##// END OF EJS Templates
manifest: persist the manifestfulltext cache...
manifest: persist the manifestfulltext cache Reconstructing the manifest from the revlog takes time, so much so that there already is a LRU cache to avoid having to load a manifest multiple times. This patch persists that LRU cache in the .hg/cache directory, so we can re-use this cache across hg commands. Commit benchmark (run on Macos 10.13 on a 2017-model Macbook Pro with Core i7 2.9GHz and flash drive), testing without and with patch run 5 times, baseline is r2a227782e754: * committing to an existing file, against the mozilla-central repository. Baseline real time average 1.9692, with patch 1.3786. A new debugcommand "hg debugmanifestfulltextcache" lets you inspect the cache, clear it, or add specific manifest nodeids to it. When calling repo.updatecaches(), the manifest(s) for the working copy parents are added to the cache. The hg perfmanifest command has an additional --clear-disk switch to clear this cache when testing manifest loading performance. Using this command to test performance on the firefox repository for revision f947d902ed91, whose manifest has a delta chain length of 60540, we see: $ hg perfmanifest f947d902ed91 --clear-disk ! wall 0.972253 comb 0.970000 user 0.850000 sys 0.120000 (best of 10) $ hg debugmanifestfulltextcache -a `hg log --debug -r f947d902ed91 | grep manifest | cut -d: -f3` Cache contains 1 manifest entries, in order of most to least recent: id: 0294517df4aad07c70701db43bc7ff24c3ce7dbc, size 25.6 MB Total cache data size 25.6 MB, on-disk 0 bytes $ hg perfmanifest f947d902ed91 ! wall 0.036748 comb 0.040000 user 0.020000 sys 0.020000 (best of 100) Worst-case scenario: a manifest text loaded from a single delta; in the firefox repository manifest node 9a1246ff762e is the chain base for the manifest attached to revision f947d902ed91. Loading this from a full cache file is just as fast as without the cache; the extra node ids ensure a big full cache: $ for node in 9a1246ff762e 1a1922c14a3e 54a31d11a36a 0294517df4aa; do > hgd debugmanifestfulltextcache -a $node > /dev/null > done $ hgd perfmanifest -m 9a1246ff762e ! wall 0.077513 comb 0.080000 user 0.030000 sys 0.050000 (best of 100) $ hgd perfmanifest -m 9a1246ff762e --clear-disk ! wall 0.078547 comb 0.080000 user 0.070000 sys 0.010000 (best of 100)

File last commit:

r35305:f77121b6 default
r38803:0a57945a 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