ahtlon/hydra
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'upstream/master' into use-store-api

Browse Source
This commit is contained in:
John Ericson
2023-12-04 10:34:00 -05:00
parent 2c3072aaee 874fcae1e8
commit 89c504e2d9
39 changed files with 534 additions and 406 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/hydra-build-step/Makefile.am
View File

@@ -1,5 +1,5 @@
bin_PROGRAMS = hydra-build-step
hydra_build_step_SOURCES = hydra-build-step.cc
hydra_build_step_LDADD = $(NIX_LIBS)
hydra_build_step_LDADD = $(NIX_LIBS) -lnixcmd
hydra_build_step_CXXFLAGS = $(NIX_CFLAGS)

25
src/hydra-build-step/hydra-build-step.cc
View File

@@ -14,6 +14,7 @@
The build log is written to the path indicated by --log-file.
*/
#include "util.hh"
#include "shared.hh"
#include "common-eval-args.hh"
#include "store-api.hh"
@@ -37,7 +38,7 @@ void mainWrapped(std::list<std::string> args)
{
verbosity = lvlError;
struct MyArgs : MixEvalArgs, MixCommonArgs
struct MyArgs : MixEvalArgs, MixCommonArgs, RootArgs
{
Path drvPath;
std::optional<std::string> buildStoreUrl;
@@ -89,8 +90,8 @@ void mainWrapped(std::list<std::string> args)
throw SysError("creating log file '%s'", logPath);
}
void log(Verbosity lvl, const FormatOrString & fs) override
{ prev.log(lvl, fs); }
void log(Verbosity lvl, std::string_view s) override
{ prev.log(lvl, s); }
void logEI(const ErrorInfo & ei) override
{ prev.logEI(ei); }
@@ -124,9 +125,9 @@ void mainWrapped(std::list<std::string> args)
for (auto & p : drv.inputSrcs)
inputs.insert(p);
for (auto & input : drv.inputDrvs) {
auto drv2 = evalStore->readDerivation(input.first);
for (auto & name : input.second) {
for (auto & [drvPath, node] : drv.inputDrvs.map) {
auto drv2 = evalStore->readDerivation(drvPath);
for (auto & name : node.value) {
if (auto i = get(drv2.outputs, name)) {
auto outPath = i->path(*evalStore, drv2.name, name);
inputs.insert(*outPath);
@@ -193,10 +194,14 @@ void mainWrapped(std::list<std::string> args)
}
}
FdSink stdout(STDOUT_FILENO);
stdout << overhead;
stdout << totalNarSize;
worker_proto::write(*evalStore, stdout, buildResult);
FdSink to { STDOUT_FILENO };
WorkerProto::WriteConn wconn {
.to = to,
// Hardcode latest version because we are deploying hydra
// itself atomically
.version = PROTOCOL_VERSION,
};
WorkerProto::write(*evalStore, wconn, buildResult);
}
int main(int argc, char * * argv)

50
src/hydra-eval-jobs/hydra-eval-jobs.cc
View File

@@ -7,6 +7,9 @@
#include "store-api.hh"
#include "eval.hh"
#include "eval-inline.hh"
#include "eval-settings.hh"
#include "signals.hh"
#include "terminal.hh"
#include "util.hh"
#include "get-drvs.hh"
#include "globals.hh"
@@ -25,7 +28,8 @@
#include <nlohmann/json.hpp>
void check_pid_status_nonblocking(pid_t check_pid) {
void check_pid_status_nonblocking(pid_t check_pid)
{
// Only check 'initialized' and known PID's
if (check_pid <= 0) { return; }
@@ -52,7 +56,7 @@ using namespace nix;
static Path gcRootsDir;
static size_t maxMemorySize;
struct MyArgs : MixEvalArgs, MixCommonArgs
struct MyArgs : MixEvalArgs, MixCommonArgs, RootArgs
{
Path releaseExpr;
bool flake = false;
@@ -93,14 +97,14 @@ static std::string queryMetaStrings(EvalState & state, DrvInfo & drv, const std:
rec = [&](Value & v) {
state.forceValue(v, noPos);
if (v.type() == nString)
res.push_back(v.string.s);
res.emplace_back(v.string_view());
else if (v.isList())
for (unsigned int n = 0; n < v.listSize(); ++n)
rec(*v.listElems()[n]);
else if (v.type() == nAttrs) {
auto a = v.attrs->find(state.symbols.create(subAttribute));
if (a != v.attrs->end())
res.push_back(std::string(state.forceString(*a->value)));
res.push_back(std::string(state.forceString(*a->value, a->pos, "while evaluating meta attributes")));
}
};
@@ -129,7 +133,7 @@ static void worker(
LockFlags {
.updateLockFile = false,
.useRegistries = false,
.allowMutable = false,
.allowUnlocked = false,
});
callFlake(state, lockedFlake, *vFlake);
@@ -197,26 +201,30 @@ static void worker(
/* If this is an aggregate, then get its constituents. */
auto a = v->attrs->get(state.symbols.create("_hydraAggregate"));
if (a && state.forceBool(*a->value, a->pos)) {
if (a && state.forceBool(*a->value, a->pos, "while evaluating the `_hydraAggregate` attribute")) {
auto a = v->attrs->get(state.symbols.create("constituents"));
if (!a)
throw EvalError("derivation must have a ‘constituents’ attribute");
NixStringContext context;
state.coerceToString(a->pos, *a->value, context, "while evaluating the `constituents` attribute", true, false);
for (auto & c : context)
std::visit(overloaded {
[&](const NixStringContextElem::Built & b) {
job["constituents"].push_back(b.drvPath->to_string(*state.store));
},
[&](const NixStringContextElem::Opaque & o) {
},
[&](const NixStringContextElem::DrvDeep & d) {
},
}, c.raw);
PathSet context;
state.coerceToString(a->pos, *a->value, context, true, false);
for (auto & i : context)
if (i.at(0) == '!') {
size_t index = i.find("!", 1);
job["constituents"].push_back(std::string(i, index + 1));
}
state.forceList(*a->value, a->pos);
state.forceList(*a->value, a->pos, "while evaluating the `constituents` attribute");
for (unsigned int n = 0; n < a->value->listSize(); ++n) {
auto v = a->value->listElems()[n];
state.forceValue(*v, noPos);
if (v->type() == nString)
job["namedConstituents"].push_back(state.forceStringNoCtx(*v));
job["namedConstituents"].push_back(v->string_view());
}
}
@@ -245,7 +253,7 @@ static void worker(
StringSet ss;
for (auto & i : v->attrs->lexicographicOrder(state.symbols)) {
std::string name(state.symbols[i->name]);
if (name.find('.') != std::string::npos || name.find(' ') != std::string::npos) {
if (name.find(' ') != std::string::npos) {
printError("skipping job with illegal name '%s'", name);
continue;
}
@@ -416,7 +424,11 @@ int main(int argc, char * * argv)
if (response.find("attrs") != response.end()) {
for (auto & i : response["attrs"]) {
auto s = (attrPath.empty() ? "" : attrPath + ".") + (std::string) i;
std::string path = i;
if (path.find(".") != std::string::npos){
path = "\"" + path + "\"";
}
auto s = (attrPath.empty() ? "" : attrPath + ".") + (std::string) path;
newAttrs.insert(s);
}
}
@@ -507,7 +519,7 @@ int main(int argc, char * * argv)
auto drvPath2 = store->parseStorePath((std::string) (*job2)["drvPath"]);
auto drv2 = store->readDerivation(drvPath2);
job["constituents"].push_back(store->printStorePath(drvPath2));
drv.inputDrvs[drvPath2] = {drv2.outputs.begin()->first};
drv.inputDrvs.map[drvPath2].value = {drv2.outputs.begin()->first};
}
if (brokenJobs.empty()) {

7
src/hydra-evaluator/hydra-evaluator.cc
View File

@@ -2,6 +2,7 @@
#include "hydra-config.hh"
#include "pool.hh"
#include "shared.hh"
#include "signals.hh"
#include <algorithm>
#include <thread>
@@ -366,6 +367,9 @@ struct Evaluator
printInfo("received jobset event");
}
} catch (pqxx::broken_connection & e) {
printError("Database connection broken: %s", e.what());
std::_Exit(1);
} catch (std::exception & e) {
printError("exception in database monitor thread: %s", e.what());
sleep(30);
@@ -473,6 +477,9 @@ struct Evaluator
while (true) {
try {
loop();
} catch (pqxx::broken_connection & e) {
printError("Database connection broken: %s", e.what());
std::_Exit(1);
} catch (std::exception & e) {
printError("exception in main loop: %s", e.what());
sleep(30);

19
src/hydra-queue-runner/build-remote.cc
View File

@@ -1,5 +1,8 @@
#include "build-result.hh"
#include "serve-protocol.hh"
#include "state.hh"
#include "current-process.hh"
#include "processes.hh"
#include "util.hh"
#include "finally.hh"
#include "url.hh"
@@ -56,7 +59,7 @@ void State::buildRemote(ref<Store> destStore,
// FIXME: set pid for cancellation
auto [status, stdout] = [&]() {
auto [status, childStdout] = [&]() {
MaintainCount<counter> mc(nrStepsBuilding);
return runProgram({
.program = "hydra-build-step",
@@ -96,11 +99,17 @@ void State::buildRemote(ref<Store> destStore,
info->consecutiveFailures = 0;
}
StringSource from { childStdout };
/* Read the BuildResult from the child. */
StringSource source(stdout);
result.overhead += readNum<uint64_t>(source);
auto totalNarSize = readNum<uint64_t>(source);
auto buildResult = worker_proto::read(*localStore, source, Phantom<BuildResult> {});
WorkerProto::ReadConn rconn {
.from = from,
// Hardcode latest version because we are deploying hydra
// itself atomically
.version = PROTOCOL_VERSION,
};
result.overhead += readNum<uint64_t>(rconn.from);
auto totalNarSize = readNum<uint64_t>(rconn.from);
auto buildResult = WorkerProto::Serialise<BuildResult>::read(*localStore, rconn);
// FIXME: make RemoteResult inherit BuildResult.
result.errorMsg = buildResult.errorMsg;

12
src/hydra-queue-runner/build-result.cc
View File

@@ -1,7 +1,7 @@
#include "hydra-build-result.hh"
#include "store-api.hh"
#include "util.hh"
#include "fs-accessor.hh"
#include "source-accessor.hh"
#include <regex>
@@ -63,7 +63,7 @@ BuildOutput getBuildOutput(
auto productsFile = narMembers.find(outputS + "/nix-support/hydra-build-products");
if (productsFile == narMembers.end() ||
productsFile->second.type != FSAccessor::Type::tRegular)
productsFile->second.type != SourceAccessor::Type::tRegular)
continue;
assert(productsFile->second.contents);
@@ -94,7 +94,7 @@ BuildOutput getBuildOutput(
product.name = product.path == store->printStorePath(output) ? "" : baseNameOf(product.path);
if (file->second.type == FSAccessor::Type::tRegular) {
if (file->second.type == SourceAccessor::Type::tRegular) {
product.isRegular = true;
product.fileSize = file->second.fileSize.value();
product.sha256hash = file->second.sha256.value();
@@ -117,7 +117,7 @@ BuildOutput getBuildOutput(
auto file = narMembers.find(product.path);
assert(file != narMembers.end());
if (file->second.type == FSAccessor::Type::tDirectory)
if (file->second.type == SourceAccessor::Type::tDirectory)
res.products.push_back(product);
}
}
@@ -126,7 +126,7 @@ BuildOutput getBuildOutput(
for (auto & output : outputs) {
auto file = narMembers.find(store->printStorePath(output) + "/nix-support/hydra-release-name");
if (file == narMembers.end() ||
file->second.type != FSAccessor::Type::tRegular)
file->second.type != SourceAccessor::Type::tRegular)
continue;
res.releaseName = trim(file->second.contents.value());
// FIXME: validate release name
@@ -136,7 +136,7 @@ BuildOutput getBuildOutput(
for (auto & output : outputs) {
auto file = narMembers.find(store->printStorePath(output) + "/nix-support/hydra-metrics");
if (file == narMembers.end() ||
file->second.type != FSAccessor::Type::tRegular)
file->second.type != SourceAccessor::Type::tRegular)
continue;
for (auto & line : tokenizeString<Strings>(file->second.contents.value(), "\n")) {
auto fields = tokenizeString<std::vector<std::string>>(line);

5
src/hydra-queue-runner/builder.cc
View File

@@ -3,6 +3,7 @@
#include "state.hh"
#include "hydra-build-result.hh"
#include "finally.hh"
#include "terminal.hh"
#include "binary-cache-store.hh"
using namespace nix;
@@ -323,7 +324,7 @@ State::StepResult State::doBuildStep(nix::ref<Store> destStore,
pqxx::work txn(*conn);
for (auto & b : direct) {
printMsg(lvlInfo, format("marking build %1% as succeeded") % b->id);
printInfo("marking build %1% as succeeded", b->id);
markSucceededBuild(txn, b, res, buildId != b->id || result.isCached,
result.startTime, result.stopTime);
}
@@ -451,7 +452,7 @@ void State::failStep(
/* Mark all builds that depend on this derivation as failed. */
for (auto & build : indirect) {
if (build->finishedInDB) continue;
printMsg(lvlError, format("marking build %1% as failed") % build->id);
printError("marking build %1% as failed", build->id);
txn.exec_params0
("update Builds set finished = 1, buildStatus = $2, startTime = $3, stopTime = $4, isCachedBuild = $5, notificationPendingSince = $4 where id = $1 and finished = 0",
build->id,

213
src/hydra-queue-runner/dispatcher.cc
View File

@@ -52,7 +52,7 @@ void State::dispatcher()
{
auto dispatcherWakeup_(dispatcherWakeup.lock());
if (!*dispatcherWakeup_) {
printMsg(lvlDebug, format("dispatcher sleeping for %1%s") %
debug("dispatcher sleeping for %1%s",
std::chrono::duration_cast<std::chrono::seconds>(sleepUntil - std::chrono::system_clock::now()).count());
dispatcherWakeup_.wait_until(dispatcherWakeupCV, sleepUntil);
}
@@ -60,7 +60,7 @@ void State::dispatcher()
}
} catch (std::exception & e) {
printMsg(lvlError, format("dispatcher: %1%") % e.what());
printError("dispatcher: %s", e.what());
sleep(1);
}
@@ -80,17 +80,118 @@ system_time State::doDispatch()
jobset.second->pruneSteps();
auto s2 = jobset.second->shareUsed();
if (s1 != s2)
printMsg(lvlDebug, format("pruned scheduling window of ‘%1%:%2%’ from %3% to %4%")
% jobset.first.first % jobset.first.second % s1 % s2);
debug("pruned scheduling window of ‘%1%:%2%’ from %3% to %4%",
jobset.first.first, jobset.first.second, s1, s2);
}
}
system_time now = std::chrono::system_clock::now();
/* Start steps until we're out of steps or slots. */
auto sleepUntil = system_time::max();
bool keepGoing;
/* Sort the runnable steps by priority. Priority is establised
as follows (in order of precedence):
- The global priority of the builds that depend on the
step. This allows admins to bump a build to the front of
the queue.
- The lowest used scheduling share of the jobsets depending
on the step.
- The local priority of the build, as set via the build's
meta.schedulingPriority field. Note that this is not
quite correct: the local priority should only be used to
establish priority between builds in the same jobset, but
here it's used between steps in different jobsets if they
happen to have the same lowest used scheduling share. But
that's not very likely.
- The lowest ID of the builds depending on the step;
i.e. older builds take priority over new ones.
FIXME: O(n lg n); obviously, it would be better to keep a
runnable queue sorted by priority. */
struct StepInfo
{
Step::ptr step;
bool alreadyScheduled = false;
/* The lowest share used of any jobset depending on this
step. */
double lowestShareUsed = 1e9;
/* Info copied from step->state to ensure that the
comparator is a partial ordering (see MachineInfo). */
int highestGlobalPriority;
int highestLocalPriority;
BuildID lowestBuildID;
StepInfo(Step::ptr step, Step::State & step_) : step(step)
{
for (auto & jobset : step_.jobsets)
lowestShareUsed = std::min(lowestShareUsed, jobset->shareUsed());
highestGlobalPriority = step_.highestGlobalPriority;
highestLocalPriority = step_.highestLocalPriority;
lowestBuildID = step_.lowestBuildID;
}
};
std::vector<StepInfo> runnableSorted;
struct RunnablePerType
{
unsigned int count{0};
std::chrono::seconds waitTime{0};
};
std::unordered_map<std::string, RunnablePerType> runnablePerType;
{
auto runnable_(runnable.lock());
runnableSorted.reserve(runnable_->size());
for (auto i = runnable_->begin(); i != runnable_->end(); ) {
auto step = i->lock();
/* Remove dead steps. */
if (!step) {
i = runnable_->erase(i);
continue;
}
++i;
auto & r = runnablePerType[step->systemType];
r.count++;
/* Skip previously failed steps that aren't ready
to be retried. */
auto step_(step->state.lock());
r.waitTime += std::chrono::duration_cast<std::chrono::seconds>(now - step_->runnableSince);
if (step_->tries > 0 && step_->after > now) {
if (step_->after < sleepUntil)
sleepUntil = step_->after;
continue;
}
runnableSorted.emplace_back(step, *step_);
}
}
sort(runnableSorted.begin(), runnableSorted.end(),
[](const StepInfo & a, const StepInfo & b)
{
return
a.highestGlobalPriority != b.highestGlobalPriority ? a.highestGlobalPriority > b.highestGlobalPriority :
a.lowestShareUsed != b.lowestShareUsed ? a.lowestShareUsed < b.lowestShareUsed :
a.highestLocalPriority != b.highestLocalPriority ? a.highestLocalPriority > b.highestLocalPriority :
a.lowestBuildID < b.lowestBuildID;
});
do {
system_time now = std::chrono::system_clock::now();
now = std::chrono::system_clock::now();
/* Copy the currentJobs field of each machine. This is
necessary to ensure that the sort comparator below is
@@ -138,104 +239,6 @@ system_time State::doDispatch()
a.currentJobs > b.currentJobs;
});
/* Sort the runnable steps by priority. Priority is establised
as follows (in order of precedence):
- The global priority of the builds that depend on the
step. This allows admins to bump a build to the front of
the queue.
- The lowest used scheduling share of the jobsets depending
on the step.
- The local priority of the build, as set via the build's
meta.schedulingPriority field. Note that this is not
quite correct: the local priority should only be used to
establish priority between builds in the same jobset, but
here it's used between steps in different jobsets if they
happen to have the same lowest used scheduling share. But
that's not very likely.
- The lowest ID of the builds depending on the step;
i.e. older builds take priority over new ones.
FIXME: O(n lg n); obviously, it would be better to keep a
runnable queue sorted by priority. */
struct StepInfo
{
Step::ptr step;
/* The lowest share used of any jobset depending on this
step. */
double lowestShareUsed = 1e9;
/* Info copied from step->state to ensure that the
comparator is a partial ordering (see MachineInfo). */
int highestGlobalPriority;
int highestLocalPriority;
BuildID lowestBuildID;
StepInfo(Step::ptr step, Step::State & step_) : step(step)
{
for (auto & jobset : step_.jobsets)
lowestShareUsed = std::min(lowestShareUsed, jobset->shareUsed());
highestGlobalPriority = step_.highestGlobalPriority;
highestLocalPriority = step_.highestLocalPriority;
lowestBuildID = step_.lowestBuildID;
}
};
std::vector<StepInfo> runnableSorted;
struct RunnablePerType
{
unsigned int count{0};
std::chrono::seconds waitTime{0};
};
std::unordered_map<std::string, RunnablePerType> runnablePerType;
{
auto runnable_(runnable.lock());
runnableSorted.reserve(runnable_->size());
for (auto i = runnable_->begin(); i != runnable_->end(); ) {
auto step = i->lock();
/* Remove dead steps. */
if (!step) {
i = runnable_->erase(i);
continue;
}
++i;
auto & r = runnablePerType[step->systemType];
r.count++;
/* Skip previously failed steps that aren't ready
to be retried. */
auto step_(step->state.lock());
r.waitTime += std::chrono::duration_cast<std::chrono::seconds>(now - step_->runnableSince);
if (step_->tries > 0 && step_->after > now) {
if (step_->after < sleepUntil)
sleepUntil = step_->after;
continue;
}
runnableSorted.emplace_back(step, *step_);
}
}
sort(runnableSorted.begin(), runnableSorted.end(),
[](const StepInfo & a, const StepInfo & b)
{
return
a.highestGlobalPriority != b.highestGlobalPriority ? a.highestGlobalPriority > b.highestGlobalPriority :
a.lowestShareUsed != b.lowestShareUsed ? a.lowestShareUsed < b.lowestShareUsed :
a.highestLocalPriority != b.highestLocalPriority ? a.highestLocalPriority > b.highestLocalPriority :
a.lowestBuildID < b.lowestBuildID;
});
/* Find a machine with a free slot and find a step to run
on it. Once we find such a pair, we restart the outer
loop because the machine sorting will have changed. */
@@ -245,6 +248,8 @@ system_time State::doDispatch()
if (mi.machine->state->currentJobs >= mi.machine->maxJobs) continue;
for (auto & stepInfo : runnableSorted) {
if (stepInfo.alreadyScheduled) continue;
auto & step(stepInfo.step);
/* Can this machine do this step? */
@@ -271,6 +276,8 @@ system_time State::doDispatch()
r.count--;
}
stepInfo.alreadyScheduled = true;
/* Make a slot reservation and start a thread to
do the build. */
auto builderThread = std::thread(&State::builder, this,

264
src/hydra-queue-runner/hydra-queue-runner.cc
View File

@@ -8,6 +8,9 @@
#include <prometheus/exposer.h>
#include <nlohmann/json.hpp>
#include "signals.hh"
#include "state.hh"
#include "hydra-build-result.hh"
#include "store-api.hh"
@@ -15,20 +18,11 @@
#include "globals.hh"
#include "hydra-config.hh"
#include "json.hh"
#include "s3-binary-cache-store.hh"
#include "shared.hh"
using namespace nix;
namespace nix {
template<> void toJSON<std::atomic<long>>(std::ostream & str, const std::atomic<long> & n) { str << n; }
template<> void toJSON<std::atomic<uint64_t>>(std::ostream & str, const std::atomic<uint64_t> & n) { str << n; }
template<> void toJSON<double>(std::ostream & str, const double & n) { str << n; }
}
using nlohmann::json;
std::string getEnvOrDie(const std::string & key)
@@ -168,9 +162,9 @@ void State::parseMachines(const std::string & contents)
same name. */
auto i = oldMachines.find(machine->sshName);
if (i == oldMachines.end())
printMsg(lvlChatty, format("adding new machine ‘%1%’") % machine->sshName);
printMsg(lvlChatty, "adding new machine ‘%1%’", machine->sshName);
else
printMsg(lvlChatty, format("updating machine ‘%1%’") % machine->sshName);
printMsg(lvlChatty, "updating machine ‘%1%’", machine->sshName);
machine->state = i == oldMachines.end()
? std::make_shared<Machine::State>()
: i->second->state;
@@ -180,7 +174,7 @@ void State::parseMachines(const std::string & contents)
for (auto & m : oldMachines)
if (newMachines.find(m.first) == newMachines.end()) {
if (m.second->enabled)
printMsg(lvlInfo, format("removing machine ‘%1%’") % m.first);
printInfo("removing machine ‘%1%’", m.first);
/* Add a disabled Machine object to make sure stats are
maintained. */
auto machine = std::make_shared<Machine>(*(m.second));
@@ -474,7 +468,7 @@ void State::markSucceededBuild(pqxx::work & txn, Build::ptr build,
product.type,
product.subtype,
product.fileSize ? std::make_optional(*product.fileSize) : std::nullopt,
product.sha256hash ? std::make_optional(product.sha256hash->to_string(Base16, false)) : std::nullopt,
product.sha256hash ? std::make_optional(product.sha256hash->to_string(HashFormat::Base16, false)) : std::nullopt,
product.path,
product.name,
product.defaultPath);
@@ -542,180 +536,167 @@ std::shared_ptr<PathLocks> State::acquireGlobalLock()
void State::dumpStatus(Connection & conn)
{
std::ostringstream out;
time_t now = time(0);
json statusJson = {
{"status", "up"},
{"time", time(0)},
{"uptime", now - startedAt},
{"pid", getpid()},
{"nrQueuedBuilds", builds.lock()->size()},
{"nrActiveSteps", activeSteps_.lock()->size()},
{"nrStepsBuilding", nrStepsBuilding.load()},
#if 0
{"nrStepsCopyingTo", nrStepsCopyingTo.load()},
{"nrStepsCopyingFrom", nrStepsCopyingFrom.load()},
#endif
{"nrUnsupportedSteps", nrUnsupportedSteps.load()},
{"nrBuildsRead", nrBuildsRead.load()},
{"buildReadTimeMs", buildReadTimeMs.load()},
{"buildReadTimeAvgMs", nrBuildsRead == 0 ? 0.0 : (float) buildReadTimeMs / nrBuildsRead},
{"nrBuildsDone", nrBuildsDone.load()},
{"nrStepsStarted", nrStepsStarted.load()},
{"nrStepsDone", nrStepsDone.load()},
{"nrRetries", nrRetries.load()},
{"maxNrRetries", maxNrRetries.load()},
{"nrQueueWakeups", nrQueueWakeups.load()},
{"nrDispatcherWakeups", nrDispatcherWakeups.load()},
{"dispatchTimeMs", dispatchTimeMs.load()},
{"dispatchTimeAvgMs", nrDispatcherWakeups == 0 ? 0.0 : (float) dispatchTimeMs / nrDispatcherWakeups},
{"nrDbConnections", dbPool.count()},
{"nrActiveDbUpdates", nrActiveDbUpdates.load()},
};
{
JSONObject root(out);
time_t now = time(0);
root.attr("status", "up");
root.attr("time", time(0));
root.attr("uptime", now - startedAt);
root.attr("pid", getpid());
{
auto builds_(builds.lock());
root.attr("nrQueuedBuilds", builds_->size());
}
{
auto steps_(steps.lock());
for (auto i = steps_->begin(); i != steps_->end(); )
if (i->second.lock()) ++i; else i = steps_->erase(i);
root.attr("nrUnfinishedSteps", steps_->size());
statusJson["nrUnfinishedSteps"] = steps_->size();
}
{
auto runnable_(runnable.lock());
for (auto i = runnable_->begin(); i != runnable_->end(); )
if (i->lock()) ++i; else i = runnable_->erase(i);
root.attr("nrRunnableSteps", runnable_->size());
statusJson["nrRunnableSteps"] = runnable_->size();
}
root.attr("nrActiveSteps", activeSteps_.lock()->size());
root.attr("nrStepsBuilding", nrStepsBuilding);
#if 0
root.attr("nrStepsCopyingTo", nrStepsCopyingTo);
root.attr("nrStepsCopyingFrom", nrStepsCopyingFrom);
#endif
root.attr("nrUnsupportedSteps", nrUnsupportedSteps);
root.attr("nrBuildsRead", nrBuildsRead);
root.attr("buildReadTimeMs", buildReadTimeMs);
root.attr("buildReadTimeAvgMs", nrBuildsRead == 0 ? 0.0 : (float) buildReadTimeMs / nrBuildsRead);
root.attr("nrBuildsDone", nrBuildsDone);
root.attr("nrStepsStarted", nrStepsStarted);
root.attr("nrStepsDone", nrStepsDone);
root.attr("nrRetries", nrRetries);
root.attr("maxNrRetries", maxNrRetries);
if (nrStepsDone) {
root.attr("totalStepTime", totalStepTime);
root.attr("totalStepBuildTime", totalStepBuildTime);
root.attr("avgStepTime", (float) totalStepTime / nrStepsDone);
root.attr("avgStepBuildTime", (float) totalStepBuildTime / nrStepsDone);
statusJson["totalStepTime"] = totalStepTime.load();
statusJson["totalStepBuildTime"] = totalStepBuildTime.load();
statusJson["avgStepTime"] = (float) totalStepTime / nrStepsDone;
statusJson["avgStepBuildTime"] = (float) totalStepBuildTime / nrStepsDone;
}
root.attr("nrQueueWakeups", nrQueueWakeups);
root.attr("nrDispatcherWakeups", nrDispatcherWakeups);
root.attr("dispatchTimeMs", dispatchTimeMs);
root.attr("dispatchTimeAvgMs", nrDispatcherWakeups == 0 ? 0.0 : (float) dispatchTimeMs / nrDispatcherWakeups);
root.attr("nrDbConnections", dbPool.count());
root.attr("nrActiveDbUpdates", nrActiveDbUpdates);
{
auto nested = root.object("machines");
auto machines_(machines.lock());
for (auto & i : *machines_) {
auto & m(i.second);
auto & s(m->state);
auto nested2 = nested.object(m->sshName);
nested2.attr("enabled", m->enabled);
{
auto list = nested2.list("systemTypes");
for (auto & s : m->systemTypes)
list.elem(s);
}
{
auto list = nested2.list("supportedFeatures");
for (auto & s : m->supportedFeatures)
list.elem(s);
}
{
auto list = nested2.list("mandatoryFeatures");
for (auto & s : m->mandatoryFeatures)
list.elem(s);
}
nested2.attr("currentJobs", s->currentJobs);
if (s->currentJobs == 0)
nested2.attr("idleSince", s->idleSince);
nested2.attr("nrStepsDone", s->nrStepsDone);
if (m->state->nrStepsDone) {
nested2.attr("totalStepTime", s->totalStepTime);
nested2.attr("totalStepBuildTime", s->totalStepBuildTime);
nested2.attr("avgStepTime", (float) s->totalStepTime / s->nrStepsDone);
nested2.attr("avgStepBuildTime", (float) s->totalStepBuildTime / s->nrStepsDone);
}
auto info(m->state->connectInfo.lock());
nested2.attr("disabledUntil", std::chrono::system_clock::to_time_t(info->disabledUntil));
nested2.attr("lastFailure", std::chrono::system_clock::to_time_t(info->lastFailure));
nested2.attr("consecutiveFailures", info->consecutiveFailures);
json machine = {
{"enabled", m->enabled},
{"systemTypes", m->systemTypes},
{"supportedFeatures", m->supportedFeatures},
{"mandatoryFeatures", m->mandatoryFeatures},
{"nrStepsDone", s->nrStepsDone.load()},
{"currentJobs", s->currentJobs.load()},
{"disabledUntil", std::chrono::system_clock::to_time_t(info->disabledUntil)},
{"lastFailure", std::chrono::system_clock::to_time_t(info->lastFailure)},
{"consecutiveFailures", info->consecutiveFailures},
};
if (s->currentJobs == 0)
machine["idleSince"] = s->idleSince.load();
if (m->state->nrStepsDone) {
machine["totalStepTime"] = s->totalStepTime.load();
machine["totalStepBuildTime"] = s->totalStepBuildTime.load();
machine["avgStepTime"] = (float) s->totalStepTime / s->nrStepsDone;
machine["avgStepBuildTime"] = (float) s->totalStepBuildTime / s->nrStepsDone;
}
statusJson["machines"][m->sshName] = machine;
}
}
{
auto nested = root.object("jobsets");
auto jobsets_json = json::object();
auto jobsets_(jobsets.lock());
for (auto & jobset : *jobsets_) {
auto nested2 = nested.object(jobset.first.first + ":" + jobset.first.second);
nested2.attr("shareUsed", jobset.second->shareUsed());
nested2.attr("seconds", jobset.second->getSeconds());
jobsets_json[jobset.first.first + ":" + jobset.first.second] = {
{"shareUsed", jobset.second->shareUsed()},
{"seconds", jobset.second->getSeconds()},
};
}
statusJson["jobsets"] = jobsets_json;
}
{
auto nested = root.object("machineTypes");
auto machineTypesJson = json::object();
auto machineTypes_(machineTypes.lock());
for (auto & i : *machineTypes_) {
auto nested2 = nested.object(i.first);
nested2.attr("runnable", i.second.runnable);
nested2.attr("running", i.second.running);
auto machineTypeJson = machineTypesJson[i.first] = {
{"runnable", i.second.runnable},
{"running", i.second.running},
};
if (i.second.runnable > 0)
nested2.attr("waitTime", i.second.waitTime.count() +
i.second.runnable * (time(0) - lastDispatcherCheck));
machineTypeJson["waitTime"] = i.second.waitTime.count() +
i.second.runnable * (time(0) - lastDispatcherCheck);
if (i.second.running == 0)
nested2.attr("lastActive", std::chrono::system_clock::to_time_t(i.second.lastActive));
machineTypeJson["lastActive"] = std::chrono::system_clock::to_time_t(i.second.lastActive);
}
statusJson["machineTypes"] = machineTypesJson;
}
auto store = getDestStore();
auto nested = root.object("store");
auto & stats = store->getStats();
nested.attr("narInfoRead", stats.narInfoRead);
nested.attr("narInfoReadAverted", stats.narInfoReadAverted);
nested.attr("narInfoMissing", stats.narInfoMissing);
nested.attr("narInfoWrite", stats.narInfoWrite);
nested.attr("narInfoCacheSize", stats.pathInfoCacheSize);
nested.attr("narRead", stats.narRead);
nested.attr("narReadBytes", stats.narReadBytes);
nested.attr("narReadCompressedBytes", stats.narReadCompressedBytes);
nested.attr("narWrite", stats.narWrite);
nested.attr("narWriteAverted", stats.narWriteAverted);
nested.attr("narWriteBytes", stats.narWriteBytes);
nested.attr("narWriteCompressedBytes", stats.narWriteCompressedBytes);
nested.attr("narWriteCompressionTimeMs", stats.narWriteCompressionTimeMs);
nested.attr("narCompressionSavings",
stats.narWriteBytes
? 1.0 - (double) stats.narWriteCompressedBytes / stats.narWriteBytes
: 0.0);
nested.attr("narCompressionSpeed", // MiB/s
statusJson["store"] = {
{"narInfoRead", stats.narInfoRead.load()},
{"narInfoReadAverted", stats.narInfoReadAverted.load()},
{"narInfoMissing", stats.narInfoMissing.load()},
{"narInfoWrite", stats.narInfoWrite.load()},
{"narInfoCacheSize", stats.pathInfoCacheSize.load()},
{"narRead", stats.narRead.load()},
{"narReadBytes", stats.narReadBytes.load()},
{"narReadCompressedBytes", stats.narReadCompressedBytes.load()},
{"narWrite", stats.narWrite.load()},
{"narWriteAverted", stats.narWriteAverted.load()},
{"narWriteBytes", stats.narWriteBytes.load()},
{"narWriteCompressedBytes", stats.narWriteCompressedBytes.load()},
{"narWriteCompressionTimeMs", stats.narWriteCompressionTimeMs.load()},
{"narCompressionSavings",
stats.narWriteBytes
? 1.0 - (double) stats.narWriteCompressedBytes / stats.narWriteBytes
: 0.0},
{"narCompressionSpeed", // MiB/s
stats.narWriteCompressionTimeMs
? (double) stats.narWriteBytes / stats.narWriteCompressionTimeMs * 1000.0 / (1024.0 * 1024.0)
: 0.0);
: 0.0},
};
auto s3Store = dynamic_cast<S3BinaryCacheStore *>(&*store);
if (s3Store) {
auto nested2 = nested.object("s3");
auto & s3Stats = s3Store->getS3Stats();
nested2.attr("put", s3Stats.put);
nested2.attr("putBytes", s3Stats.putBytes);
nested2.attr("putTimeMs", s3Stats.putTimeMs);
nested2.attr("putSpeed",
s3Stats.putTimeMs
? (double) s3Stats.putBytes / s3Stats.putTimeMs * 1000.0 / (1024.0 * 1024.0)
: 0.0);
nested2.attr("get", s3Stats.get);
nested2.attr("getBytes", s3Stats.getBytes);
nested2.attr("getTimeMs", s3Stats.getTimeMs);
nested2.attr("getSpeed",
s3Stats.getTimeMs
? (double) s3Stats.getBytes / s3Stats.getTimeMs * 1000.0 / (1024.0 * 1024.0)
: 0.0);
nested2.attr("head", s3Stats.head);
nested2.attr("costDollarApprox",
(s3Stats.get + s3Stats.head) / 10000.0 * 0.004
+ s3Stats.put / 1000.0 * 0.005 +
+ s3Stats.getBytes / (1024.0 * 1024.0 * 1024.0) * 0.09);
auto jsonS3 = statusJson["s3"] = {
{"put", s3Stats.put.load()},
{"putBytes", s3Stats.putBytes.load()},
{"putTimeMs", s3Stats.putTimeMs.load()},
{"putSpeed",
s3Stats.putTimeMs
? (double) s3Stats.putBytes / s3Stats.putTimeMs * 1000.0 / (1024.0 * 1024.0)
: 0.0},
{"get", s3Stats.get.load()},
{"getBytes", s3Stats.getBytes.load()},
{"getTimeMs", s3Stats.getTimeMs.load()},
{"getSpeed",
s3Stats.getTimeMs
? (double) s3Stats.getBytes / s3Stats.getTimeMs * 1000.0 / (1024.0 * 1024.0)
: 0.0},
{"head", s3Stats.head.load()},
{"costDollarApprox",
(s3Stats.get + s3Stats.head) / 10000.0 * 0.004
+ s3Stats.put / 1000.0 * 0.005 +
+ s3Stats.getBytes / (1024.0 * 1024.0 * 1024.0) * 0.09},
};
}
}
@@ -724,7 +705,7 @@ void State::dumpStatus(Connection & conn)
pqxx::work txn(conn);
// FIXME: use PostgreSQL 9.5 upsert.
txn.exec("delete from SystemStatus where what = 'queue-runner'");
txn.exec_params0("insert into SystemStatus values ('queue-runner', $1)", out.str());
txn.exec_params0("insert into SystemStatus values ('queue-runner', $1)", statusJson.dump());
txn.exec("notify status_dumped");
txn.commit();
}
@@ -949,7 +930,6 @@ int main(int argc, char * * argv)
});
settings.verboseBuild = true;
settings.lockCPU = false;
State state{metricsAddrOpt};
if (status)

12
src/hydra-queue-runner/nar-extractor.cc
View File

@@ -24,13 +24,13 @@ struct Extractor : ParseSink
void createDirectory(const Path & path) override
{
members.insert_or_assign(prefix + path, NarMemberData { .type = FSAccessor::Type::tDirectory });
members.insert_or_assign(prefix + path, NarMemberData { .type = SourceAccessor::Type::tDirectory });
}
void createRegularFile(const Path & path) override
{
curMember = &members.insert_or_assign(prefix + path, NarMemberData {
.type = FSAccessor::Type::tRegular,
.type = SourceAccessor::Type::tRegular,
.fileSize = 0,
.contents = filesToKeep.count(path) ? std::optional("") : std::nullopt,
}).first->second;
@@ -66,8 +66,14 @@ struct Extractor : ParseSink
void createSymlink(const Path & path, const std::string & target) override
{
members.insert_or_assign(prefix + path, NarMemberData { .type = FSAccessor::Type::tSymlink });
members.insert_or_assign(prefix + path, NarMemberData { .type = SourceAccessor::Type::tSymlink });
}
void isExecutable() override
{ }
void closeRegularFile() override
{ }
};

4
src/hydra-queue-runner/nar-extractor.hh
View File

@@ -1,13 +1,13 @@
#pragma once
#include "fs-accessor.hh"
#include "source-accessor.hh"
#include "types.hh"
#include "serialise.hh"
#include "hash.hh"
struct NarMemberData
{
nix::FSAccessor::Type type;
nix::SourceAccessor::Type type;
std::optional<uint64_t> fileSize;
std::optional<std::string> contents;
std::optional<nix::Hash> sha256;

18
src/hydra-queue-runner/queue-monitor.cc
View File

@@ -13,7 +13,7 @@ void State::queueMonitor()
try {
queueMonitorLoop();
} catch (std::exception & e) {
printMsg(lvlError, format("queue monitor: %1%") % e.what());
printError("queue monitor: %s", e.what());
sleep(10); // probably a DB problem, so don't retry right away
}
}
@@ -142,13 +142,13 @@ bool State::getQueuedBuilds(Connection & conn,
createBuild = [&](Build::ptr build) {
prom.queue_build_loads.Increment();
printMsg(lvlTalkative, format("loading build %1% (%2%)") % build->id % build->fullJobName());
printMsg(lvlTalkative, "loading build %1% (%2%)", build->id, build->fullJobName());
nrAdded++;
newBuildsByID.erase(build->id);
if (!localStore->isValidPath(build->drvPath)) {
/* Derivation has been GC'ed prematurely. */
printMsg(lvlError, format("aborting GC'ed build %1%") % build->id);
printError("aborting GC'ed build %1%", build->id);
if (!build->finishedInDB) {
auto mc = startDbUpdate();
pqxx::work txn(conn);
@@ -302,7 +302,7 @@ bool State::getQueuedBuilds(Connection & conn,
/* Add the new runnable build steps to ‘runnable’ and wake up
the builder threads. */
printMsg(lvlChatty, format("got %1% new runnable steps from %2% new builds") % newRunnable.size() % nrAdded);
printMsg(lvlChatty, "got %1% new runnable steps from %2% new builds", newRunnable.size(), nrAdded);
for (auto & r : newRunnable)
makeRunnable(r);
@@ -315,7 +315,7 @@ bool State::getQueuedBuilds(Connection & conn,
if (std::chrono::system_clock::now() > start + std::chrono::seconds(600)) {
prom.queue_checks_early_exits.Increment();
break;
}
}
}
prom.queue_checks_finished.Increment();
@@ -358,13 +358,13 @@ void State::processQueueChange(Connection & conn)
for (auto i = builds_->begin(); i != builds_->end(); ) {
auto b = currentIds.find(i->first);
if (b == currentIds.end()) {
printMsg(lvlInfo, format("discarding cancelled build %1%") % i->first);
printInfo("discarding cancelled build %1%", i->first);
i = builds_->erase(i);
// FIXME: ideally we would interrupt active build steps here.
continue;
}
if (i->second->globalPriority < b->second) {
printMsg(lvlInfo, format("priority of build %1% increased") % i->first);
printInfo("priority of build %1% increased", i->first);
i->second->globalPriority = b->second;
i->second->propagatePriorities();
}
@@ -561,7 +561,7 @@ Step::ptr State::createStep(ref<Store> destStore,
printMsg(lvlDebug, "creating build step ‘%1%’", localStore->printStorePath(drvPath));
/* Create steps for the dependencies. */
for (auto & i : step->drv->inputDrvs) {
for (auto & i : step->drv->inputDrvs.map) {
auto dep = createStep(destStore, conn, build, i.first, 0, step, finishedDrvs, newSteps, newRunnable);
if (dep) {
auto step_(step->state.lock());
@@ -654,7 +654,7 @@ BuildOutput State::getBuildOutputCached(Connection & conn, nix::ref<nix::Store>
if (r.empty()) continue;
BuildID id = r[0][0].as<BuildID>();
printMsg(lvlInfo, format("reusing build %d") % id);
printInfo("reusing build %d", id);
BuildOutput res;
res.failed = r[0][1].as<int>() == bsFailedWithOutput;

4
src/lib/Hydra/Controller/API.pm
View File

@@ -216,8 +216,8 @@ sub scmdiff : Path('/api/scmdiff') Args(0) {
} elsif ($type eq "git") {
my $clonePath = getSCMCacheDir . "/git/" . sha256_hex($uri);
die if ! -d $clonePath;
$diff .= `(cd $clonePath; git log $rev1..$rev2)`;
$diff .= `(cd $clonePath; git diff $rev1..$rev2)`;
$diff .= `(cd $clonePath; git --git-dir .git log $rev1..$rev2)`;
$diff .= `(cd $clonePath; git --git-dir .git diff $rev1..$rev2)`;
}
$c->stash->{'plain'} = { data => (scalar $diff) || " " };

14
src/lib/Hydra/Controller/Build.pm
View File

@@ -238,9 +238,17 @@ sub serveFile {
"store", "cat", "--store", getStoreUri(), "$path"]) };
# Detect MIME type.
state $magic = File::LibMagic->new(follow_symlinks => 1);
my $info = $magic->info_from_filename($path);
my $type = $info->{mime_with_encoding};
my $type = "text/plain";
if ($path =~ /.*\.(\S{1,})$/xms) {
my $ext = $1;
my $mimeTypes = MIME::Types->new(only_complete => 1);
my $t = $mimeTypes->mimeTypeOf($ext);
$type = ref $t ? $t->type : $t if $t;
} else {
state $magic = File::LibMagic->new(follow_symlinks => 1);
my $info = $magic->info_from_filename($path);
$type = $info->{mime_with_encoding};
}
$c->response->content_type($type);
$c->forward('Hydra::View::Plain');
}

2
src/lib/Hydra/Controller/User.pm
View File

@@ -463,7 +463,7 @@ sub my_jobs_tab :Chained('dashboard_base') :PathPart('my-jobs-tab') :Args(0) {
, "jobset.enabled" => 1
},
{ order_by => ["project", "jobset", "job"]
, join => ["project", "jobset"]
, join => {"jobset" => "project"}
})];
}

2
src/lib/Hydra/Schema/Result/Users.pm
View File

@@ -216,7 +216,7 @@ sub json_hint {
sub _authenticator() {
my $authenticator = Crypt::Passphrase->new(
encoder => 'Argon2',
encoder => { module => 'Argon2', output_size => 16 },
validators => [
(sub {
my ($password, $hash) = @_;

1
src/libhydra/db.hh
View File

@@ -2,6 +2,7 @@
#include <pqxx/pqxx>
#include "environment-variables.hh"
#include "util.hh"

1
src/libhydra/hydra-config.hh
View File

@@ -2,6 +2,7 @@
#include <map>
#include "file-system.hh"
#include "util.hh"
struct HydraConfig

5
src/root/auth.tt
View File

@@ -82,7 +82,7 @@
function onGoogleSignIn(googleUser) {
requestJSON({
url: "[% c.uri_for('/google-login') %]",
data: "id_token=" + googleUser.getAuthResponse().id_token,
data: "id_token=" + googleUser.credential,
type: 'POST',
success: function(data) {
window.location.reload();
@@ -91,9 +91,6 @@
return false;
};
$("#google-signin").click(function() {
$(".g-signin2:first-child > div").click();
});
</script>
[% END %]

2
src/root/common.tt
View File

@@ -374,7 +374,7 @@ BLOCK renderInputDiff; %]
[% ELSIF bi1.uri == bi2.uri && bi1.revision != bi2.revision %]
[% IF bi1.type == "git" %]
<tr><td>
<b>[% bi1.name %]</b></td><td><tt>[% INCLUDE renderDiffUri contents=(bi1.revision.substr(0, 6) _ ' to ' _ bi2.revision.substr(0, 6)) %]</tt>
<b>[% bi1.name %]</b></td><td><tt>[% INCLUDE renderDiffUri contents=(bi1.revision.substr(0, 8) _ ' to ' _ bi2.revision.substr(0, 8)) %]</tt>
</td></tr>
[% ELSE %]
<tr><td>

6
src/root/topbar.tt
View File

@@ -133,8 +133,10 @@
[% ELSE %]
[% WRAPPER makeSubMenu title="Sign in" id="sign-in-menu" align="right" %]
[% IF c.config.enable_google_login %]
<div style="display: none" class="g-signin2" data-onsuccess="onGoogleSignIn" data-theme="dark"></div>
<a class="dropdown-item" href="#" id="google-signin">Sign in with Google</a>
<script src="https://accounts.google.com/gsi/client" async defer></script>
<div id="g_id_onload" data-client_id="[% c.config.google_client_id %]" data-callback="onGoogleSignIn">
</div>
<div class="g_id_signin" data-type="standard"></div>
<div class="dropdown-divider"></div>
[% END %]
[% IF c.config.github_client_id %]

3
src/sql/upgrade-83.sql Normal file
View File

@@ -0,0 +1,3 @@
-- This index was introduced in a migration but was never recorded in
-- hydra.sql (the source of truth), which is why `if exists` is required.
drop index if exists IndexBuildOutputsOnPath;