3f032156c8
Like yesterday's change to run CPU-parent child tasks serially in thread, this
reduces peak memory usage by improving the temporaly locality of the bitmaps we
create.
E.g. Let's say we start with tasks A B C and D
Queue: [ A B C D ]
Running A creates A' and A", which depend on a bitmap created by A.
Queue: [ B C D A' A" * ]
That bitmap now needs sit around in RAM while B C and D run pointlessly and can
only be destroyed at *. If instead we do this and push dependent child tasks
to the front of the queue, the queue and bitmap lifetime looks like this:
Queue: [ A' A" * B C D ]
This is much, much worse in practice because the queue is often several thousand
tasks long. 100s of megs of bitmaps can pile up for 10s of seconds pointlessly.
To make this work we add addNext() to SkThreadPool and its cousin DMTaskRunner.
I also took the opportunity to swap head and tail in the threadpool
implementation so it matches the comments and intuition better: we always pop
the head, add() puts it at the tail, addNext() at the head.
Before
Debug: 49s, 1403352k peak
Release: 16s, 2064008k peak
After
Debug: 49s, 1234788k peak
Release: 15s, 1903424k peak
BUG=skia:2478
R=bsalomon@google.com, borenet@google.com, mtklein@google.com
Author: mtklein@chromium.org
Review URL: https://codereview.chromium.org/263803003
git-svn-id: http://skia.googlecode.com/svn/trunk@14506 2bbb7eff-a529-9590-31e7-b0007b416f81
81 lines
2.1 KiB
C++
81 lines
2.1 KiB
C++
#include "DMTask.h"
|
|
#include "DMTaskRunner.h"
|
|
#include "SkCommandLineFlags.h"
|
|
|
|
DEFINE_bool(cpu, true, "Master switch for running CPU-bound work.");
|
|
DEFINE_bool(gpu, true, "Master switch for running GPU-bound work.");
|
|
|
|
namespace DM {
|
|
|
|
Task::Task(Reporter* reporter, TaskRunner* taskRunner)
|
|
: fReporter(reporter)
|
|
, fTaskRunner(taskRunner)
|
|
, fDepth(0) {
|
|
fReporter->start();
|
|
}
|
|
|
|
Task::Task(const Task& parent)
|
|
: fReporter(parent.fReporter)
|
|
, fTaskRunner(parent.fTaskRunner)
|
|
, fDepth(parent.depth() + 1) {
|
|
fReporter->start();
|
|
}
|
|
|
|
void Task::fail(const char* msg) {
|
|
SkString failure(this->name());
|
|
if (msg) {
|
|
failure.appendf(": %s", msg);
|
|
}
|
|
fReporter->fail(failure);
|
|
}
|
|
|
|
void Task::start() {
|
|
fStart = SkTime::GetMSecs();
|
|
}
|
|
|
|
void Task::finish() {
|
|
fReporter->finish(this->name(), SkTime::GetMSecs() - fStart);
|
|
}
|
|
|
|
void Task::spawnChildNext(CpuTask* task) {
|
|
fTaskRunner->addNext(task);
|
|
}
|
|
|
|
CpuTask::CpuTask(Reporter* reporter, TaskRunner* taskRunner) : Task(reporter, taskRunner) {}
|
|
CpuTask::CpuTask(const Task& parent) : Task(parent) {}
|
|
|
|
void CpuTask::run() {
|
|
this->start();
|
|
if (FLAGS_cpu && !this->shouldSkip()) {
|
|
this->draw();
|
|
}
|
|
this->finish();
|
|
SkDELETE(this);
|
|
}
|
|
|
|
void CpuTask::spawnChild(CpuTask* task) {
|
|
// Run children serially on this (CPU) thread. This tends to save RAM and is usually no slower.
|
|
// Calling spawnChildNext() is nearly equivalent, but it'd pointlessly contend on the
|
|
// threadpool; spawnChildNext() is most useful when you want to change threadpools.
|
|
task->run();
|
|
}
|
|
|
|
GpuTask::GpuTask(Reporter* reporter, TaskRunner* taskRunner) : Task(reporter, taskRunner) {}
|
|
|
|
void GpuTask::run(GrContextFactory& factory) {
|
|
this->start();
|
|
if (FLAGS_gpu && !this->shouldSkip()) {
|
|
this->draw(&factory);
|
|
}
|
|
this->finish();
|
|
SkDELETE(this);
|
|
}
|
|
|
|
void GpuTask::spawnChild(CpuTask* task) {
|
|
// Really spawn a new task so it runs on the CPU threadpool instead of the GPU one we're on now.
|
|
// It goes on the front of the queue to minimize the time we must hold reference bitmaps in RAM.
|
|
this->spawnChildNext(task);
|
|
}
|
|
|
|
} // namespace DM
|