This is an archive of the discontinued Mercurial Phabricator instance.

Differential D9778

reverse-branch-cache: switch to doubling allocating scheme
ClosedPublic

Authored by joerg.sonnenberger on Jan 14 2021, 8:19 PM.

Details

Reviewers
marmoute
pulkit
Group Reviewers
hg-reviewers
Commits
rHG1726a53a8494: reverse-branch-cache: switch to doubling allocating scheme
Summary

In preperation for updating the reverse-branch-cache incrementally
whenever a new changeset comes in, avoid bad performance on resize with
Python 3.7 (and likely other 3.x versions).

Diff Detail

Repository
rHG Mercurial
Lint
Automatic diff as part of commit; lint not applicable.
Unit
Automatic diff as part of commit; unit tests not applicable.

Event Timeline

marmoute accepted this revision.Jan 18 2021, 11:08 AM
marmoute added a subscriber: marmoute.

This is clearer. For extra clarity I would probably use something like:

extendsize = (requiredsize * 2) - rbccur

This give about the same result but is simpler to read.

pulkit accepted this revision.Jan 21 2021, 6:22 AM
This revision is now accepted and ready to land.Jan 21 2021, 6:22 AM

Revision Contents
Changeset List

PathPackages
Mmercurial/branchmap.py (15 lines)

Diff 25191

mercurial/branchmap.py

# Revision branch info cache # Revision branch info cache
_rbcversion = b'-v1' _rbcversion = b'-v1'
_rbcnames = b'rbc-names' + _rbcversion _rbcnames = b'rbc-names' + _rbcversion
_rbcrevs = b'rbc-revs' + _rbcversion _rbcrevs = b'rbc-revs' + _rbcversion
# [4 byte hash prefix][4 byte branch name number with sign bit indicating open] # [4 byte hash prefix][4 byte branch name number with sign bit indicating open]
_rbcrecfmt = b'>4sI' _rbcrecfmt = b'>4sI'
_rbcrecsize = calcsize(_rbcrecfmt) _rbcrecsize = calcsize(_rbcrecfmt)
_rbcmininc = 64 * _rbcrecsize
_rbcnodelen = 4 _rbcnodelen = 4
_rbcbranchidxmask = 0x7FFFFFFF _rbcbranchidxmask = 0x7FFFFFFF
_rbccloseflag = 0x80000000 _rbccloseflag = 0x80000000
class revbranchcache(object): class revbranchcache(object):
"""Persistent cache, mapping from revision number to branch name and close. """Persistent cache, mapping from revision number to branch name and close.
This is a low level cache, independent of filtering. This is a low level cache, independent of filtering.
if 'branchinfo' in vars(self): if 'branchinfo' in vars(self):
del self.branchinfo del self.branchinfo
def _setcachedata(self, rev, node, branchidx): def _setcachedata(self, rev, node, branchidx):
"""Writes the node's branch data to the in-memory cache data.""" """Writes the node's branch data to the in-memory cache data."""
if rev == nullrev: if rev == nullrev:
return return
rbcrevidx = rev * _rbcrecsize rbcrevidx = rev * _rbcrecsize
if len(self._rbcrevs) < rbcrevidx + _rbcrecsize: requiredsize = rbcrevidx + _rbcrecsize
self._rbcrevs.extend( rbccur = len(self._rbcrevs)
b'\0' if rbccur < requiredsize:
* (len(self._repo.changelog) * _rbcrecsize - len(self._rbcrevs)) # bytearray doesn't allocate extra space at least in Python 3.7.
) # When multiple changesets are added in a row, precise resize would
# result in quadratic complexity. Overallocate to compensate by
# use the classic doubling technique for dynamic arrays instead.
# If there was a gap in the map before, less space will be reserved.
self._rbcrevs.extend(b'\0' * max(_rbcmininc, requiredsize))
pack_into(_rbcrecfmt, self._rbcrevs, rbcrevidx, node, branchidx) pack_into(_rbcrecfmt, self._rbcrevs, rbcrevidx, node, branchidx)
self._rbcrevslen = min(self._rbcrevslen, rev) self._rbcrevslen = min(self._rbcrevslen, rev)
tr = self._repo.currenttransaction() tr = self._repo.currenttransaction()
if tr: if tr:
tr.addfinalize(b'write-revbranchcache', self.write) tr.addfinalize(b'write-revbranchcache', self.write)
def write(self, tr=None): def write(self, tr=None):