##// 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:

r43563:33fe96a5 default
r43594:ffd04bc9 default
Show More
discovery.rs
159 lines | 5.6 KiB | application/rls-services+xml | RustLexer
// discovery.rs
//
// Copyright 2018 Georges Racinet <gracinet@anybox.fr>
//
// 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::discovery` module provided by the
//! `hg-core` crate. From Python, this will be seen as `rustext.discovery`
//!
//! # Classes visible from Python:
//! - [`PartialDiscover`] is the Rust implementation of
//! `mercurial.setdiscovery.partialdiscovery`.
use crate::{
cindex::Index, conversion::rev_pyiter_collect, exceptions::GraphError,
};
use cpython::{
ObjectProtocol, PyDict, PyModule, PyObject, PyResult, PyTuple, Python,
PythonObject, ToPyObject,
};
use hg::discovery::PartialDiscovery as CorePartialDiscovery;
use hg::Revision;
use std::collections::HashSet;
use std::cell::RefCell;
py_class!(pub class PartialDiscovery |py| {
data inner: RefCell<Box<CorePartialDiscovery<Index>>>;
// `_respectsize` is currently only here to replicate the Python API and
// will be used in future patches inside methods that are yet to be
// implemented.
def __new__(
_cls,
repo: PyObject,
targetheads: PyObject,
respectsize: bool,
randomize: bool = true
) -> PyResult<PartialDiscovery> {
let index = repo.getattr(py, "changelog")?.getattr(py, "index")?;
Self::create_instance(
py,
RefCell::new(Box::new(CorePartialDiscovery::new(
Index::new(py, index)?,
rev_pyiter_collect(py, &targetheads)?,
respectsize,
randomize,
)))
)
}
def addcommons(&self, commons: PyObject) -> PyResult<PyObject> {
let mut inner = self.inner(py).borrow_mut();
let commons_vec: Vec<Revision> = rev_pyiter_collect(py, &commons)?;
inner.add_common_revisions(commons_vec)
.map_err(|e| GraphError::pynew(py, e))?;
Ok(py.None())
}
def addmissings(&self, missings: PyObject) -> PyResult<PyObject> {
let mut inner = self.inner(py).borrow_mut();
let missings_vec: Vec<Revision> = rev_pyiter_collect(py, &missings)?;
inner.add_missing_revisions(missings_vec)
.map_err(|e| GraphError::pynew(py, e))?;
Ok(py.None())
}
def addinfo(&self, sample: PyObject) -> PyResult<PyObject> {
let mut missing: Vec<Revision> = Vec::new();
let mut common: Vec<Revision> = Vec::new();
for info in sample.iter(py)? { // info is a pair (Revision, bool)
let mut revknown = info?.iter(py)?;
let rev: Revision = revknown.next().unwrap()?.extract(py)?;
let known: bool = revknown.next().unwrap()?.extract(py)?;
if known {
common.push(rev);
} else {
missing.push(rev);
}
}
let mut inner = self.inner(py).borrow_mut();
inner.add_common_revisions(common)
.map_err(|e| GraphError::pynew(py, e))?;
inner.add_missing_revisions(missing)
.map_err(|e| GraphError::pynew(py, e))?;
Ok(py.None())
}
def hasinfo(&self) -> PyResult<bool> {
Ok(self.inner(py).borrow().has_info())
}
def iscomplete(&self) -> PyResult<bool> {
Ok(self.inner(py).borrow().is_complete())
}
def stats(&self) -> PyResult<PyDict> {
let stats = self.inner(py).borrow().stats();
let as_dict: PyDict = PyDict::new(py);
as_dict.set_item(py, "undecided",
stats.undecided.map(
|l| l.to_py_object(py).into_object())
.unwrap_or_else(|| py.None()))?;
Ok(as_dict)
}
def commonheads(&self) -> PyResult<HashSet<Revision>> {
self.inner(py).borrow().common_heads()
.map_err(|e| GraphError::pynew(py, e))
}
def takefullsample(&self, _headrevs: PyObject,
size: usize) -> PyResult<PyObject> {
let mut inner = self.inner(py).borrow_mut();
let sample = inner.take_full_sample(size)
.map_err(|e| GraphError::pynew(py, e))?;
let as_vec: Vec<PyObject> = sample
.iter()
.map(|rev| rev.to_py_object(py).into_object())
.collect();
Ok(PyTuple::new(py, as_vec.as_slice()).into_object())
}
def takequicksample(&self, headrevs: PyObject,
size: usize) -> PyResult<PyObject> {
let mut inner = self.inner(py).borrow_mut();
let revsvec: Vec<Revision> = rev_pyiter_collect(py, &headrevs)?;
let sample = inner.take_quick_sample(revsvec, size)
.map_err(|e| GraphError::pynew(py, e))?;
let as_vec: Vec<PyObject> = sample
.iter()
.map(|rev| rev.to_py_object(py).into_object())
.collect();
Ok(PyTuple::new(py, as_vec.as_slice()).into_object())
}
});
/// Create the module, with __package__ given from parent
pub fn init_module(py: Python, package: &str) -> PyResult<PyModule> {
let dotted_name = &format!("{}.discovery", package);
let m = PyModule::new(py, dotted_name)?;
m.add(py, "__package__", package)?;
m.add(
py,
"__doc__",
"Discovery of common node sets - Rust implementation",
)?;
m.add_class::<PartialDiscovery>(py)?;
let sys = PyModule::import(py, "sys")?;
let sys_modules: PyDict = sys.get(py, "modules")?.extract(py)?;
sys_modules.set_item(py, dotted_name, &m)?;
// Example C code (see pyexpat.c and import.c) will "give away the
// reference", but we won't because it will be consumed once the
// Rust PyObject is dropped.
Ok(m)
}