Mercurial > hg
view rust/hg-cpython/src/ancestors.rs @ 50338:81c7d04f4722 stable
match: match explicit file using a set
The matcher as all the logic to do quick comparison against explicit patterns,
however the pattern matcher was shadowing the code using that set and used the
compiled regex pattern in all cases, which is quite slow. We restore the usage
of the set based matching to boost performance.
Building the regexp is still consuming a large amount of time (actually, the
majority of the time), which is still silly. Maybe using re2 would help that,
but this is a quest for another adventure.
Another path to improve this is to have a pattern type dedicated to match the
exact path to a file only (not a directory). This pattern could use the set
matching only and be skipped in the regex all together.
Benchmarks
==========
In the following benchmark we are comparing the `hg cat` and `hg files` run
time when matching against all files in the repository. They are
run:
- without the rust extensions
- with the standard python engine (so without re2)
Performance improvement in this series
--------------------------------------
###### hg files ###############################################################
### mercurial-2018-08-01-zstd-sparse-revlog ### sorted
base-changeset: 0.230092 seconds
prev-changeset: 0.230069 seconds
this-changeset: 0.211425 seconds (-8.36%)
### mercurial-2018-08-01-zstd-sparse-revlog ### shuffled
base-changeset: 0.234235 seconds
prev-changeset: 0.231165 seconds (-1.38%)
this-changeset: 0.212300 seconds (-9.43%)
### pypy-2018-08-01-zstd-sparse-revlog ### sorted
base-changeset: 0.613567 seconds
prev-changeset: 0.616799 seconds
this-changeset: 0.510852 seconds (-16.82%)
### pypy-2018-08-01-zstd-sparse-revlog ### shuffled
base-changeset: 0.801880 seconds
prev-changeset: 0.616393 seconds (-23.22%)
this-changeset: 0.511903 seconds (-36.23%)
### netbeans-2018-08-01-zstd-sparse-revlog ### sorted
base-changeset: 21.541828 seconds
prev-changeset: 21.586773 seconds
this-changeset: 13.648347 seconds (-36.76%)
### netbeans-2018-08-01-zstd-sparse-revlog ### shuffled
base-changeset: 172.759857 seconds
prev-changeset: 21.908197 seconds (-87.32%)
this-changeset: 13.945110 seconds (-91.93%)
### mozilla-central-2018-08-01-zstd-sparse-revlog ### sorted
base-changeset: 62.474221 seconds
prev-changeset: 61.279490 seconds (-1.22%)
this-changeset: 29.529469 seconds (-52.40%)
### mozilla-central-2018-08-01-zstd-sparse-revlog ### shuffled
base-changeset: 1364.180218 seconds
prev-changeset: 62.473549 seconds (-95.40%)
this-changeset: 30.625249 seconds (-97.75%)
###### hg cat #################################################################
### mercurial-2018-08-01-zstd-sparse-revlog ### sorted
base-changeset: 0.764407 seconds
prev-changeset: 0.763883 seconds
this-changeset: 0.737326 seconds (-3.68%)
### mercurial-2018-08-01-zstd-sparse-revlog ### shuffled
base-changeset: 0.768924 seconds
prev-changeset: 0.765848 seconds
this-changeset: 0.174d0b seconds (-4.44%)
### pypy-2018-08-01-zstd-sparse-revlog ### sorted
base-changeset: 2.065220 seconds
prev-changeset: 2.070498 seconds
this-changeset: 1.939482 seconds (-6.08%)
### pypy-2018-08-01-zstd-sparse-revlog ### shuffled
base-changeset: 2.276388 seconds
prev-changeset: 2.069197 seconds (-9.15%)
this-changeset: 1.931746 seconds (-15.19%)
### netbeans-2018-08-01-zstd-sparse-revlog ### sorted
base-changeset: 40.967983 seconds
prev-changeset: 41.392423 seconds
this-changeset: 32.181681 seconds (-22.20%)
### netbeans-2018-08-01-zstd-sparse-revlog ### shuffled
base-changeset: 216.388709 seconds
prev-changeset: 41.648689 seconds (-80.88%)
this-changeset: 32.580817 seconds (-85.04%)
### mozilla-central-2018-08-01-zstd-sparse-revlog ### sorted
base-changeset: 105.228510 seconds
prev-changeset: 103.315670 seconds (-1.23%)
this-changeset: 69.416118 seconds (-33.64%)
### mozilla-central-2018-08-01-zstd-sparse-revlog ### shuffled
base-changeset: 1448.722784 seconds
prev-changeset: 104.369358 seconds (-92.80%)
this-changeset: 70.554789 seconds (-95.13%)
Different way to list the same data with this revision
------------------------------------------------------
###### hg files ###############################################################
### mercurial-2018-08-01-zstd-sparse-revlog
root: 0.119182 seconds
glob: 0.120697 seconds (+1.27%)
sorted: 0.211425 seconds (+77.40%)
shuffled: 0.212300 seconds (+78.13%)
### pypy-2018-08-01-zstd-sparse-revlog
root: 0.121986 seconds
glob: 0.124822 seconds (+2.32%)
sorted: 0.510852 seconds (+318.78%)
shuffled: 0.511903 seconds (+319.64%)
### netbeans-2018-08-01-zstd-sparse-revlog
root: 0.173984 seconds
glob: 0.227203 seconds (+30.59%)
sorted: 13.648347 seconds (+7744.59%)
shuffled: 13.945110 seconds (+7915.16%)
### mozilla-central-2018-08-01-zstd-sparse-revlog
root: 0.366463 seconds
glob: 0.491030 seconds (+33.99%)
sorted: 29.529469 seconds (+7957.96%)
shuffled: 30.625249 seconds (+8256.97%)
###### hg cat #################################################################
### mercurial-2018-08-01-zstd-sparse-revlog
glob: 0.647471 seconds
root: 0.643120 seconds
shuffled: 0.174d0b seconds (+13.92%)
sorted: 0.737326 seconds (+13.88%)
### mozilla-central-2018-08-01-zstd-sparse-revlog
glob: 40.596983 seconds
root: 40.129136 seconds
shuffled: 70.554789 seconds (+73.79%)
sorted: 69.416118 seconds (+70.99%)
### netbeans-2018-08-01-zstd-sparse-revlog
glob: 18.777924 seconds
root: 18.613905 seconds
shuffled: 32.580817 seconds (+73.51%)
sorted: 32.181681 seconds (+71.38%)
### pypy-2018-08-01-zstd-sparse-revlog
glob: 1.555319 seconds
root: 1.536534 seconds
shuffled: 1.931746 seconds (+24.20%)
sorted: 1.939482 seconds (+24.70%)
author | Pierre-Yves David <pierre-yves.david@octobus.net> |
---|---|
date | Sat, 01 Apr 2023 05:58:59 +0200 |
parents | 35ebe6f824be |
children | 4c5f6e95df84 |
line wrap: on
line source
// ancestors.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::ancestors` module provided by the //! `hg-core` crate. From Python, this will be seen as `rustext.ancestor` //! and can be used as replacement for the the pure `ancestor` Python module. //! //! # Classes visible from Python: //! - [`LazyAncestors`] is the Rust implementation of //! `mercurial.ancestor.lazyancestors`. The only difference is that it is //! instantiated with a C `parsers.index` instance instead of a parents //! function. //! //! - [`MissingAncestors`] is the Rust implementation of //! `mercurial.ancestor.incrementalmissingancestors`. //! //! API differences: //! + it is instantiated with a C `parsers.index` //! instance instead of a parents function. //! + `MissingAncestors.bases` is a method returning a tuple instead of //! a set-valued attribute. We could return a Python set easily if our //! [PySet PR](https://github.com/dgrunwald/rust-cpython/pull/165) //! is accepted. //! //! - [`AncestorsIterator`] is the Rust counterpart of the //! `ancestor._lazyancestorsiter` Python generator. From Python, instances of //! this should be mainly obtained by calling `iter()` on a [`LazyAncestors`] //! instance. //! //! [`LazyAncestors`]: struct.LazyAncestors.html //! [`MissingAncestors`]: struct.MissingAncestors.html //! [`AncestorsIterator`]: struct.AncestorsIterator.html use crate::revlog::pyindex_to_graph; use crate::{ cindex::Index, conversion::rev_pyiter_collect, exceptions::GraphError, }; use cpython::{ ObjectProtocol, PyClone, PyDict, PyList, PyModule, PyObject, PyResult, Python, PythonObject, ToPyObject, }; use hg::MissingAncestors as CoreMissing; use hg::Revision; use std::cell::RefCell; use std::collections::HashSet; use vcsgraph::lazy_ancestors::{ AncestorsIterator as VCGAncestorsIterator, LazyAncestors as VCGLazyAncestors, }; py_class!(pub class AncestorsIterator |py| { data inner: RefCell<Box<VCGAncestorsIterator<Index>>>; def __next__(&self) -> PyResult<Option<Revision>> { match self.inner(py).borrow_mut().next() { Some(Err(e)) => Err(GraphError::pynew_from_vcsgraph(py, e)), None => Ok(None), Some(Ok(r)) => Ok(Some(r)), } } def __contains__(&self, rev: Revision) -> PyResult<bool> { self.inner(py).borrow_mut().contains(rev) .map_err(|e| GraphError::pynew_from_vcsgraph(py, e)) } def __iter__(&self) -> PyResult<Self> { Ok(self.clone_ref(py)) } def __new__(_cls, index: PyObject, initrevs: PyObject, stoprev: Revision, inclusive: bool) -> PyResult<AncestorsIterator> { let initvec: Vec<Revision> = rev_pyiter_collect(py, &initrevs)?; let ait = VCGAncestorsIterator::new( pyindex_to_graph(py, index)?, initvec, stoprev, inclusive, ) .map_err(|e| GraphError::pynew_from_vcsgraph(py, e))?; AncestorsIterator::from_inner(py, ait) } }); impl AncestorsIterator { pub fn from_inner( py: Python, ait: VCGAncestorsIterator<Index>, ) -> PyResult<Self> { Self::create_instance(py, RefCell::new(Box::new(ait))) } } py_class!(pub class LazyAncestors |py| { data inner: RefCell<Box<VCGLazyAncestors<Index>>>; def __contains__(&self, rev: Revision) -> PyResult<bool> { self.inner(py) .borrow_mut() .contains(rev) .map_err(|e| GraphError::pynew_from_vcsgraph(py, e)) } def __iter__(&self) -> PyResult<AncestorsIterator> { AncestorsIterator::from_inner(py, self.inner(py).borrow().iter()) } def __bool__(&self) -> PyResult<bool> { Ok(!self.inner(py).borrow().is_empty()) } def __new__(_cls, index: PyObject, initrevs: PyObject, stoprev: Revision, inclusive: bool) -> PyResult<Self> { let initvec: Vec<Revision> = rev_pyiter_collect(py, &initrevs)?; let lazy = VCGLazyAncestors::new(pyindex_to_graph(py, index)?, initvec, stoprev, inclusive) .map_err(|e| GraphError::pynew_from_vcsgraph(py, e))?; Self::create_instance(py, RefCell::new(Box::new(lazy))) } }); py_class!(pub class MissingAncestors |py| { data inner: RefCell<Box<CoreMissing<Index>>>; def __new__( _cls, index: PyObject, bases: PyObject ) -> PyResult<MissingAncestors> { let bases_vec: Vec<Revision> = rev_pyiter_collect(py, &bases)?; let inner = CoreMissing::new(pyindex_to_graph(py, index)?, bases_vec); MissingAncestors::create_instance(py, RefCell::new(Box::new(inner))) } def hasbases(&self) -> PyResult<bool> { Ok(self.inner(py).borrow().has_bases()) } def addbases(&self, bases: PyObject) -> PyResult<PyObject> { let mut inner = self.inner(py).borrow_mut(); let bases_vec: Vec<Revision> = rev_pyiter_collect(py, &bases)?; inner.add_bases(bases_vec); // cpython doc has examples with PyResult<()> but this gives me // the trait `cpython::ToPyObject` is not implemented for `()` // so let's return an explicit None Ok(py.None()) } def bases(&self) -> PyResult<HashSet<Revision>> { Ok(self.inner(py).borrow().get_bases().clone()) } def basesheads(&self) -> PyResult<HashSet<Revision>> { let inner = self.inner(py).borrow(); inner.bases_heads().map_err(|e| GraphError::pynew(py, e)) } def removeancestorsfrom(&self, revs: PyObject) -> PyResult<PyObject> { let mut inner = self.inner(py).borrow_mut(); // this is very lame: we convert to a Rust set, update it in place // and then convert back to Python, only to have Python remove the // excess (thankfully, Python is happy with a list or even an iterator) // Leads to improve this: // - have the CoreMissing instead do something emit revisions to // discard // - define a trait for sets of revisions in the core and implement // it for a Python set rewrapped with the GIL marker let mut revs_pyset: HashSet<Revision> = rev_pyiter_collect(py, &revs)?; inner.remove_ancestors_from(&mut revs_pyset) .map_err(|e| GraphError::pynew(py, e))?; // convert as Python list let mut remaining_pyint_vec: Vec<PyObject> = Vec::with_capacity( revs_pyset.len()); for rev in revs_pyset { remaining_pyint_vec.push(rev.to_py_object(py).into_object()); } let remaining_pylist = PyList::new(py, remaining_pyint_vec.as_slice()); revs.call_method(py, "intersection_update", (remaining_pylist, ), None) } def missingancestors(&self, revs: PyObject) -> PyResult<PyList> { let mut inner = self.inner(py).borrow_mut(); let revs_vec: Vec<Revision> = rev_pyiter_collect(py, &revs)?; let missing_vec = match inner.missing_ancestors(revs_vec) { Ok(missing) => missing, Err(e) => { return Err(GraphError::pynew(py, e)); } }; // convert as Python list let mut missing_pyint_vec: Vec<PyObject> = Vec::with_capacity( missing_vec.len()); for rev in missing_vec { missing_pyint_vec.push(rev.to_py_object(py).into_object()); } Ok(PyList::new(py, missing_pyint_vec.as_slice())) } }); /// Create the module, with __package__ given from parent pub fn init_module(py: Python, package: &str) -> PyResult<PyModule> { let dotted_name = &format!("{}.ancestor", package); let m = PyModule::new(py, dotted_name)?; m.add(py, "__package__", package)?; m.add( py, "__doc__", "Generic DAG ancestor algorithms - Rust implementation", )?; m.add_class::<AncestorsIterator>(py)?; m.add_class::<LazyAncestors>(py)?; m.add_class::<MissingAncestors>(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) }