1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-24 03:33:20 +01:00
llvm-mirror/lib/Support/Unix/Threading.inc
Dimitry Andric 4829f7d03a Implement computeHostNumHardwareThreads() for FreeBSD
This retrieves CPU affinity via FreeBSD's cpuset(2) API, and makes LLVM
respect affinity settings configured by the user via the cpuset(1)
command.

In particular, this allows to reduce the number of threads used on
machines with high core counts, which can interact badly with
parallelized build systems. This is particularly noticable with lld,
which spawns lots of threads even for linking e.g. hello_world!

This fix is related to PR48193, but does not adress the more fundamental
problem, which is that LLVM by default grabs as many CPUs and/or threads
as possible.

Reviewed By: MaskRay

Differential Revision: https://reviews.llvm.org/D92271
2020-11-29 00:49:39 +01:00

312 lines
9.8 KiB
C++

//===- Unix/Threading.inc - Unix Threading Implementation ----- -*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file provides the Unix specific implementation of Threading functions.
//
//===----------------------------------------------------------------------===//
#include "Unix.h"
#include "llvm/ADT/ScopeExit.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/ADT/Twine.h"
#if defined(__APPLE__)
#include <mach/mach_init.h>
#include <mach/mach_port.h>
#endif
#include <pthread.h>
#if defined(__FreeBSD__) || defined(__OpenBSD__)
#include <pthread_np.h> // For pthread_getthreadid_np() / pthread_set_name_np()
#endif
#if defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
#include <errno.h>
#include <sys/cpuset.h>
#include <sys/sysctl.h>
#include <sys/user.h>
#include <unistd.h>
#endif
#if defined(__NetBSD__)
#include <lwp.h> // For _lwp_self()
#endif
#if defined(__OpenBSD__)
#include <unistd.h> // For getthrid()
#endif
#if defined(__linux__)
#include <sched.h> // For sched_getaffinity
#include <sys/syscall.h> // For syscall codes
#include <unistd.h> // For syscall()
#endif
static void *threadFuncSync(void *Arg) {
SyncThreadInfo *TI = static_cast<SyncThreadInfo *>(Arg);
TI->UserFn(TI->UserData);
return nullptr;
}
static void *threadFuncAsync(void *Arg) {
std::unique_ptr<AsyncThreadInfo> Info(static_cast<AsyncThreadInfo *>(Arg));
(*Info)();
return nullptr;
}
static void
llvm_execute_on_thread_impl(void *(*ThreadFunc)(void *), void *Arg,
llvm::Optional<unsigned> StackSizeInBytes,
JoiningPolicy JP) {
int errnum;
// Construct the attributes object.
pthread_attr_t Attr;
if ((errnum = ::pthread_attr_init(&Attr)) != 0) {
ReportErrnumFatal("pthread_attr_init failed", errnum);
}
auto AttrGuard = llvm::make_scope_exit([&] {
if ((errnum = ::pthread_attr_destroy(&Attr)) != 0) {
ReportErrnumFatal("pthread_attr_destroy failed", errnum);
}
});
// Set the requested stack size, if given.
if (StackSizeInBytes) {
if ((errnum = ::pthread_attr_setstacksize(&Attr, *StackSizeInBytes)) != 0) {
ReportErrnumFatal("pthread_attr_setstacksize failed", errnum);
}
}
// Construct and execute the thread.
pthread_t Thread;
if ((errnum = ::pthread_create(&Thread, &Attr, ThreadFunc, Arg)) != 0)
ReportErrnumFatal("pthread_create failed", errnum);
if (JP == JoiningPolicy::Join) {
// Wait for the thread
if ((errnum = ::pthread_join(Thread, nullptr)) != 0) {
ReportErrnumFatal("pthread_join failed", errnum);
}
} else if (JP == JoiningPolicy::Detach) {
if ((errnum = ::pthread_detach(Thread)) != 0) {
ReportErrnumFatal("pthread_detach failed", errnum);
}
}
}
uint64_t llvm::get_threadid() {
#if defined(__APPLE__)
// Calling "mach_thread_self()" bumps the reference count on the thread
// port, so we need to deallocate it. mach_task_self() doesn't bump the ref
// count.
thread_port_t Self = mach_thread_self();
mach_port_deallocate(mach_task_self(), Self);
return Self;
#elif defined(__FreeBSD__)
return uint64_t(pthread_getthreadid_np());
#elif defined(__NetBSD__)
return uint64_t(_lwp_self());
#elif defined(__OpenBSD__)
return uint64_t(getthrid());
#elif defined(__ANDROID__)
return uint64_t(gettid());
#elif defined(__linux__)
return uint64_t(syscall(SYS_gettid));
#else
return uint64_t(pthread_self());
#endif
}
static constexpr uint32_t get_max_thread_name_length_impl() {
#if defined(__NetBSD__)
return PTHREAD_MAX_NAMELEN_NP;
#elif defined(__APPLE__)
return 64;
#elif defined(__linux__)
#if HAVE_PTHREAD_SETNAME_NP
return 16;
#else
return 0;
#endif
#elif defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
return 16;
#elif defined(__OpenBSD__)
return 32;
#else
return 0;
#endif
}
uint32_t llvm::get_max_thread_name_length() {
return get_max_thread_name_length_impl();
}
void llvm::set_thread_name(const Twine &Name) {
// Make sure the input is null terminated.
SmallString<64> Storage;
StringRef NameStr = Name.toNullTerminatedStringRef(Storage);
// Truncate from the beginning, not the end, if the specified name is too
// long. For one, this ensures that the resulting string is still null
// terminated, but additionally the end of a long thread name will usually
// be more unique than the beginning, since a common pattern is for similar
// threads to share a common prefix.
// Note that the name length includes the null terminator.
if (get_max_thread_name_length() > 0)
NameStr = NameStr.take_back(get_max_thread_name_length() - 1);
(void)NameStr;
#if defined(__linux__)
#if (defined(__GLIBC__) && defined(_GNU_SOURCE)) || defined(__ANDROID__)
#if HAVE_PTHREAD_SETNAME_NP
::pthread_setname_np(::pthread_self(), NameStr.data());
#endif
#endif
#elif defined(__FreeBSD__) || defined(__OpenBSD__)
::pthread_set_name_np(::pthread_self(), NameStr.data());
#elif defined(__NetBSD__)
::pthread_setname_np(::pthread_self(), "%s",
const_cast<char *>(NameStr.data()));
#elif defined(__APPLE__)
::pthread_setname_np(NameStr.data());
#endif
}
void llvm::get_thread_name(SmallVectorImpl<char> &Name) {
Name.clear();
#if defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
int pid = ::getpid();
uint64_t tid = get_threadid();
struct kinfo_proc *kp = nullptr, *nkp;
size_t len = 0;
int error;
int ctl[4] = { CTL_KERN, KERN_PROC, KERN_PROC_PID | KERN_PROC_INC_THREAD,
(int)pid };
while (1) {
error = sysctl(ctl, 4, kp, &len, nullptr, 0);
if (kp == nullptr || (error != 0 && errno == ENOMEM)) {
// Add extra space in case threads are added before next call.
len += sizeof(*kp) + len / 10;
nkp = (struct kinfo_proc *)::realloc(kp, len);
if (nkp == nullptr) {
free(kp);
return;
}
kp = nkp;
continue;
}
if (error != 0)
len = 0;
break;
}
for (size_t i = 0; i < len / sizeof(*kp); i++) {
if (kp[i].ki_tid == (lwpid_t)tid) {
Name.append(kp[i].ki_tdname, kp[i].ki_tdname + strlen(kp[i].ki_tdname));
break;
}
}
free(kp);
return;
#elif defined(__NetBSD__)
constexpr uint32_t len = get_max_thread_name_length_impl();
char buf[len];
::pthread_getname_np(::pthread_self(), buf, len);
Name.append(buf, buf + strlen(buf));
#elif defined(__OpenBSD__)
constexpr uint32_t len = get_max_thread_name_length_impl();
char buf[len];
::pthread_get_name_np(::pthread_self(), buf, len);
Name.append(buf, buf + strlen(buf));
#elif defined(__linux__)
#if HAVE_PTHREAD_GETNAME_NP
constexpr uint32_t len = get_max_thread_name_length_impl();
char Buffer[len] = {'\0'}; // FIXME: working around MSan false positive.
if (0 == ::pthread_getname_np(::pthread_self(), Buffer, len))
Name.append(Buffer, Buffer + strlen(Buffer));
#endif
#endif
}
SetThreadPriorityResult llvm::set_thread_priority(ThreadPriority Priority) {
#if defined(__linux__) && defined(SCHED_IDLE)
// Some *really* old glibcs are missing SCHED_IDLE.
// http://man7.org/linux/man-pages/man3/pthread_setschedparam.3.html
// http://man7.org/linux/man-pages/man2/sched_setscheduler.2.html
sched_param priority;
// For each of the above policies, param->sched_priority must be 0.
priority.sched_priority = 0;
// SCHED_IDLE for running very low priority background jobs.
// SCHED_OTHER the standard round-robin time-sharing policy;
return !pthread_setschedparam(
pthread_self(),
Priority == ThreadPriority::Background ? SCHED_IDLE : SCHED_OTHER,
&priority)
? SetThreadPriorityResult::SUCCESS
: SetThreadPriorityResult::FAILURE;
#elif defined(__APPLE__)
// https://developer.apple.com/library/archive/documentation/System/Conceptual/ManPages_iPhoneOS/man2/getpriority.2.html
// When setting a thread into background state the scheduling priority is set
// to lowest value, disk and network IO are throttled. Network IO will be
// throttled for any sockets the thread opens after going into background
// state. Any previously opened sockets are not affected.
// https://developer.apple.com/library/archive/documentation/System/Conceptual/ManPages_iPhoneOS/man3/getiopolicy_np.3.html
// I/Os with THROTTLE policy are called THROTTLE I/Os. If a THROTTLE I/O
// request occurs within a small time window (usually a fraction of a second)
// of another NORMAL I/O request, the thread that issues the THROTTLE I/O is
// forced to sleep for a certain interval. This slows down the thread that
// issues the THROTTLE I/O so that NORMAL I/Os can utilize most of the disk
// I/O bandwidth.
return !setpriority(PRIO_DARWIN_THREAD, 0,
Priority == ThreadPriority::Background ? PRIO_DARWIN_BG
: 0)
? SetThreadPriorityResult::SUCCESS
: SetThreadPriorityResult::FAILURE;
#endif
return SetThreadPriorityResult::FAILURE;
}
#include <thread>
int computeHostNumHardwareThreads() {
#if defined(__FreeBSD__)
cpuset_t mask;
CPU_ZERO(&mask);
if (cpuset_getaffinity(CPU_LEVEL_WHICH, CPU_WHICH_TID, -1, sizeof(mask),
&mask) == 0)
return CPU_COUNT(&mask);
#elif defined(__linux__)
cpu_set_t Set;
if (sched_getaffinity(0, sizeof(Set), &Set) == 0)
return CPU_COUNT(&Set);
#endif
// Guard against std::thread::hardware_concurrency() returning 0.
if (unsigned Val = std::thread::hardware_concurrency())
return Val;
return 1;
}
void llvm::ThreadPoolStrategy::apply_thread_strategy(
unsigned ThreadPoolNum) const {}
llvm::BitVector llvm::get_thread_affinity_mask() {
// FIXME: Implement
llvm_unreachable("Not implemented!");
}
unsigned llvm::get_cpus() { return 1; }