view rust/hg-core/src/vfs.rs @ 48178:f12a19d03d2c

fix: reduce number of tool executions By grouping together (path, ctx) pairs according to the inputs they would provide to fixer tools, we can deduplicate executions of fixer tools to significantly reduce the amount of time spent running slow tools. This change does not handle clean files in the working copy, which could still be deduplicated against the files in the checked out commit. It's a little harder to do that because the filerev is not available in the workingfilectx (and it doesn't exist for added files). Anecdotally, this change makes some real uses cases at Google 10x faster. I think we were originally hesitant to do this because the benefits weren't obvious, and implementing it efficiently is kind of tricky. If we simply memoized the formatter execution function, we would be keeping tons of file content in memory. Also included is a regression test for a corner case that I broke with my first attempt at optimizing this code. Differential Revision: https://phab.mercurial-scm.org/D11280
author Danny Hooper <hooper@google.com>
date Thu, 02 Sep 2021 14:08:45 -0700
parents e834b79def74
children 9d0e5629cfbf
line wrap: on
line source

use crate::errors::{HgError, IoErrorContext, IoResultExt};
use memmap2::{Mmap, MmapOptions};
use std::io::ErrorKind;
use std::path::{Path, PathBuf};

/// Filesystem access abstraction for the contents of a given "base" diretory
#[derive(Clone, Copy)]
pub struct Vfs<'a> {
    pub(crate) base: &'a Path,
}

impl Vfs<'_> {
    pub fn join(&self, relative_path: impl AsRef<Path>) -> PathBuf {
        self.base.join(relative_path)
    }

    pub fn read(
        &self,
        relative_path: impl AsRef<Path>,
    ) -> Result<Vec<u8>, HgError> {
        let path = self.join(relative_path);
        std::fs::read(&path).when_reading_file(&path)
    }

    pub fn mmap_open(
        &self,
        relative_path: impl AsRef<Path>,
    ) -> Result<Mmap, HgError> {
        let path = self.base.join(relative_path);
        let file = std::fs::File::open(&path).when_reading_file(&path)?;
        // TODO: what are the safety requirements here?
        let mmap = unsafe { MmapOptions::new().map(&file) }
            .when_reading_file(&path)?;
        Ok(mmap)
    }

    pub fn rename(
        &self,
        relative_from: impl AsRef<Path>,
        relative_to: impl AsRef<Path>,
    ) -> Result<(), HgError> {
        let from = self.join(relative_from);
        let to = self.join(relative_to);
        std::fs::rename(&from, &to)
            .with_context(|| IoErrorContext::RenamingFile { from, to })
    }
}

fn fs_metadata(
    path: impl AsRef<Path>,
) -> Result<Option<std::fs::Metadata>, HgError> {
    let path = path.as_ref();
    match std::fs::metadata(path) {
        Ok(meta) => Ok(Some(meta)),
        Err(error) => match error.kind() {
            // TODO: when we require a Rust version where `NotADirectory` is
            // stable, invert this logic and return None for it and `NotFound`
            // and propagate any other error.
            ErrorKind::PermissionDenied => Err(error).with_context(|| {
                IoErrorContext::ReadingMetadata(path.to_owned())
            }),
            _ => Ok(None),
        },
    }
}

pub(crate) fn is_dir(path: impl AsRef<Path>) -> Result<bool, HgError> {
    Ok(fs_metadata(path)?.map_or(false, |meta| meta.is_dir()))
}

pub(crate) fn is_file(path: impl AsRef<Path>) -> Result<bool, HgError> {
    Ok(fs_metadata(path)?.map_or(false, |meta| meta.is_file()))
}