view rust/hg-cpython/src/update.rs @ 52060:8b7123c8947b

update: add a Rust fast-path when updating from null (and clean)

This case is easy to detect and we have all we need to generate a valid
working copy and dirstate entirely in Rust, which speeds things up
considerably:

On my machine updating a repo of ~300k files goes from 10.00s down to 4.2s,
all while consuming 50% less system time, with all caches hot.
Something to note is that further improvements will probably happen
with the upcoming `InnerRevlog` series that does smarter
mmap hanlding, especially for filelogs.

Here are benchmark numbers on a machine with only 4 cores (and no SMT enabled)

```
### data-env-vars.name               = heptapod-public-2024-03-25-ds2-pnm
  # benchmark.name                   = hg.command.update
  # bin-env-vars.hg.py-re2-module    = default
  # bin-env-vars.hg.changeset.node   = <this change>
  # benchmark.variants.atomic-update = no
  # benchmark.variants.scenario      = null-to-tip
  # benchmark.variants.worker        = default
default: 5.328762  ~~~~~
rust: 1.308654  (-75.44%, -4.02)
### data-env-vars.name               = mercurial-devel-2024-03-22-ds2-pnm
  # benchmark.name                   = hg.command.update
  # bin-env-vars.hg.py-re2-module    = default
  # bin-env-vars.hg.changeset.node   = <this change>
  # benchmark.variants.atomic-update = no
  # benchmark.variants.scenario      = null-to-tip
  # benchmark.variants.worker        = default
default: 1.693271  ~~~~~
rust: 1.151053  (-32.02%, -0.54)
### data-env-vars.name               = mozilla-unified-2024-03-22-ds2-pnm
  # benchmark.name                   = hg.command.update
  # bin-env-vars.hg.py-re2-module    = default
  # bin-env-vars.hg.changeset.node   = <this change>
  # benchmark.variants.atomic-update = no
  # benchmark.variants.scenario      = null-to-tip
  # benchmark.variants.worker        = default
default: 38.901613  ~~~~~
rust: 11.637880 (-70.08%, -27.26)
### data-env-vars.name               = netbsd-xsrc-public-2024-09-19-ds2-pnm
  # benchmark.name                   = hg.command.update
  # bin-env-vars.hg.py-re2-module    = default
  # bin-env-vars.hg.changeset.node   = <this change>
  # benchmark.variants.atomic-update = no
  # benchmark.variants.scenario      = null-to-tip
  # benchmark.variants.worker        = default
default: 4.793727  ~~~~~
rust: 1.505905  (-68.59%, -3.29)
```

// debug.rs
//
// Copyright 2024 Mercurial developers
//
// This software may be used and distributed according to the terms of the
// GNU General Public License version 2 or any later version.

//! Module for updating a repository.
use cpython::{PyDict, PyModule, PyObject, PyResult, Python};
use hg::{
    progress::{HgProgressBar, Progress},
    update::update_from_null,
    BaseRevision,
};

use crate::{
    exceptions::FallbackError,
    utils::{hgerror_to_pyerr, repo_from_path},
};

pub fn update_from_null_fast_path(
    py: Python,
    repo_path: PyObject,
    to: BaseRevision,
) -> PyResult<usize> {
    log::trace!("Using update from null fastpath");
    let repo = repo_from_path(py, repo_path)?;
    let progress: &dyn Progress = &HgProgressBar::new("updating");
    hgerror_to_pyerr(py, update_from_null(&repo, to.into(), progress))
}

pub fn init_module(py: Python, package: &str) -> PyResult<PyModule> {
    let dotted_name = &format!("{}.update", package);
    let m = PyModule::new(py, dotted_name)?;

    m.add(py, "__package__", package)?;
    m.add(py, "__doc__", "Rust module for updating a repository")?;
    m.add(py, "FallbackError", py.get_type::<FallbackError>())?;
    m.add(
        py,
        "update_from_null",
        py_fn!(
            py,
            update_from_null_fast_path(repo_path: PyObject, to: BaseRevision,)
        ),
    )?;

    let sys = PyModule::import(py, "sys")?;
    let sys_modules: PyDict = sys.get(py, "modules")?.extract(py)?;
    sys_modules.set_item(py, dotted_name, &m)?;

    Ok(m)
}