uutils/diffutils
0
0
Fork 0
mirror of https://github.com/uutils/diffutils.git synced 2026-06-10 15:48:59 -07:00
Code Issues Packages Projects Releases Wiki Activity

cmp: completely avoid Rust fmt in verbose mode

Browse Source 
This makes the code less readable, but gets us a massive improvement
to performance. Comparing ~36M completely different files now takes
~40% of the time. Compared to GNU cmp, we now run the same comparison
in ~26% of the time.

This also improves comparing binary files. A comparison of chromium
and libxul now takes ~60% of the time. We also beat GNU cmpi by about
the same margin.

Before:

 > hyperfine --warmup 1 -i --output=pipe \
     '../target/release/diffutils cmp -l huge huge.3'
 Benchmark 1: ../target/release/diffutils cmp -l huge huge.3
   Time (mean ± σ):      2.000 s ±  0.016 s    [User: 1.603 s, System: 0.392 s]
   Range (min … max):    1.989 s …  2.043 s    10 runs

   Warning: Ignoring non-zero exit code.

 > hyperfine --warmup 1 -i --output=pipe \
     '../target/release/diffutils cmp -l -b \
     /usr/lib64/chromium-browser/chromium-browser \
     /usr/lib64/firefox/libxul.so'
 Benchmark 1: ../target/release/diffutils cmp -l -b /usr/lib64/chromium-browser/chromium-browser /usr/lib64/firefox/libxul.so
   Time (mean ± σ):     24.704 s ±  0.162 s    [User: 21.948 s, System: 2.700 s]
   Range (min … max):   24.359 s … 24.889 s    10 runs

   Warning: Ignoring non-zero exit code.

After:

 > hyperfine --warmup 1 -i --output=pipe \
     '../target/release/diffutils cmp -l huge huge.3'
 Benchmark 1: ../target/release/diffutils cmp -l huge huge.3
   Time (mean ± σ):     849.5 ms ±   6.2 ms    [User: 538.3 ms, System: 306.8 ms]
   Range (min … max):   839.4 ms … 857.7 ms    10 runs

   Warning: Ignoring non-zero exit code.

 > hyperfine --warmup 1 -i --output=pipe \
     '../target/release/diffutils cmp -l -b \
     /usr/lib64/chromium-browser/chromium-browser \
     /usr/lib64/firefox/libxul.so'
 Benchmark 1: ../target/release/diffutils cmp -l -b /usr/lib64/chromium-browser/chromium-browser /usr/lib64/firefox/libxul.so
   Time (mean ± σ):     14.646 s ±  0.040 s    [User: 12.328 s, System: 2.286 s]
   Range (min … max):   14.585 s … 14.702 s    10 runs

   Warning: Ignoring non-zero exit code.
This commit is contained in:
Gustavo Noronha Silva
2024-09-24 22:31:35 -03:00
parent 2e681301b4
commit fac8dab182
1 changed files with 65 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/cmp.rs
+65 -19
View File
@@ -530,6 +530,9 @@ fn format_byte(byte: u8) -> String {
unsafe { String::from_utf8_unchecked(quoted) }
}
// This function has been optimized to not use the Rust fmt system, which
// leads to a massive speed up when processing large files: cuts the time
// for comparing 2 ~36MB completely different files in half on an M1 Max.
fn report_verbose_diffs(diffs: Vec<(usize, u8, u8)>, params: &Params) -> Result<(), String> {
assert!(!params.quiet);
@@ -542,19 +545,49 @@ fn report_verbose_diffs(diffs: Vec<(usize, u8, u8)>, params: &Params) -> Result<
let mut from_oct = [0u8; 3]; // for octal conversions
let mut to_oct = [0u8; 3];
// Capacity calc: at_byte width + 2 x 3-byte octal numbers + 4-byte value + up to 2 byte value + 4 spaces
let mut output = Vec::<u8>::with_capacity(width + 3 * 2 + 4 + 2 + 4);
if params.print_bytes {
for (at_byte, from_byte, to_byte) in diffs {
output.clear();
// "{:>width$} {:>3o} {:4} {:>3o} {}",
let at_byte_str = at_byte_buf.format(at_byte);
writeln!(
stdout,
"{:>width$} {} {:4} {} {}",
at_byte_str,
format_octal(from_byte, &mut from_oct),
format_byte(from_byte),
format_octal(to_byte, &mut to_oct),
format_byte(to_byte),
)
.map_err(|e| {
let at_byte_padding = width - at_byte_str.len();
for _ in 0..at_byte_padding {
output.push(b' ')
}
output.extend_from_slice(at_byte_str.as_bytes());
output.push(b' ');
output.extend_from_slice(format_octal(from_byte, &mut from_oct).as_bytes());
output.push(b' ');
let from_byte_str = format_byte(from_byte);
let from_byte_padding = 4 - from_byte_str.len();
output.extend_from_slice(from_byte_str.as_bytes());
for _ in 0..from_byte_padding {
output.push(b' ')
}
output.push(b' ');
output.extend_from_slice(format_octal(to_byte, &mut to_oct).as_bytes());
output.push(b' ');
output.extend_from_slice(format_byte(to_byte).as_bytes());
output.push(b'\n');
stdout.write_all(output.as_slice()).map_err(|e| {
format!(
"{}: error printing output: {e}",
params.executable.to_string_lossy()
@@ -563,16 +596,29 @@ fn report_verbose_diffs(diffs: Vec<(usize, u8, u8)>, params: &Params) -> Result<
}
} else {
for (at_byte, from_byte, to_byte) in diffs {
output.clear();
// "{:>width$} {:>3o} {:>3o}"
let at_byte_str = at_byte_buf.format(at_byte);
writeln!(
stdout,
"{:>width$} {} {}",
at_byte_str,
format_octal(from_byte, &mut from_oct),
format_octal(to_byte, &mut to_oct),
width = width
)
.map_err(|e| {
let at_byte_padding = width - at_byte_str.len();
for _ in 0..at_byte_padding {
output.push(b' ')
}
output.extend_from_slice(at_byte_str.as_bytes());
output.push(b' ');
output.extend_from_slice(format_octal(from_byte, &mut from_oct).as_bytes());
output.push(b' ');
output.extend_from_slice(format_octal(to_byte, &mut to_oct).as_bytes());
output.push(b'\n');
stdout.write_all(output.as_slice()).map_err(|e| {
format!(
"{}: error printing output: {e}",
params.executable.to_string_lossy()