mirror of
https://github.com/IfcOpenShell/IfcOpenShell.git
synced 2026-08-28 07:49:59 +00:00
Dion Moult
777b728205
A 66-model session oscillated with a ~4 s period — 298 releases in one log: the pool grew to its ceiling, the next report read ~83 MB free, the budget dropped and the pool shrank, the reading rebounded, the budget rose and the pool re-grew, reloading the same chunks each time. Objects flickered on and off continuously. The report includes transients the viewer itself creates: the upload staging behind a burst of chunk loads (~170 MB in that session) and a released sub-buffer the driver has not yet reclaimed. A budget that followed every reading fed those straight back into growth decisions. GpuBudget::update now bounds the cache outright on the first device report and afterwards moves only on sustained readings: lower when free memory is below half the margin on two consecutive scheduled reports, raise when it is above 1.5× the margin on two, and nothing in between. Transients drain well within a poll interval, so a momentary low never reaches the pool, while a process that really took memory still does a second later. A refused allocation (onPressure) is never deferred. Verified in the saturated regime (working set ~990 MB against a 683 MB budget, continuous streaming): zero releases over 75 s. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
87 lines
4.2 KiB
C++
87 lines
4.2 KiB
C++
/********************************************************************************
|
|
* *
|
|
* This file is part of IfcOpenShell. *
|
|
* *
|
|
* IfcOpenShell is free software: you can redistribute it and/or modify *
|
|
* it under the terms of the Lesser GNU General Public License as published by *
|
|
* the Free Software Foundation, either version 3.0 of the License, or *
|
|
* (at your option) any later version. *
|
|
* *
|
|
* IfcOpenShell is distributed in the hope that it will be useful, *
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of *
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the *
|
|
* Lesser GNU General Public License for more details. *
|
|
* *
|
|
* You should have received a copy of the Lesser GNU General Public License *
|
|
* along with this program. If not, see <http://www.gnu.org/licenses/>. *
|
|
* *
|
|
********************************************************************************/
|
|
|
|
#include "GpuBudget.h"
|
|
|
|
#include <algorithm>
|
|
|
|
void GpuBudget::bound(std::uint64_t budget) {
|
|
if (hard_cap_ > 0) budget = std::min(budget, hard_cap_);
|
|
bounded_ = true;
|
|
budget_ = std::max(budget, kMinCacheBudgetBytes);
|
|
}
|
|
|
|
void GpuBudget::setHardCap(std::uint64_t hard_cap_bytes) {
|
|
hard_cap_ = hard_cap_bytes;
|
|
if (hard_cap_ > 0) bound(bounded_ ? budget_ : hard_cap_);
|
|
}
|
|
|
|
void GpuBudget::update(std::uint64_t device_free_bytes,
|
|
std::uint64_t cache_capacity_bytes) {
|
|
if (device_free_bytes == 0) return;
|
|
const std::uint64_t available = cache_capacity_bytes + device_free_bytes;
|
|
const std::uint64_t margin = margin_bytes();
|
|
const std::uint64_t reading = available > margin ? available - margin : 0;
|
|
if (!had_device_report_) {
|
|
had_device_report_ = true;
|
|
bound(reading);
|
|
return;
|
|
}
|
|
|
|
const bool tight = device_free_bytes < margin / 2;
|
|
const bool roomy = device_free_bytes > margin + margin / 2 && reading > budget_;
|
|
low_reports_ = tight ? low_reports_ + 1 : 0;
|
|
high_reports_ = roomy ? high_reports_ + 1 : 0;
|
|
if (low_reports_ >= kConfirmReports) {
|
|
bound(std::min(budget_, reading));
|
|
low_reports_ = 0;
|
|
} else if (high_reports_ >= kConfirmReports) {
|
|
bound(reading);
|
|
high_reports_ = 0;
|
|
}
|
|
}
|
|
|
|
bool GpuBudget::onPressure(std::uint64_t cache_capacity_bytes,
|
|
std::uint64_t bytes_needed,
|
|
std::uint64_t device_free_bytes) {
|
|
++pressure_events_;
|
|
// The driver refused bytes_needed while reporting device_free_bytes
|
|
// free, so at least (free - needed) of what it reports is not really
|
|
// available. Remember that so update() stops short of it next time.
|
|
if (device_free_bytes > bytes_needed) {
|
|
learned_margin_ = std::max(learned_margin_,
|
|
device_free_bytes - bytes_needed + kPressureSlackBytes);
|
|
}
|
|
// What the cache may keep once the failed allocation and its slack
|
|
// have been carved out of what it holds right now. The pool's actual
|
|
// capacity, not the previous budget, is the honest baseline: the
|
|
// budget may never have been reached (unbounded, or growth refused
|
|
// earlier by the driver), and lowering a number the pool never hit
|
|
// would free nothing.
|
|
const std::uint64_t carve = bytes_needed + kPressureSlackBytes;
|
|
const std::uint64_t target = cache_capacity_bytes > carve
|
|
? cache_capacity_bytes - carve
|
|
: 0;
|
|
const std::uint64_t lowered = std::max(target, kMinCacheBudgetBytes);
|
|
if (bounded_ && lowered >= budget_) return false;
|
|
bound(lowered);
|
|
low_reports_ = high_reports_ = 0;
|
|
return true;
|
|
}
|