view rust/hg-cpython/src/utils.rs @ 51403:f8bf1a8e9181

phases: keep internal state as rev-num instead of node-id Node-id are expensive to work with, dealing with revision is much simple and faster. The fact we still used node-id here shows how few effort have been put into making the phase logic fast. We tend to no longer use node-id internally for about ten years. This has a large impact of repository with many draft roots. For example this Mozilla-try copy have ? Million draft roots and `perf::unbundle` see a significant improvement. ### data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog # benchmark.name = hg.perf.perf-unbundle # bin-env-vars.hg.flavor = no-rust # bin-env-vars.hg.py-re2-module = default # benchmark.variants.issue6528 = disabled # benchmark.variants.revs = last-1 before:: 1.746791 seconds after:: 1.278379 seconds (-26.82%) # benchmark.variants.revs = last-10 before:: 3.145774 seconds after:: 2.103735 seconds (-33.13%) # benchmark.variants.revs = last-100 before:: 3.487635 seconds after:: 2.446749 seconds (-29.85%) # benchmark.variants.revs = last-1000 before:: 5.007568 seconds after:: 3.989923 seconds (-20.32%)
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Tue, 20 Feb 2024 21:40:13 +0100
parents c7fb9b74e753
children 28a0eb21ff04
line wrap: on
line source

use cpython::exc::ValueError;
use cpython::{PyBytes, PyDict, PyErr, PyObject, PyResult, PyTuple, Python};
use hg::revlog::Node;

#[allow(unused)]
pub fn print_python_trace(py: Python) -> PyResult<PyObject> {
    eprintln!("===============================");
    eprintln!("Printing Python stack from Rust");
    eprintln!("===============================");
    let traceback = py.import("traceback")?;
    let sys = py.import("sys")?;
    let kwargs = PyDict::new(py);
    kwargs.set_item(py, "file", sys.get(py, "stderr")?)?;
    traceback.call(py, "print_stack", PyTuple::new(py, &[]), Some(&kwargs))
}

// Necessary evil for the time being, could maybe be moved to
// a TryFrom in Node itself
const NODE_BYTES_LENGTH: usize = 20;
type NodeData = [u8; NODE_BYTES_LENGTH];

/// Copy incoming Python bytes given as `PyObject` into `Node`,
/// doing the necessary checks
pub fn node_from_py_object<'a>(
    py: Python,
    bytes: &'a PyObject,
) -> PyResult<Node> {
    let as_py_bytes: &'a PyBytes = bytes.extract(py)?;
    node_from_py_bytes(py, as_py_bytes)
}

/// Clone incoming Python bytes given as `PyBytes` as a `Node`,
/// doing the necessary checks.
pub fn node_from_py_bytes(py: Python, bytes: &PyBytes) -> PyResult<Node> {
    <NodeData>::try_from(bytes.data(py))
        .map_err(|_| {
            PyErr::new::<ValueError, _>(
                py,
                format!("{}-byte hash required", NODE_BYTES_LENGTH),
            )
        })
        .map(Into::into)
}