##// END OF EJS Templates
xdiff: add a preprocessing step that trims files...
xdiff: add a preprocessing step that trims files xdiff has a `xdl_trim_ends` step that removes common lines, unmatchable lines. That is in theory good, but happens too late - after splitting, hashing, and adjusting the hash values so they are unique. Those splitting, hashing and adjusting hash values steps could have noticeable overhead. Diffing two large files with minor (one-line-ish) changes are not uncommon. In that case, the raw performance of those preparation steps seriously matter. Even allocating an O(N) array and storing line offsets to it is expensive. Therefore my previous attempts [1] [2] cannot be good enough since they do not remove the O(N) array assignment. This patch adds a preprocessing step - `xdl_trim_files` that runs before other preprocessing steps. It counts common prefix and suffix and lines in them (needed for displaying line number), without doing anything else. Testing with a crafted large (169MB) file, with minor change: ``` open('a','w').write(''.join('%s\n' % (i % 100000) for i in xrange(30000000) if i != 6000000)) open('b','w').write(''.join('%s\n' % (i % 100000) for i in xrange(30000000) if i != 6003000)) ``` Running xdiff by a simple binary [3], this patch improves the xdiff perf by more than 10x for the above case: ``` # xdiff before this patch 2.41s user 1.13s system 98% cpu 3.592 total # xdiff after this patch 0.14s user 0.16s system 98% cpu 0.309 total # gnu diffutils 0.12s user 0.15s system 98% cpu 0.272 total # (best of 20 runs) ``` It's still slightly slower than GNU diffutils. But it's pretty close now. Testing with real repo data: For the whole repo, this patch makes xdiff 25% faster: ``` # hg perfbdiff --count 100 --alldata -c d334afc585e2 --blocks [--xdiff] # xdiff, after ! wall 0.058861 comb 0.050000 user 0.050000 sys 0.000000 (best of 100) # xdiff, before ! wall 0.077816 comb 0.080000 user 0.080000 sys 0.000000 (best of 91) # bdiff ! wall 0.117473 comb 0.120000 user 0.120000 sys 0.000000 (best of 67) ``` For files that are long (ex. commands.py), the speedup is more than 3x, very significant: ``` # hg perfbdiff --count 3000 --blocks commands.py.i 1 [--xdiff] # xdiff, after ! wall 0.690583 comb 0.690000 user 0.690000 sys 0.000000 (best of 12) # xdiff, before ! wall 2.240361 comb 2.210000 user 2.210000 sys 0.000000 (best of 4) # bdiff ! wall 2.469852 comb 2.440000 user 2.440000 sys 0.000000 (best of 4) ``` [1]: https://phab.mercurial-scm.org/D2631 [2]: https://phab.mercurial-scm.org/D2634 [3]: ``` // Code to run xdiff from command line. No proper error handling. #include <stdlib.h> #include <unistd.h> #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> #include "mercurial/thirdparty/xdiff/xdiff.h" #define ensure(x) if (!(x)) exit(255); mmfile_t readfile(const char *path) { struct stat st; int fd = open(path, O_RDONLY); fstat(fd, &st); mmfile_t file = { malloc(st.st_size), st.st_size }; ensure(read(fd, file.ptr, st.st_size) == st.st_size); close(fd); return file; } int main(int argc, char const *argv[]) { mmfile_t a = readfile(argv[1]), b = readfile(argv[2]); xpparam_t xpp = {0}; xdemitconf_t xecfg = {0}; xdemitcb_t ecb = {0}; xdl_diff(&a, &b, &xpp, &xecfg, &ecb); return 0; } ``` Differential Revision: https://phab.mercurial-scm.org/D2686

File last commit:

r35305:f77121b6 default
r36838:f33a87cf default
Show More
dagutil.py
287 lines | 8.2 KiB | text/x-python | PythonLexer
# dagutil.py - dag utilities for mercurial
#
# Copyright 2010 Benoit Boissinot <bboissin@gmail.com>
# and Peter Arrenbrecht <peter@arrenbrecht.ch>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from __future__ import absolute_import
from .i18n import _
from .node import nullrev
class basedag(object):
'''generic interface for DAGs
terms:
"ix" (short for index) identifies a nodes internally,
"id" identifies one externally.
All params are ixs unless explicitly suffixed otherwise.
Pluralized params are lists or sets.
'''
def __init__(self):
self._inverse = None
def nodeset(self):
'''set of all node ixs'''
raise NotImplementedError
def heads(self):
'''list of head ixs'''
raise NotImplementedError
def parents(self, ix):
'''list of parents ixs of ix'''
raise NotImplementedError
def inverse(self):
'''inverse DAG, where parents becomes children, etc.'''
raise NotImplementedError
def ancestorset(self, starts, stops=None):
'''
set of all ancestors of starts (incl), but stop walk at stops (excl)
'''
raise NotImplementedError
def descendantset(self, starts, stops=None):
'''
set of all descendants of starts (incl), but stop walk at stops (excl)
'''
return self.inverse().ancestorset(starts, stops)
def headsetofconnecteds(self, ixs):
'''
subset of connected list of ixs so that no node has a descendant in it
By "connected list" we mean that if an ancestor and a descendant are in
the list, then so is at least one path connecting them.
'''
raise NotImplementedError
def externalize(self, ix):
'''return a node id'''
return self._externalize(ix)
def externalizeall(self, ixs):
'''return a list of (or set if given a set) of node ids'''
ids = self._externalizeall(ixs)
if isinstance(ixs, set):
return set(ids)
return list(ids)
def internalize(self, id):
'''return a node ix'''
return self._internalize(id)
def internalizeall(self, ids, filterunknown=False):
'''return a list of (or set if given a set) of node ixs'''
ixs = self._internalizeall(ids, filterunknown)
if isinstance(ids, set):
return set(ixs)
return list(ixs)
class genericdag(basedag):
'''generic implementations for DAGs'''
def ancestorset(self, starts, stops=None):
if stops:
stops = set(stops)
else:
stops = set()
seen = set()
pending = list(starts)
while pending:
n = pending.pop()
if n not in seen and n not in stops:
seen.add(n)
pending.extend(self.parents(n))
return seen
def headsetofconnecteds(self, ixs):
hds = set(ixs)
if not hds:
return hds
for n in ixs:
for p in self.parents(n):
hds.discard(p)
assert hds
return hds
class revlogbaseddag(basedag):
'''generic dag interface to a revlog'''
def __init__(self, revlog, nodeset):
basedag.__init__(self)
self._revlog = revlog
self._heads = None
self._nodeset = nodeset
def nodeset(self):
return self._nodeset
def heads(self):
if self._heads is None:
self._heads = self._getheads()
return self._heads
def _externalize(self, ix):
return self._revlog.index[ix][7]
def _externalizeall(self, ixs):
idx = self._revlog.index
return [idx[i][7] for i in ixs]
def _internalize(self, id):
ix = self._revlog.rev(id)
if ix == nullrev:
raise LookupError(id, self._revlog.indexfile, _('nullid'))
return ix
def _internalizeall(self, ids, filterunknown):
rl = self._revlog
if filterunknown:
return [r for r in map(rl.nodemap.get, ids)
if (r is not None
and r != nullrev
and r not in rl.filteredrevs)]
return [self._internalize(i) for i in ids]
class revlogdag(revlogbaseddag):
'''dag interface to a revlog'''
def __init__(self, revlog, localsubset=None):
revlogbaseddag.__init__(self, revlog, set(revlog))
self._heads = localsubset
def _getheads(self):
return [r for r in self._revlog.headrevs() if r != nullrev]
def parents(self, ix):
rlog = self._revlog
idx = rlog.index
revdata = idx[ix]
prev = revdata[5]
if prev != nullrev:
prev2 = revdata[6]
if prev2 == nullrev:
return [prev]
return [prev, prev2]
prev2 = revdata[6]
if prev2 != nullrev:
return [prev2]
return []
def inverse(self):
if self._inverse is None:
self._inverse = inverserevlogdag(self)
return self._inverse
def ancestorset(self, starts, stops=None):
rlog = self._revlog
idx = rlog.index
if stops:
stops = set(stops)
else:
stops = set()
seen = set()
pending = list(starts)
while pending:
rev = pending.pop()
if rev not in seen and rev not in stops:
seen.add(rev)
revdata = idx[rev]
for i in [5, 6]:
prev = revdata[i]
if prev != nullrev:
pending.append(prev)
return seen
def headsetofconnecteds(self, ixs):
if not ixs:
return set()
rlog = self._revlog
idx = rlog.index
headrevs = set(ixs)
for rev in ixs:
revdata = idx[rev]
for i in [5, 6]:
prev = revdata[i]
if prev != nullrev:
headrevs.discard(prev)
assert headrevs
return headrevs
def linearize(self, ixs):
'''linearize and topologically sort a list of revisions
The linearization process tries to create long runs of revs where
a child rev comes immediately after its first parent. This is done by
visiting the heads of the given revs in inverse topological order,
and for each visited rev, visiting its second parent, then its first
parent, then adding the rev itself to the output list.
'''
sorted = []
visit = list(self.headsetofconnecteds(ixs))
visit.sort(reverse=True)
finished = set()
while visit:
cur = visit.pop()
if cur < 0:
cur = -cur - 1
if cur not in finished:
sorted.append(cur)
finished.add(cur)
else:
visit.append(-cur - 1)
visit += [p for p in self.parents(cur)
if p in ixs and p not in finished]
assert len(sorted) == len(ixs)
return sorted
class inverserevlogdag(revlogbaseddag, genericdag):
'''inverse of an existing revlog dag; see revlogdag.inverse()'''
def __init__(self, orig):
revlogbaseddag.__init__(self, orig._revlog, orig._nodeset)
self._orig = orig
self._children = {}
self._roots = []
self._walkfrom = len(self._revlog) - 1
def _walkto(self, walkto):
rev = self._walkfrom
cs = self._children
roots = self._roots
idx = self._revlog.index
while rev >= walkto:
data = idx[rev]
isroot = True
for prev in [data[5], data[6]]: # parent revs
if prev != nullrev:
cs.setdefault(prev, []).append(rev)
isroot = False
if isroot:
roots.append(rev)
rev -= 1
self._walkfrom = rev
def _getheads(self):
self._walkto(nullrev)
return self._roots
def parents(self, ix):
if ix is None:
return []
if ix <= self._walkfrom:
self._walkto(ix)
return self._children.get(ix, [])
def inverse(self):
return self._orig