##// END OF EJS Templates
copies: move from a copy on branchpoint to a copy on write approach...
copies: move from a copy on branchpoint to a copy on write approach Before this changes, any branch points results in a copy of the dictionary containing the copy information. This can be very costly for branchy history with few rename information. Instead, we take a "copy on write" approach. Copying the input data only when we are about to update them. In practice we where already doing the copying in half of these case (because `_chain` makes a copy), so we don't add a significant cost here even in the linear case. However the speed up in branchy case is very significant. Here are some timing on the pypy repository. revision: large amount; added files: large amount; rename small amount; c3b14617fbd7 9ba6ab77fd29 before: ! wall 1.399863 comb 1.400000 user 1.370000 sys 0.030000 (median of 10) after: ! wall 0.766453 comb 0.770000 user 0.750000 sys 0.020000 (median of 11) revision: large amount; added files: small amount; rename small amount; c3b14617fbd7 f650a9b140d2 before: ! wall 1.876748 comb 1.890000 user 1.870000 sys 0.020000 (median of 10) after: ! wall 1.167223 comb 1.170000 user 1.150000 sys 0.020000 (median of 10) revision: large amount; added files: large amount; rename large amount; 08ea3258278e d9fa043f30c0 before: ! wall 0.242457 comb 0.240000 user 0.240000 sys 0.000000 (median of 39) after: ! wall 0.211476 comb 0.210000 user 0.210000 sys 0.000000 (median of 45) revision: small amount; added files: large amount; rename large amount; df6f7a526b60 a83dc6a2d56f before: ! wall 0.013193 comb 0.020000 user 0.020000 sys 0.000000 (median of 224) after: ! wall 0.013290 comb 0.010000 user 0.010000 sys 0.000000 (median of 222) revision: small amount; added files: large amount; rename small amount; 4aa4e1f8e19a 169138063d63 before: ! wall 0.001673 comb 0.000000 user 0.000000 sys 0.000000 (median of 1000) after: ! wall 0.001677 comb 0.000000 user 0.000000 sys 0.000000 (median of 1000) revision: small amount; added files: small amount; rename small amount; 4bc173b045a6 964879152e2e before: ! wall 0.000119 comb 0.000000 user 0.000000 sys 0.000000 (median of 8023) after: ! wall 0.000119 comb 0.000000 user 0.000000 sys 0.000000 (median of 7997) revision: medium amount; added files: large amount; rename medium amount; c95f1ced15f2 2c68e87c3efe before: ! wall 0.201898 comb 0.210000 user 0.200000 sys 0.010000 (median of 48) after: ! wall 0.167415 comb 0.170000 user 0.160000 sys 0.010000 (median of 58) revision: medium amount; added files: medium amount; rename small amount; d343da0c55a8 d7746d32bf9d before: ! wall 0.036820 comb 0.040000 user 0.040000 sys 0.000000 (median of 100) after: ! wall 0.035797 comb 0.040000 user 0.040000 sys 0.000000 (median of 100) The extra cost in the linear case can be reclaimed later with some extra logic. Differential Revision: https://phab.mercurial-scm.org/D7124

File last commit:

r43479:1ca3823a default
r43594:ffd04bc9 default
Show More
parsers.rs
176 lines | 5.2 KiB | application/rls-services+xml | RustLexer
// parsers.rs
//
// Copyright 2019 Raphaël Gomès <rgomes@octobus.net>
//
// This software may be used and distributed according to the terms of the
// GNU General Public License version 2 or any later version.
//! Bindings for the `hg::dirstate::parsers` module provided by the
//! `hg-core` package.
//!
//! From Python, this will be seen as `mercurial.rustext.parsers`
//!
use cpython::{
exc, PyBytes, PyDict, PyErr, PyInt, PyModule, PyResult, PyTuple, Python,
PythonObject, ToPyObject,
};
use hg::{
pack_dirstate, parse_dirstate, utils::hg_path::HgPathBuf,
DirstatePackError, DirstateParents, DirstateParseError, PARENT_SIZE,
};
use std::collections::HashMap;
use std::convert::TryInto;
use crate::dirstate::{extract_dirstate, make_dirstate_tuple};
use std::time::Duration;
fn parse_dirstate_wrapper(
py: Python,
dmap: PyDict,
copymap: PyDict,
st: PyBytes,
) -> PyResult<PyTuple> {
let mut dirstate_map = HashMap::new();
let mut copies = HashMap::new();
match parse_dirstate(&mut dirstate_map, &mut copies, st.data(py)) {
Ok(parents) => {
for (filename, entry) in &dirstate_map {
dmap.set_item(
py,
PyBytes::new(py, filename.as_ref()),
make_dirstate_tuple(py, entry)?,
)?;
}
for (path, copy_path) in copies {
copymap.set_item(
py,
PyBytes::new(py, path.as_ref()),
PyBytes::new(py, copy_path.as_ref()),
)?;
}
Ok(
(PyBytes::new(py, &parents.p1), PyBytes::new(py, &parents.p2))
.to_py_object(py),
)
}
Err(e) => Err(PyErr::new::<exc::ValueError, _>(
py,
match e {
DirstateParseError::TooLittleData => {
"too little data for parents".to_string()
}
DirstateParseError::Overflow => {
"overflow in dirstate".to_string()
}
DirstateParseError::CorruptedEntry(e) => e,
DirstateParseError::Damaged => {
"dirstate appears to be damaged".to_string()
}
},
)),
}
}
fn pack_dirstate_wrapper(
py: Python,
dmap: PyDict,
copymap: PyDict,
pl: PyTuple,
now: PyInt,
) -> PyResult<PyBytes> {
let p1 = pl.get_item(py, 0).extract::<PyBytes>(py)?;
let p1: &[u8] = p1.data(py);
let p2 = pl.get_item(py, 1).extract::<PyBytes>(py)?;
let p2: &[u8] = p2.data(py);
let mut dirstate_map = extract_dirstate(py, &dmap)?;
let copies: Result<HashMap<HgPathBuf, HgPathBuf>, PyErr> = copymap
.items(py)
.iter()
.map(|(key, value)| {
Ok((
HgPathBuf::from_bytes(key.extract::<PyBytes>(py)?.data(py)),
HgPathBuf::from_bytes(value.extract::<PyBytes>(py)?.data(py)),
))
})
.collect();
if p1.len() != PARENT_SIZE || p2.len() != PARENT_SIZE {
return Err(PyErr::new::<exc::ValueError, _>(
py,
"expected a 20-byte hash".to_string(),
));
}
match pack_dirstate(
&mut dirstate_map,
&copies?,
DirstateParents {
p1: p1.try_into().unwrap(),
p2: p2.try_into().unwrap(),
},
Duration::from_secs(now.as_object().extract::<u64>(py)?),
) {
Ok(packed) => {
for (filename, entry) in &dirstate_map {
dmap.set_item(
py,
PyBytes::new(py, filename.as_ref()),
make_dirstate_tuple(py, entry)?,
)?;
}
Ok(PyBytes::new(py, &packed))
}
Err(error) => Err(PyErr::new::<exc::ValueError, _>(
py,
match error {
DirstatePackError::CorruptedParent => {
"expected a 20-byte hash".to_string()
}
DirstatePackError::CorruptedEntry(e) => e,
DirstatePackError::BadSize(expected, actual) => {
format!("bad dirstate size: {} != {}", actual, expected)
}
},
)),
}
}
/// Create the module, with `__package__` given from parent
pub fn init_parsers_module(py: Python, package: &str) -> PyResult<PyModule> {
let dotted_name = &format!("{}.parsers", package);
let m = PyModule::new(py, dotted_name)?;
m.add(py, "__package__", package)?;
m.add(py, "__doc__", "Parsers - Rust implementation")?;
m.add(
py,
"parse_dirstate",
py_fn!(
py,
parse_dirstate_wrapper(dmap: PyDict, copymap: PyDict, st: PyBytes)
),
)?;
m.add(
py,
"pack_dirstate",
py_fn!(
py,
pack_dirstate_wrapper(
dmap: PyDict,
copymap: PyDict,
pl: PyTuple,
now: PyInt
)
),
)?;
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)
}