1
0
Fork 0
mirror of https://github.com/NixOS/nix synced 2025-06-27 08:31:16 +02:00

Make computeFSClosure() single-threaded again

The fact that queryPathInfo() is synchronous meant that we needed a
thread for every concurrent binary cache lookup, even though they end
up being handled by the same download thread. Requiring hundreds of
threads is not a good idea. So now there is an asynchronous version of
queryPathInfo() that takes a callback function to process the
result. Similarly, enqueueDownload() now takes a callback rather than
returning a future.

Thus, a command like

  nix path-info --store https://cache.nixos.org/ -r /nix/store/slljrzwmpygy1daay14kjszsr9xix063-nixos-16.09beta231.dccf8c5

that returns 4941 paths now takes 1.87s using only 2 threads (the main
thread and the downloader thread). (This is with a prewarmed
CloudFront.)
This commit is contained in:
Eelco Dolstra 2016-09-16 18:54:14 +02:00
parent 054be50257
commit 75989bdca7
16 changed files with 410 additions and 227 deletions

View file

@ -8,66 +8,90 @@
namespace nix {
void Store::computeFSClosure(const Path & path,
PathSet & paths, bool flipDirection, bool includeOutputs, bool includeDerivers)
void Store::computeFSClosure(const Path & startPath,
PathSet & paths_, bool flipDirection, bool includeOutputs, bool includeDerivers)
{
ThreadPool pool;
Sync<bool> state_;
std::function<void(Path)> doPath;
doPath = [&](const Path & path) {
{
auto state(state_.lock());
if (paths.count(path)) return;
paths.insert(path);
}
auto info = queryPathInfo(path);
if (flipDirection) {
PathSet referrers;
queryReferrers(path, referrers);
for (auto & ref : referrers)
if (ref != path)
pool.enqueue(std::bind(doPath, ref));
if (includeOutputs) {
PathSet derivers = queryValidDerivers(path);
for (auto & i : derivers)
pool.enqueue(std::bind(doPath, i));
}
if (includeDerivers && isDerivation(path)) {
PathSet outputs = queryDerivationOutputs(path);
for (auto & i : outputs)
if (isValidPath(i) && queryPathInfo(i)->deriver == path)
pool.enqueue(std::bind(doPath, i));
}
} else {
for (auto & ref : info->references)
if (ref != path)
pool.enqueue(std::bind(doPath, ref));
if (includeOutputs && isDerivation(path)) {
PathSet outputs = queryDerivationOutputs(path);
for (auto & i : outputs)
if (isValidPath(i)) pool.enqueue(std::bind(doPath, i));
}
if (includeDerivers && isValidPath(info->deriver))
pool.enqueue(std::bind(doPath, info->deriver));
}
struct State
{
size_t pending;
PathSet & paths;
std::exception_ptr exc;
};
pool.enqueue(std::bind(doPath, path));
Sync<State> state_(State{0, paths_, 0});
pool.process();
std::function<void(const Path &)> enqueue;
std::condition_variable done;
enqueue = [&](const Path & path) -> void {
{
auto state(state_.lock());
if (state->exc) return;
if (state->paths.count(path)) return;
state->paths.insert(path);
state->pending++;
}
queryPathInfo(path,
[&, path](ref<ValidPathInfo> info) {
// FIXME: calls to isValidPath() should be async
if (flipDirection) {
PathSet referrers;
queryReferrers(path, referrers);
for (auto & ref : referrers)
if (ref != path)
enqueue(ref);
if (includeOutputs)
for (auto & i : queryValidDerivers(path))
enqueue(i);
if (includeDerivers && isDerivation(path))
for (auto & i : queryDerivationOutputs(path))
if (isValidPath(i) && queryPathInfo(i)->deriver == path)
enqueue(i);
} else {
for (auto & ref : info->references)
if (ref != path)
enqueue(ref);
if (includeOutputs && isDerivation(path))
for (auto & i : queryDerivationOutputs(path))
if (isValidPath(i)) enqueue(i);
if (includeDerivers && isValidPath(info->deriver))
enqueue(info->deriver);
}
{
auto state(state_.lock());
assert(state->pending);
if (!--state->pending) done.notify_one();
}
},
[&, path](std::exception_ptr exc) {
auto state(state_.lock());
if (!state->exc) state->exc = exc;
assert(state->pending);
if (!--state->pending) done.notify_one();
});
};
enqueue(startPath);
{
auto state(state_.lock());
while (state->pending) state.wait(done);
if (state->exc) std::rethrow_exception(state->exc);
}
}