
 12225 ms: std::__detail::_Compiler<std::regex_traits<char>>::_M_term (28 times, avg 436 ms)
 11363 ms: nlohmann::basic_json<>::parse<const char *> (21 times, avg 541 ms)
 10628 ms: nlohmann::basic_json<>::basic_json (109 times, avg 97 ms)
 10134 ms: std::__detail::_Compiler<std::regex_traits<char>>::_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<boost::stacktrace::de... (137 times, avg 22 ms)
  2896 ms: void boost::io::detail::mk_str<$>(std::__cxx11::basic_string<$>&, 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<boost::stacktrace::de... (137 times, avg 23 ms)
  3045 ms: void boost::io::detail::mk_str<$>(std::__cxx11::basic_string<$>&, 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
2024-08-28 09:55:05 -07:00

382 lines
9.9 KiB
C++

#include "current-process.hh"
#include "environment-variables.hh"
#include "finally.hh"
#include "logging.hh"
#include "processes.hh"
#include "strings.hh"
#include "serialise.hh"
#include "signals.hh"
#include <cerrno>
#include <cstdlib>
#include <cstring>
#include <iostream>
#include <grp.h>
#include <sys/types.h>
#include <sys/wait.h>
#include <unistd.h>
#ifdef __APPLE__
# include <sys/syscall.h>
#endif
#ifdef __linux__
# include <sys/prctl.h>
# include <sys/mman.h>
#endif
namespace nix {
Pid::Pid()
{
}
Pid::Pid(Pid && other) : pid(other.pid), separatePG(other.separatePG), killSignal(other.killSignal)
{
other.pid = -1;
}
Pid & Pid::operator=(Pid && other)
{
Pid tmp(std::move(other));
std::swap(pid, tmp.pid);
std::swap(separatePG, tmp.separatePG);
std::swap(killSignal, tmp.killSignal);
return *this;
}
Pid::~Pid() noexcept(false)
{
if (pid != -1) kill();
}
int Pid::kill()
{
assert(pid != -1);
debug("killing process %1%", pid);
/* Send the requested signal to the child. If it has its own
process group, send the signal to every process in the child
process group (which hopefully includes *all* its children). */
if (::kill(separatePG ? -pid : pid, killSignal) != 0) {
/* On BSDs, killing a process group will return EPERM if all
processes in the group are zombies (or something like
that). So try to detect and ignore that situation. */
#if __FreeBSD__ || __APPLE__
if (errno != EPERM || ::kill(pid, 0) != 0)
#endif
logError(SysError("killing process %d", pid).info());
}
return wait();
}
int Pid::wait()
{
assert(pid != -1);
while (1) {
int status;
int res = waitpid(pid, &status, 0);
if (res == pid) {
pid = -1;
return status;
}
if (errno != EINTR)
throw SysError("cannot get exit status of PID %d", pid);
checkInterrupt();
}
}
void Pid::setSeparatePG(bool separatePG)
{
this->separatePG = separatePG;
}
void Pid::setKillSignal(int signal)
{
this->killSignal = signal;
}
pid_t Pid::release()
{
pid_t p = pid;
pid = -1;
return p;
}
void killUser(uid_t uid)
{
debug("killing all processes running under uid '%1%'", uid);
assert(uid != 0); /* just to be safe... */
/* The system call kill(-1, sig) sends the signal `sig' to all
users to which the current process can send signals. So we
fork a process, switch to uid, and send a mass kill. */
Pid pid{startProcess([&]() {
if (setuid(uid) == -1)
throw SysError("setting uid");
while (true) {
#ifdef __APPLE__
/* OSX's kill syscall takes a third parameter that, among
other things, determines if kill(-1, signo) affects the
calling process. In the OSX libc, it's set to true,
which means "follow POSIX", which we don't want here
*/
if (syscall(SYS_kill, -1, SIGKILL, false) == 0) break;
#else
if (kill(-1, SIGKILL) == 0) break;
#endif
if (errno == ESRCH || errno == EPERM) break; /* no more processes */
if (errno != EINTR)
throw SysError("cannot kill processes for uid '%1%'", uid);
}
_exit(0);
})};
int status = pid.wait();
if (status != 0)
throw Error("cannot kill processes for uid '%1%': %2%", uid, statusToString(status));
/* !!! We should really do some check to make sure that there are
no processes left running under `uid', but there is no portable
way to do so (I think). The most reliable way may be `ps -eo
uid | grep -q $uid'. */
}
//////////////////////////////////////////////////////////////////////
static pid_t doFork(std::function<void()> fun)
{
pid_t pid = fork();
if (pid != 0) return pid;
fun();
abort();
}
#if __linux__
static int childEntry(void * arg)
{
auto main = static_cast<std::function<void()> *>(arg);
(*main)();
return 1;
}
#endif
Pid startProcess(std::function<void()> fun, const ProcessOptions & options)
{
std::function<void()> wrapper = [&]() {
logger = makeSimpleLogger();
try {
#if __linux__
if (options.dieWithParent && prctl(PR_SET_PDEATHSIG, SIGKILL) == -1)
throw SysError("setting death signal");
#endif
fun();
} catch (std::exception & e) {
try {
std::cerr << options.errorPrefix << e.what() << "\n";
} catch (...) { }
} catch (...) { }
if (options.runExitHandlers)
exit(1);
else
_exit(1);
};
pid_t pid = -1;
if (options.cloneFlags) {
#ifdef __linux__
// Not supported, since then we don't know when to free the stack.
assert(!(options.cloneFlags & CLONE_VM));
size_t stackSize = 1 * 1024 * 1024;
auto stack = static_cast<char *>(mmap(0, stackSize,
PROT_WRITE | PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0));
if (stack == MAP_FAILED) throw SysError("allocating stack");
Finally freeStack([&]() { munmap(stack, stackSize); });
pid = clone(childEntry, stack + stackSize, options.cloneFlags | SIGCHLD, &wrapper);
#else
throw Error("clone flags are only supported on Linux");
#endif
} else
pid = doFork(wrapper);
if (pid == -1) throw SysError("unable to fork");
return Pid{pid};
}
std::string runProgram(Path program, bool searchPath, const Strings & args, bool isInteractive)
{
auto res = runProgram(RunOptions {.program = program, .searchPath = searchPath, .args = args, .isInteractive = isInteractive});
if (!statusOk(res.first))
throw ExecError(res.first, "program '%1%' %2%", program, statusToString(res.first));
return res.second;
}
// Output = error code + "standard out" output stream
std::pair<int, std::string> runProgram(RunOptions && options)
{
options.captureStdout = true;
int status = 0;
std::string stdout;
try {
auto proc = runProgram2(options);
Finally const _wait([&] { proc.wait(); });
stdout = proc.getStdout()->drain();
} catch (ExecError & e) {
status = e.status;
}
return {status, std::move(stdout)};
}
RunningProgram::RunningProgram(PathView program, Pid pid, AutoCloseFD stdout)
: program(program)
, pid(std::move(pid))
, stdoutSource(stdout ? std::make_unique<FdSource>(stdout.get()) : nullptr)
, stdout_(std::move(stdout))
{
}
RunningProgram::~RunningProgram()
{
if (pid) {
// we will not kill a subprocess because we *can't* kill a subprocess
// reliably without placing it in its own process group, and cleaning
// up a subprocess only when `separatePG` is set is a loaded footgun.
assert(false && "destroying un-wait()ed running process");
std::terminate();
}
}
void RunningProgram::wait()
{
if (std::uncaught_exceptions() == 0) {
int status = pid.wait();
if (status)
throw ExecError(status, "program '%1%' %2%", program, statusToString(status));
} else {
pid.kill();
debug("killed subprocess %1% during exception handling", program);
}
}
RunningProgram runProgram2(const RunOptions & options)
{
checkInterrupt();
/* Create a pipe. */
Pipe out;
if (options.captureStdout) out.create();
ProcessOptions processOptions;
std::optional<Finally<std::function<void()>>> resumeLoggerDefer;
if (options.isInteractive) {
logger->pause();
resumeLoggerDefer.emplace(
[]() {
logger->resume();
}
);
}
/* Fork. */
Pid pid{startProcess([&]() {
if (options.environment)
replaceEnv(*options.environment);
if (options.captureStdout && dup2(out.writeSide.get(), STDOUT_FILENO) == -1)
throw SysError("dupping stdout");
if (options.mergeStderrToStdout)
if (dup2(STDOUT_FILENO, STDERR_FILENO) == -1)
throw SysError("cannot dup stdout into stderr");
if (options.chdir && chdir((*options.chdir).c_str()) == -1)
throw SysError("chdir failed");
if (options.gid && setgid(*options.gid) == -1)
throw SysError("setgid failed");
/* Drop all other groups if we're setgid. */
if (options.gid && setgroups(0, 0) == -1)
throw SysError("setgroups failed");
if (options.uid && setuid(*options.uid) == -1)
throw SysError("setuid failed");
Strings args_(options.args);
args_.push_front(options.program);
restoreProcessContext();
if (options.searchPath)
execvp(options.program.c_str(), stringsToCharPtrs(args_).data());
// This allows you to refer to a program with a pathname relative
// to the PATH variable.
else
execv(options.program.c_str(), stringsToCharPtrs(args_).data());
throw SysError("executing '%1%'", options.program);
}, processOptions)};
out.writeSide.close();
return RunningProgram{
options.program,
std::move(pid),
options.captureStdout ? std::move(out.readSide) : AutoCloseFD{}
};
}
std::string statusToString(int status)
{
if (!WIFEXITED(status) || WEXITSTATUS(status) != 0) {
if (WIFEXITED(status))
return fmt("failed with exit code %1%", WEXITSTATUS(status));
else if (WIFSIGNALED(status)) {
int sig = WTERMSIG(status);
#if HAVE_STRSIGNAL
const char * description = strsignal(sig);
return fmt("failed due to signal %1% (%2%)", sig, description);
#else
return fmt("failed due to signal %1%", sig);
#endif
}
else
return "died abnormally";
} else return "succeeded";
}
bool statusOk(int status)
{
return WIFEXITED(status) && WEXITSTATUS(status) == 0;
}
}