Files
Jungfraujoch/common/ThreadAffinity.cpp
leonarski_f 84228bf8be
Build Packages / Create release (push) Successful in 24s
Build Packages / build:viewer:macos-arm64:nocuda (push) Successful in 3m29s
Build Packages / build:rugnux:macos-arm64:nocuda (push) Successful in 2m43s
Build Packages / build:rugnux:linux-aarch64:cuda (push) Successful in 8m27s
Build Packages / build:rugnux:linux-x86_64:cuda (push) Successful in 9m53s
Build Packages / build:viewer:linux-x86_64:nocuda (push) Successful in 9m58s
Build Packages / build:viewer:linux-x86_64:cuda (push) Successful in 11m22s
Build Packages / build:jfjoch:rocky8:nocuda (push) Successful in 13m39s
Build Packages / build:viewer:windows-x86_64:nocuda (push) Successful in 18m37s
Build Packages / build:jfjoch:rocky9:nocuda (push) Successful in 16m32s
Build Packages / build:viewer:windows-x86_64:cuda (push) Successful in 24m11s
Build Packages / HDF5 consumer tests (DIALS, XDS) (push) Successful in 25m30s
Build Packages / build:jfjoch:ubuntu2404:nocuda (push) Successful in 19m3s
Build Packages / build:jfjoch:ubuntu2204:nocuda (push) Successful in 20m23s
Build Packages / build:jfjoch:rocky8:cuda-sls9 (push) Successful in 19m41s
Build Packages / Generate python client (push) Successful in 50s
Build Packages / Build documentation (push) Successful in 1m16s
Build Packages / build:jfjoch:rocky9:cuda-sls9 (push) Successful in 21m0s
Build Packages / build:jfjoch:rocky8:cuda (push) Successful in 18m38s
Build Packages / build:rugnux:windows-x86_64:cuda (push) Successful in 14m33s
Build Packages / build:jfjoch:rocky9:cuda (push) Successful in 17m55s
Build Packages / build:jfjoch:ubuntu2204:cuda (push) Successful in 20m50s
Build Packages / build:jfjoch:ubuntu2404:cuda (push) Successful in 18m38s
Build Packages / Unit tests (push) Successful in 1h46m14s
v1.0.0-rc.173 (#83)
* jfjoch_broker: Optional per-dataset authentication - statistics, images and plots can require a bearer token, which jfjoch_viewer supports.
* jfjoch_viewer: Dark mode and a theme-matched colour scheme, a magnifier panel, and simpler contrast and background controls.
* Rugnux: Multiple performance improvements on GPU and CPU (CPU-only processing up to 40% faster, faster image decoding on ARM), with unchanged results.
* Rugnux: `--model` rigid-body refinement runs on the GPU, and the model-validation check is faster and more reliable.
* Rugnux: Improved scaling and merging - error model, outlier rejection, absorption correction and French-Wilson amplitudes now agree more closely with XDS and ctruncate.
* Rugnux: Improved integration - radial background on powder and ice rings, crowded rotation data keep their reflections, and CPU-only builds integrate large unit cells as GPU builds do.
* Rugnux: More robust detector geometry - measured beam centre, X-ray bandwidth and goniometer rate, and geometry refinement accepted only on significant evidence.
* Rugnux: Merged files are written in the standard setting, or in the setting of a reference MTZ, structure-factor mmCIF or model, with its free-R flags.
* Rugnux: Richer report - ice and powder rings, further lattices, superstructure candidates and mosaicity, with warnings worded as prompts to check.
* Rugnux: Clear error messages when a data set needs more GPU or host memory than is available.

Reviewed-on: #83
Co-authored-by: Filip Leonarski <filip.leonarski@psi.ch>
2026-09-29 15:57:32 +02:00

105 lines
3.0 KiB
C++

// SPDX-FileCopyrightText: 2026 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
// SPDX-License-Identifier: GPL-3.0-only
#include "ThreadAffinity.h"
#ifdef __linux__
#include <cstdio>
#include <filesystem>
#include <fstream>
#include <sstream>
#include <pthread.h>
#include <sched.h>
namespace {
// The process's CPUs, taken before any thread has been pinned: static initialisation runs on the
// main thread before main().
cpu_set_t StartMask() {
cpu_set_t mask;
CPU_ZERO(&mask);
if (sched_getaffinity(0, sizeof(mask), &mask) != 0)
for (int c = 0; c < CPU_SETSIZE; c++)
CPU_SET(c, &mask);
return mask;
}
const cpu_set_t start_mask = StartMask();
int NumaNodeCount() {
int n = 0;
std::error_code ec;
for (const auto &e : std::filesystem::directory_iterator("/sys/devices/system/node", ec)) {
const std::string name = e.path().filename().string();
if (name.rfind("node", 0) == 0 && name.size() > 4
&& name.find_first_not_of("0123456789", 4) == std::string::npos)
n++;
}
return n;
}
// "0-23,48-71" -> the CPUs it names.
bool ParseCpuList(const std::string &list, cpu_set_t &out) {
CPU_ZERO(&out);
std::stringstream ss(list);
std::string range;
bool any = false;
while (std::getline(ss, range, ',')) {
int lo, hi;
if (std::sscanf(range.c_str(), "%d-%d", &lo, &hi) == 2) {
} else if (std::sscanf(range.c_str(), "%d", &lo) == 1) {
hi = lo;
} else
continue;
for (int c = lo; c <= hi && c < CPU_SETSIZE; c++) {
CPU_SET(c, &out);
any = true;
}
}
return any;
}
}
int NumaNodeOfPciDevice(const std::string &pci_bus_id) {
if (NumaNodeCount() < 2)
return -1;
unsigned domain, bus, device, function;
if (std::sscanf(pci_bus_id.c_str(), "%x:%x:%x.%x", &domain, &bus, &device, &function) != 4)
return -1;
char path[128];
std::snprintf(path, sizeof(path), "/sys/bus/pci/devices/%04x:%02x:%02x.%x/numa_node",
domain, bus, device, function);
std::ifstream f(path);
int node = -1;
if (!(f >> node))
return -1;
return node;
}
void PinThreadToNumaNode(int node) {
if (node < 0)
return;
std::ifstream f("/sys/devices/system/node/node" + std::to_string(node) + "/cpulist");
std::string list;
cpu_set_t node_cpus;
if (!std::getline(f, list) || !ParseCpuList(list, node_cpus))
return;
cpu_set_t mask;
CPU_AND(&mask, &node_cpus, &start_mask);
if (CPU_COUNT(&mask) == 0)
return;
pthread_setaffinity_np(pthread_self(), sizeof(mask), &mask);
}
void RestoreThreadAffinity() {
pthread_setaffinity_np(pthread_self(), sizeof(start_mask), &start_mask);
}
#else
int NumaNodeOfPciDevice(const std::string &) { return -1; }
void PinThreadToNumaNode(int) {}
void RestoreThreadAffinity() {}
#endif