lix/src/build-remote/build-remote.cc
Jade Lovelace 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

391 lines
15 KiB
C++
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

#include <algorithm>
#include <set>
#include <memory>
#include <tuple>
#if __APPLE__
#include <sys/time.h>
#endif
#include "machines.hh"
#include "shared.hh"
#include "pathlocks.hh"
#include "globals.hh"
#include "serialise.hh"
#include "build-result.hh"
#include "store-api.hh"
#include "derivations.hh"
#include "strings.hh"
#include "local-store.hh"
#include "legacy.hh"
#include "experimental-features.hh"
#include "hash.hh"
using namespace nix;
static void handleAlarm(int sig) {
}
std::string escapeUri(std::string uri)
{
std::replace(uri.begin(), uri.end(), '/', '_');
return uri;
}
static std::string currentLoad;
static std::string makeLockFilename(const std::string & storeUri) {
// We include 48 bytes of escaped URI to give an idea of what the lock
// is on, then 16 bytes of hash to disambiguate.
// This avoids issues with the escaped URI being very long and causing
// path too long errors, while also avoiding any possibility of collision
// caused by simple truncation.
auto hash = hashString(HashType::SHA256, storeUri).to_string(Base::Base32, false);
return escapeUri(storeUri).substr(0, 48) + "-" + hash.substr(0, 16);
}
static AutoCloseFD openSlotLock(const Machine & m, uint64_t slot)
{
return openLockFile(fmt("%s/%s-%d", currentLoad, makeLockFilename(m.storeUri), slot), true);
}
static bool allSupportedLocally(Store & store, const std::set<std::string>& requiredFeatures) {
for (auto & feature : requiredFeatures)
if (!store.systemFeatures.get().count(feature)) return false;
return true;
}
static int main_build_remote(int argc, char * * argv)
{
{
logger = makeJSONLogger(*logger);
/* Ensure we don't get any SSH passphrase or host key popups. */
unsetenv("DISPLAY");
unsetenv("SSH_ASKPASS");
/* If we ever use the common args framework, make sure to
remove initPlugins below and initialize settings first.
*/
if (argc != 2)
throw UsageError("called without required arguments");
verbosity = (Verbosity) std::stoll(argv[1]);
FdSource source(STDIN_FILENO);
/* Read the parent's settings. */
while (readInt(source)) {
auto name = readString(source);
auto value = readString(source);
settings.set(name, value);
}
auto maxBuildJobs = settings.maxBuildJobs;
settings.maxBuildJobs.set("1"); // hack to make tests with local?root= work
initPlugins();
auto store = openStore();
/* It would be more appropriate to use $XDG_RUNTIME_DIR, since
that gets cleared on reboot, but it wouldn't work on macOS. */
auto currentLoadName = "/current-load";
if (auto localStore = store.dynamic_pointer_cast<LocalFSStore>())
currentLoad = std::string { localStore->stateDir } + currentLoadName;
else
currentLoad = settings.nixStateDir + currentLoadName;
std::shared_ptr<Store> sshStore;
AutoCloseFD bestSlotLock;
auto machines = getMachines();
debug("got %d remote builders", machines.size());
if (machines.empty()) {
std::cerr << "# decline-permanently\n";
return 0;
}
std::optional<StorePath> drvPath;
std::string storeUri;
while (true) {
try {
auto s = readString(source);
if (s != "try") return 0;
} catch (EndOfFile &) { return 0; }
auto amWilling = readInt(source);
auto neededSystem = readString(source);
drvPath = store->parseStorePath(readString(source));
auto requiredFeatures = readStrings<std::set<std::string>>(source);
/* It would be possible to build locally after some builds clear out,
so don't show the warning now: */
bool couldBuildLocally = maxBuildJobs > 0
&& ( neededSystem == settings.thisSystem
|| settings.extraPlatforms.get().count(neededSystem) > 0)
&& allSupportedLocally(*store, requiredFeatures);
/* It's possible to build this locally right now: */
bool canBuildLocally = amWilling && couldBuildLocally;
/* Error ignored here, will be caught later */
mkdir(currentLoad.c_str(), 0777);
while (true) {
bestSlotLock.reset();
AutoCloseFD lock = openLockFile(currentLoad + "/main-lock", true);
lockFile(lock.get(), ltWrite, true);
bool rightType = false;
Machine * bestMachine = nullptr;
uint64_t bestLoad = 0;
for (auto & m : machines) {
debug("considering building on remote machine '%s'", m.storeUri);
if (m.enabled &&
m.systemSupported(neededSystem) &&
m.allSupported(requiredFeatures) &&
m.mandatoryMet(requiredFeatures))
{
rightType = true;
AutoCloseFD free;
uint64_t load = 0;
for (uint64_t slot = 0; slot < m.maxJobs; ++slot) {
auto slotLock = openSlotLock(m, slot);
if (lockFile(slotLock.get(), ltWrite, false)) {
if (!free) {
free = std::move(slotLock);
}
} else {
++load;
}
}
if (!free) {
continue;
}
bool best = false;
if (!bestSlotLock) {
best = true;
} else if (load / m.speedFactor < bestLoad / bestMachine->speedFactor) {
best = true;
} else if (load / m.speedFactor == bestLoad / bestMachine->speedFactor) {
if (m.speedFactor > bestMachine->speedFactor) {
best = true;
} else if (m.speedFactor == bestMachine->speedFactor) {
if (load < bestLoad) {
best = true;
}
}
}
if (best) {
bestLoad = load;
bestSlotLock = std::move(free);
bestMachine = &m;
}
}
}
if (!bestSlotLock) {
if (rightType && !canBuildLocally)
std::cerr << "# postpone\n";
else
{
// add the template values.
std::string drvstr;
if (drvPath.has_value())
drvstr = drvPath->to_string();
else
drvstr = "<unknown>";
std::string machinesFormatted;
for (auto & m : machines) {
machinesFormatted += HintFmt(
"\n([%s], %s, [%s], [%s])",
concatStringsSep<StringSet>(", ", m.systemTypes),
m.maxJobs,
concatStringsSep<StringSet>(", ", m.supportedFeatures),
concatStringsSep<StringSet>(", ", m.mandatoryFeatures)
).str();
}
auto error = HintFmt(
"Failed to find a machine for remote build!\n"
"derivation: %s\n"
"required (system, features): (%s, [%s])\n"
"%s available machines:\n"
"(systems, maxjobs, supportedFeatures, mandatoryFeatures)%s",
drvstr,
neededSystem,
concatStringsSep<StringSet>(", ", requiredFeatures),
machines.size(),
Uncolored(machinesFormatted)
);
printMsg(couldBuildLocally ? lvlChatty : lvlWarn, error.str());
std::cerr << "# decline\n";
}
break;
}
#if __APPLE__
futimes(bestSlotLock.get(), nullptr);
#else
futimens(bestSlotLock.get(), nullptr);
#endif
lock.reset();
try {
Activity act(*logger, lvlTalkative, actUnknown, fmt("connecting to '%s'", bestMachine->storeUri));
sshStore = bestMachine->openStore();
sshStore->connect();
storeUri = bestMachine->storeUri;
} catch (std::exception & e) {
auto msg = chomp(drainFD(5, false));
printError("cannot build on '%s': %s%s",
bestMachine->storeUri, e.what(),
msg.empty() ? "" : ": " + msg);
bestMachine->enabled = false;
continue;
}
goto connected;
}
}
connected:
close(5);
assert(sshStore);
std::cerr << "# accept\n" << storeUri << "\n";
auto inputs = readStrings<PathSet>(source);
auto wantedOutputs = readStrings<StringSet>(source);
auto lockFileName = currentLoad + "/" + makeLockFilename(storeUri) + ".upload-lock";
AutoCloseFD uploadLock = openLockFile(lockFileName, true);
{
Activity act(*logger, lvlTalkative, actUnknown, fmt("waiting for the upload lock to '%s'", storeUri));
auto old = signal(SIGALRM, handleAlarm);
alarm(15 * 60);
if (!lockFile(uploadLock.get(), ltWrite, true))
printError("somebody is hogging the upload lock for '%s', continuing...");
alarm(0);
signal(SIGALRM, old);
}
auto substitute = settings.buildersUseSubstitutes ? Substitute : NoSubstitute;
{
Activity act(*logger, lvlTalkative, actUnknown, fmt("copying dependencies to '%s'", storeUri));
copyPaths(*store, *sshStore, store->parseStorePathSet(inputs), NoRepair, NoCheckSigs, substitute);
}
uploadLock.reset();
auto drv = store->readDerivation(*drvPath);
std::optional<BuildResult> optResult;
// If we don't know whether we are trusted (e.g. `ssh://`
// stores), we assume we are. This is necessary for backwards
// compat.
bool trustedOrLegacy = ({
std::optional trusted = sshStore->isTrustedClient();
!trusted || *trusted;
});
// See the very large comment in `case WorkerProto::Op::BuildDerivation:` in
// `src/libstore/daemon.cc` that explains the trust model here.
//
// This condition mirrors that: that code enforces the "rules" outlined there;
// we do the best we can given those "rules".
if (trustedOrLegacy || drv.type().isCA()) {
// Hijack the inputs paths of the derivation to include all
// the paths that come from the `inputDrvs` set. We dont do
// that for the derivations whose `inputDrvs` is empty
// because:
//
// 1. Its not needed
//
// 2. Changing the `inputSrcs` set changes the associated
// output ids, which break CA derivations
if (!drv.inputDrvs.map.empty())
drv.inputSrcs = store->parseStorePathSet(inputs);
optResult = sshStore->buildDerivation(*drvPath, (const BasicDerivation &) drv);
auto & result = *optResult;
if (!result.success())
throw Error("build of '%s' on '%s' failed: %s", store->printStorePath(*drvPath), storeUri, result.errorMsg);
} else {
copyClosure(*store, *sshStore, StorePathSet {*drvPath}, NoRepair, NoCheckSigs, substitute);
auto res = sshStore->buildPathsWithResults({
DerivedPath::Built {
.drvPath = makeConstantStorePathRef(*drvPath),
.outputs = OutputsSpec::All {},
}
});
// One path to build should produce exactly one build result
assert(res.size() == 1);
optResult = std::move(res[0]);
}
auto outputHashes = staticOutputHashes(*store, drv);
std::set<Realisation> missingRealisations;
StorePathSet missingPaths;
if (experimentalFeatureSettings.isEnabled(Xp::CaDerivations) && !drv.type().hasKnownOutputPaths()) {
for (auto & outputName : wantedOutputs) {
auto thisOutputHash = outputHashes.at(outputName);
auto thisOutputId = DrvOutput{ thisOutputHash, outputName };
if (!store->queryRealisation(thisOutputId)) {
debug("missing output %s", outputName);
assert(optResult);
auto & result = *optResult;
auto i = result.builtOutputs.find(outputName);
assert(i != result.builtOutputs.end());
auto & newRealisation = i->second;
missingRealisations.insert(newRealisation);
missingPaths.insert(newRealisation.outPath);
}
}
} else {
auto outputPaths = drv.outputsAndOptPaths(*store);
for (auto & [outputName, hopefullyOutputPath] : outputPaths) {
assert(hopefullyOutputPath.second);
if (!store->isValidPath(*hopefullyOutputPath.second))
missingPaths.insert(*hopefullyOutputPath.second);
}
}
if (!missingPaths.empty()) {
Activity act(*logger, lvlTalkative, actUnknown, fmt("copying outputs from '%s'", storeUri));
if (auto localStore = store.dynamic_pointer_cast<LocalStore>())
for (auto & path : missingPaths)
localStore->locksHeld.insert(store->printStorePath(path)); /* FIXME: ugly */
copyPaths(*sshStore, *store, missingPaths, NoRepair, NoCheckSigs, NoSubstitute);
}
// XXX: Should be done as part of `copyPaths`
for (auto & realisation : missingRealisations) {
// Should hold, because if the feature isn't enabled the set
// of missing realisations should be empty
experimentalFeatureSettings.require(Xp::CaDerivations);
store->registerDrvOutput(realisation);
}
return 0;
}
}
static RegisterLegacyCommand r_build_remote("build-remote", main_build_remote);