Process files in parallel (#531)

This PR makes the oxipng binary process multiple files in parallel,
finally fulfilling #275. There seemed to be some debate about whether
oxipng _should_ do this or not but there's a couple of reasons I think
it makes sense:
1. The concern seemed mostly around the complexity of such a feature.
Not to worry, it was trivial* 🙂
2. Since then, oxipng has dropped from a max of something like 180
simultaneous compression trials down to 10, which is very much a good
thing but it does mean it's not utilising any more cores than that.

Some benchmarks on around 100 files on a machine with 8 cores:
Level | Master time | PR time
-|-|-
2 | 28.303 | 19.005
3 | 36.507 | 23.089
5 | 1:10.86 | 1:16.01

*Some additional changes were required in order to make sure sensible
output is printed to the terminal, since things won't be in order
anymore. Here's some example output from before:
```
Processing: tests/files/fully_optimized.png
    file size = 67 bytes (0 bytes = 0.00% decrease)
File already optimized
Processing: tests/files/corrupted_header.png
Invalid PNG header detected
Processing: tests/files/verbose_mode.png
    file size = 102480 bytes (12228 bytes = 10.66% decrease)
Output: tests/files/verbose_mode.png
```
And after:
```
Processing: tests/files/verbose_mode.png
Processing: tests/files/fully_optimized.png
Processing: tests/files/corrupted_header.png
tests/files/corrupted_header.png: Invalid PNG header detected
tests/files/fully_optimized.png: Could not optimize further, no change written
102480 bytes (10.66% smaller): tests/files/verbose_mode.png
```

Closes #275, #84, #169, #196 and #419.

[edit] This is the last thing I wanted to land before the next release 🥳
This commit is contained in:
andrews05 2023-07-11 19:45:10 +12:00 committed by GitHub
parent 31e796c4e8
commit 4ae64c568b
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 35 additions and 15 deletions

View file

@ -453,13 +453,15 @@ pub fn optimize(input: &InFile, output: &OutFile, opts: &Options) -> PngResult<(
// Run the optimizer on the decoded PNG.
let mut optimized_output = optimize_png(&mut png, &in_data, opts, deadline)?;
let in_length = in_data.len();
if is_fully_optimized(in_data.len(), optimized_output.len(), opts) {
info!("File already optimized");
match (output, input) {
// if p is None, it also means same as the input path
(OutFile::Path(ref p), InFile::Path(ref input_path))
if p.as_ref().map_or(true, |p| p == input_path) =>
{
info!("{}: Could not optimize further, no change written", input);
return Ok(());
}
_ => {
@ -468,8 +470,22 @@ pub fn optimize(input: &InFile, output: &OutFile, opts: &Options) -> PngResult<(
}
}
let savings = if in_length >= optimized_output.len() {
format!(
"{} bytes ({:.2}% smaller)",
optimized_output.len(),
(in_length - optimized_output.len()) as f64 / in_length as f64 * 100_f64
)
} else {
format!(
"{} bytes ({:.2}% larger)",
optimized_output.len(),
(optimized_output.len() - in_length) as f64 / in_length as f64 * 100_f64
)
};
if opts.pretend {
info!("Running in pretend mode, no output");
info!("{}: Running in pretend mode, no output", savings);
return Ok(());
}
@ -516,7 +532,7 @@ pub fn optimize(input: &InFile, output: &OutFile, opts: &Options) -> PngResult<(
if let Some(metadata_input) = &opt_metadata_preserved {
copy_times(metadata_input, output_path)?;
}
info!("Output: {}", output_path.display());
info!("{}: {}", savings, output_path.display());
}
}
Ok(())
@ -606,14 +622,14 @@ fn optimize_png(
);
}
if file_original_size >= output.len() {
info!(
debug!(
" file size = {} bytes ({} bytes = {:.2}% decrease)",
output.len(),
file_original_size - output.len(),
(file_original_size - output.len()) as f64 / file_original_size as f64 * 100_f64
);
} else {
info!(
debug!(
" file size = {} bytes ({} bytes = {:.2}% increase)",
output.len(),
output.len() - file_original_size,

View file

@ -13,6 +13,9 @@
#![warn(clippy::range_plus_one)]
#![allow(clippy::cognitive_complexity)]
#[cfg(not(feature = "parallel"))]
mod rayon;
use clap::{value_parser, Arg, ArgAction, ArgMatches, Command};
use indexmap::IndexSet;
use log::{error, warn};
@ -21,6 +24,7 @@ use oxipng::Options;
use oxipng::RowFilter;
use oxipng::StripChunks;
use oxipng::{InFile, OutFile};
use rayon::prelude::*;
use std::fs::DirBuilder;
#[cfg(feature = "zopfli")]
use std::num::NonZeroU8;
@ -313,9 +317,8 @@ Heuristic filter selection strategies:
true,
);
let mut success = false;
for (input, output) in files {
match oxipng::optimize(&input, &output, &opts) {
let success = files.into_par_iter().filter(|(input, output)| {
match oxipng::optimize(input, output, &opts) {
// For optimizing single files, this will return the correct exit code always.
// For recursive optimization, the correct choice is a bit subjective.
// We're choosing to return a 0 exit code if ANY file in the set
@ -323,16 +326,15 @@ Heuristic filter selection strategies:
// The reason for this is that recursion may pick up files that are not
// PNG files, and return an error for them.
// We don't really want to return an error code for those files.
Ok(_) => {
success = true;
}
Ok(_) => true,
Err(e) => {
error!("{}", e);
error!("{}: {}", input, e);
false
}
};
}
}
});
if !success {
if success.count() == 0 {
exit(1);
}
}

View file

@ -75,6 +75,7 @@ pub fn join<A, B>(a: impl FnOnce() -> A, b: impl FnOnce() -> B) -> (A, B) {
(a(), b())
}
#[allow(dead_code)]
pub fn spawn<A>(a: impl FnOnce() -> A) -> A {
a()
}

View file

@ -188,6 +188,7 @@ fn verbose_mode() {
"Found better combination:",
" zc = 11 f = None ",
" IDAT size = ",
" file size = ",
];
assert_eq!(logs.len(), expected_prefixes.len());
for (i, log) in logs.into_iter().enumerate() {