mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-22 18:54:02 +01:00
Improve module.pcm lock file performance on machines with high core counts
Summary: When building a large Xcode project with multiple module dependencies, and mixed Objective-C & Swift, I observed a large number of clang processes stalling at zero CPU for 30+ seconds throughout the build. This was especially prevalent on my 18-core iMac Pro. After some sampling, the major cause appears to be the lock file implementation for precompiled modules in the module cache. When the lock is heavily contended by multiple clang processes, the exponential backoff runs in lockstep, with some of the processes sleeping for 30+ seconds in order to acquire the file lock. In the attached patch, I implemented a more aggressive polling mechanism that limits the sleep interval to a max of 500ms, and randomizes the wait time. I preserved a limited form of exponential backoff. I also updated the code to use cross-platform timing, thread sleep, and random number capabilities available in C++11. On iMac Pro (2.3 GHz Intel Xeon W, 18 core): Xcode 11.1 bundled clang: 502.2 seconds (average of 5 runs) Custom clang build with LockFileManager patch applied: 276.6 seconds (average of 5 runs) This is a 1.82x speedup for this use case. On MacBook Pro (4 core 3.1GHz Intel i7): Xcode 11.1 bundled clang: 539.4 seconds (average of 2 runs) Custom clang build with LockFileManager patch applied: 509.5 seconds (average of 2 runs) As expected, machines with fewer cores benefit less from this change. ``` Call graph: 2992 Thread_393602 DispatchQueue_1: com.apple.main-thread (serial) 2992 start (in libdyld.dylib) + 1 [0x7fff6a1683d5] 2992 main (in clang) + 297 [0x1097a1059] 2992 driver_main(int, char const**) (in clang) + 2803 [0x1097a5513] 2992 cc1_main(llvm::ArrayRef<char const*>, char const*, void*) (in clang) + 1608 [0x1097a7cc8] 2992 clang::ExecuteCompilerInvocation(clang::CompilerInstance*) (in clang) + 3299 [0x1097dace3] 2992 clang::CompilerInstance::ExecuteAction(clang::FrontendAction&) (in clang) + 509 [0x1097dcc1d] 2992 clang::FrontendAction::Execute() (in clang) + 42 [0x109818b3a] 2992 clang::ParseAST(clang::Sema&, bool, bool) (in clang) + 185 [0x10981b369] 2992 clang::Parser::ParseFirstTopLevelDecl(clang::OpaquePtr<clang::DeclGroupRef>&) (in clang) + 37 [0x10983e9b5] 2992 clang::Parser::ParseTopLevelDecl(clang::OpaquePtr<clang::DeclGroupRef>&) (in clang) + 141 [0x10983ecfd] 2992 clang::Parser::ParseExternalDeclaration(clang::Parser::ParsedAttributesWithRange&, clang::ParsingDeclSpec*) (in clang) + 695 [0x10983f3b7] 2992 clang::Parser::ParseObjCAtDirectives(clang::Parser::ParsedAttributesWithRange&) (in clang) + 637 [0x10a9be9bd] 2992 clang::Parser::ParseModuleImport(clang::SourceLocation) (in clang) + 170 [0x10c4841ba] 2992 clang::Parser::ParseModuleName(clang::SourceLocation, llvm::SmallVectorImpl<std::__1::pair<clang::IdentifierInfo*, clang::SourceLocation> >&, bool) (in clang) + 503 [0x10c485267] 2992 clang::Preprocessor::Lex(clang::Token&) (in clang) + 316 [0x1098285cc] 2992 clang::Preprocessor::LexAfterModuleImport(clang::Token&) (in clang) + 690 [0x10cc7af62] 2992 clang::CompilerInstance::loadModule(clang::SourceLocation, llvm::ArrayRef<std::__1::pair<clang::IdentifierInfo*, clang::SourceLocation> >, clang::Module::NameVisibilityKind, bool) (in clang) + 7989 [0x10bba6535] 2992 compileAndLoadModule(clang::CompilerInstance&, clang::SourceLocation, clang::SourceLocation, clang::Module*, llvm::StringRef) (in clang) + 296 [0x10bba8318] 2992 llvm::LockFileManager::waitForUnlock() (in clang) + 91 [0x10b6953ab] 2992 nanosleep (in libsystem_c.dylib) + 199 [0x7fff6a22c914] 2992 __semwait_signal (in libsystem_kernel.dylib) + 10 [0x7fff6a2a0f32] ``` Differential Revision: https://reviews.llvm.org/D69575
This commit is contained in:
parent
1e282655bf
commit
d31a976026
@ -78,8 +78,8 @@ public:
|
|||||||
|
|
||||||
/// For a shared lock, wait until the owner releases the lock.
|
/// For a shared lock, wait until the owner releases the lock.
|
||||||
/// Total timeout for the file to appear is ~1.5 minutes.
|
/// Total timeout for the file to appear is ~1.5 minutes.
|
||||||
/// \param MaxSeconds the maximum wait time per iteration in seconds.
|
/// \param MaxSeconds the maximum total wait time in seconds.
|
||||||
WaitForUnlockResult waitForUnlock(const unsigned MaxSeconds = 40);
|
WaitForUnlockResult waitForUnlock(const unsigned MaxSeconds = 90);
|
||||||
|
|
||||||
/// Remove the lock file. This may delete a different lock file than
|
/// Remove the lock file. This may delete a different lock file than
|
||||||
/// the one previously read if there is a race.
|
/// the one previously read if there is a race.
|
||||||
|
@ -17,12 +17,16 @@
|
|||||||
#include "llvm/Support/Signals.h"
|
#include "llvm/Support/Signals.h"
|
||||||
#include "llvm/Support/raw_ostream.h"
|
#include "llvm/Support/raw_ostream.h"
|
||||||
#include <cerrno>
|
#include <cerrno>
|
||||||
|
#include <chrono>
|
||||||
#include <ctime>
|
#include <ctime>
|
||||||
#include <memory>
|
#include <memory>
|
||||||
|
#include <random>
|
||||||
#include <sys/stat.h>
|
#include <sys/stat.h>
|
||||||
#include <sys/types.h>
|
#include <sys/types.h>
|
||||||
#include <system_error>
|
#include <system_error>
|
||||||
|
#include <thread>
|
||||||
#include <tuple>
|
#include <tuple>
|
||||||
|
|
||||||
#ifdef _WIN32
|
#ifdef _WIN32
|
||||||
#include <windows.h>
|
#include <windows.h>
|
||||||
#endif
|
#endif
|
||||||
@ -295,23 +299,29 @@ LockFileManager::waitForUnlock(const unsigned MaxSeconds) {
|
|||||||
if (getState() != LFS_Shared)
|
if (getState() != LFS_Shared)
|
||||||
return Res_Success;
|
return Res_Success;
|
||||||
|
|
||||||
#ifdef _WIN32
|
// Since we don't yet have an event-based method to wait for the lock file,
|
||||||
unsigned long Interval = 1;
|
// implement randomized exponential backoff, similar to Ethernet collision
|
||||||
#else
|
// algorithm. This improves performance on machines with high core counts
|
||||||
struct timespec Interval;
|
// when the file lock is heavily contended by multiple clang processes
|
||||||
Interval.tv_sec = 0;
|
const unsigned long MinWaitDurationMS = 10;
|
||||||
Interval.tv_nsec = 1000000;
|
const unsigned long MaxWaitMultiplier = 50; // 500ms max wait
|
||||||
#endif
|
unsigned long WaitMultiplier = 1;
|
||||||
|
unsigned long ElapsedTimeSeconds = 0;
|
||||||
|
|
||||||
|
std::random_device Device;
|
||||||
|
std::default_random_engine Engine(Device());
|
||||||
|
|
||||||
|
auto StartTime = std::chrono::steady_clock::now();
|
||||||
|
|
||||||
do {
|
do {
|
||||||
|
// FIXME: implement event-based waiting
|
||||||
|
|
||||||
// Sleep for the designated interval, to allow the owning process time to
|
// Sleep for the designated interval, to allow the owning process time to
|
||||||
// finish up and remove the lock file.
|
// finish up and remove the lock file.
|
||||||
// FIXME: Should we hook in to system APIs to get a notification when the
|
std::uniform_int_distribution<unsigned long> Distribution(1,
|
||||||
// lock file is deleted?
|
WaitMultiplier);
|
||||||
#ifdef _WIN32
|
unsigned long WaitDurationMS = MinWaitDurationMS * Distribution(Engine);
|
||||||
Sleep(Interval);
|
std::this_thread::sleep_for(std::chrono::milliseconds(WaitDurationMS));
|
||||||
#else
|
|
||||||
nanosleep(&Interval, nullptr);
|
|
||||||
#endif
|
|
||||||
|
|
||||||
if (sys::fs::access(LockFileName.c_str(), sys::fs::AccessMode::Exist) ==
|
if (sys::fs::access(LockFileName.c_str(), sys::fs::AccessMode::Exist) ==
|
||||||
errc::no_such_file_or_directory) {
|
errc::no_such_file_or_directory) {
|
||||||
@ -325,24 +335,16 @@ LockFileManager::waitForUnlock(const unsigned MaxSeconds) {
|
|||||||
if (!processStillExecuting((*Owner).first, (*Owner).second))
|
if (!processStillExecuting((*Owner).first, (*Owner).second))
|
||||||
return Res_OwnerDied;
|
return Res_OwnerDied;
|
||||||
|
|
||||||
// Exponentially increase the time we wait for the lock to be removed.
|
WaitMultiplier *= 2;
|
||||||
#ifdef _WIN32
|
if (WaitMultiplier > MaxWaitMultiplier) {
|
||||||
Interval *= 2;
|
WaitMultiplier = MaxWaitMultiplier;
|
||||||
#else
|
|
||||||
Interval.tv_sec *= 2;
|
|
||||||
Interval.tv_nsec *= 2;
|
|
||||||
if (Interval.tv_nsec >= 1000000000) {
|
|
||||||
++Interval.tv_sec;
|
|
||||||
Interval.tv_nsec -= 1000000000;
|
|
||||||
}
|
}
|
||||||
#endif
|
|
||||||
} while (
|
ElapsedTimeSeconds = std::chrono::duration_cast<std::chrono::seconds>(
|
||||||
#ifdef _WIN32
|
std::chrono::steady_clock::now() - StartTime)
|
||||||
Interval < MaxSeconds * 1000
|
.count();
|
||||||
#else
|
|
||||||
Interval.tv_sec < (time_t)MaxSeconds
|
} while (ElapsedTimeSeconds < MaxSeconds);
|
||||||
#endif
|
|
||||||
);
|
|
||||||
|
|
||||||
// Give up.
|
// Give up.
|
||||||
return Res_Timeout;
|
return Res_Timeout;
|
||||||
|
Loading…
Reference in New Issue
Block a user