Mercurial > hg
view tests/f @ 42621:99ebde4fec99
commit: improve the files field of changelog for merges
Currently, the files list of merge commits repeats all the deletions
(either actual deletions, or files that got renamed) that happened
between base and p2 of the merge. If p2 is the main branch, the list
can easily be much bigger than the change being merged.
This results in various problems worth improving:
- changelog is bigger than necessary
- `hg log directory` lists many unrelated merge commits, and `hg log
-v -r commit` frequently fills multiple screens worth of files
- it possibly slows down adjustlinkrev, by forcing it to read more
manifests, and that function can certainly be a bottleneck
- the server side of pulls can waste a lot of time simply opening the
filelogs for pointless files (the constant factors for opening even
a tiny filelog is apparently pretty bad)
So stop listing such files as described in the code. Impacted merge
commits and their descendants get a different hash than they would
have without this. This doesn't seem problematic, except for
convert. The previous commit helped with that in the hg->hg case (but
if you do svn->hg twice from scratch, hashes can still change).
The rest of the description is numbers. I don't have much to report,
because recreating the files list of existing repositories is not
easy:
- debugupgradeformat and bundle/unbundle don't recreate the list
- export/import tends to choke quickly applying patches or on
description that contain diffs,
- merge commits from the convert extension don't have the right files
list for reasons orthogonal to the current commit
- replaying the merge with hg update/hg merge/hg revert --all/hg
commit can end up failing in hg revert
- I wasn't sure that using debugsetparents + debugrebuilddirstate
would really build the right thing
I measured commit time before and after this change, in a case with no
files filtered out, several files filtered out (no difference) and 5k
files filtered out (+1% time).
Recreating the 100 more recent merges in a private repo, the
concatenated uncompressed files lists goes from 1.12MB to
0.52MB. Excluding 3 merges that are not representative, then the size
goes from 570k to 15k.
I converted part of mozilla-central, and observed file list shrinking
quite a bit too, starting at the very first merge, 733641d9feaf, going
from 550 files to 10 files (although they have relatively few merges,
so they probably wouldn't care).
Differential Revision: https://phab.mercurial-scm.org/D6613
author | Valentin Gatien-Baron <valentin.gatienbaron@gmail.com> |
---|---|
date | Tue, 02 Jul 2019 12:59:58 -0400 |
parents | da1629c7dda1 |
children | 47ef023d0165 |
line wrap: on
line source
#!/usr/bin/env python """ Utility for inspecting files in various ways. This tool is like the collection of tools found in a unix environment but are cross platform and stable and suitable for our needs in the test suite. This can be used instead of tools like: [ dd find head hexdump ls md5sum readlink sha1sum stat tail test readlink.py md5sum.py """ from __future__ import absolute_import import binascii import glob import hashlib import optparse import os import re import sys # Python 3 adapters ispy3 = (sys.version_info[0] >= 3) if ispy3: def iterbytes(s): for i in range(len(s)): yield s[i:i + 1] else: iterbytes = iter def visit(opts, filenames, outfile): """Process filenames in the way specified in opts, writing output to outfile.""" for f in sorted(filenames): isstdin = f == '-' if not isstdin and not os.path.lexists(f): outfile.write(b'%s: file not found\n' % f.encode('utf-8')) continue quiet = opts.quiet and not opts.recurse or isstdin isdir = os.path.isdir(f) islink = os.path.islink(f) isfile = os.path.isfile(f) and not islink dirfiles = None content = None facts = [] if isfile: if opts.type: facts.append(b'file') if any((opts.hexdump, opts.dump, opts.md5, opts.sha1, opts.sha256)): with open(f, 'rb') as fobj: content = fobj.read() elif islink: if opts.type: facts.append(b'link') content = os.readlink(f).encode('utf8') elif isstdin: content = getattr(sys.stdin, 'buffer', sys.stdin).read() if opts.size: facts.append(b'size=%d' % len(content)) elif isdir: if opts.recurse or opts.type: dirfiles = glob.glob(f + '/*') facts.append(b'directory with %d files' % len(dirfiles)) elif opts.type: facts.append(b'type unknown') if not isstdin: stat = os.lstat(f) if opts.size and not isdir: facts.append(b'size=%d' % stat.st_size) if opts.mode and not islink: facts.append(b'mode=%o' % (stat.st_mode & 0o777)) if opts.links: facts.append(b'links=%d' % stat.st_nlink) if opts.newer: # mtime might be in whole seconds so newer file might be same if stat.st_mtime >= os.stat(opts.newer).st_mtime: facts.append(b'newer than %s' % opts.newer.encode( 'utf8', 'replace')) else: facts.append(b'older than %s' % opts.newer.encode( 'utf8', 'replace')) if opts.md5 and content is not None: h = hashlib.md5(content) facts.append(b'md5=%s' % binascii.hexlify(h.digest())[:opts.bytes]) if opts.sha1 and content is not None: h = hashlib.sha1(content) facts.append(b'sha1=%s' % binascii.hexlify(h.digest())[:opts.bytes]) if opts.sha256 and content is not None: h = hashlib.sha256(content) facts.append(b'sha256=%s' % binascii.hexlify(h.digest())[:opts.bytes]) if isstdin: outfile.write(b', '.join(facts) + b'\n') elif facts: outfile.write(b'%s: %s\n' % (f.encode('utf-8'), b', '.join(facts))) elif not quiet: outfile.write(b'%s:\n' % f.encode('utf-8')) if content is not None: chunk = content if not islink: if opts.lines: if opts.lines >= 0: chunk = b''.join(chunk.splitlines(True)[:opts.lines]) else: chunk = b''.join(chunk.splitlines(True)[opts.lines:]) if opts.bytes: if opts.bytes >= 0: chunk = chunk[:opts.bytes] else: chunk = chunk[opts.bytes:] if opts.hexdump: for i in range(0, len(chunk), 16): s = chunk[i:i + 16] outfile.write(b'%04x: %-47s |%s|\n' % (i, b' '.join( b'%02x' % ord(c) for c in iterbytes(s)), re.sub(b'[^ -~]', b'.', s))) if opts.dump: if not quiet: outfile.write(b'>>>\n') outfile.write(chunk) if not quiet: if chunk.endswith(b'\n'): outfile.write(b'<<<\n') else: outfile.write(b'\n<<< no trailing newline\n') if opts.recurse and dirfiles: assert not isstdin visit(opts, dirfiles, outfile) if __name__ == "__main__": parser = optparse.OptionParser("%prog [options] [filenames]") parser.add_option("-t", "--type", action="store_true", help="show file type (file or directory)") parser.add_option("-m", "--mode", action="store_true", help="show file mode") parser.add_option("-l", "--links", action="store_true", help="show number of links") parser.add_option("-s", "--size", action="store_true", help="show size of file") parser.add_option("-n", "--newer", action="store", help="check if file is newer (or same)") parser.add_option("-r", "--recurse", action="store_true", help="recurse into directories") parser.add_option("-S", "--sha1", action="store_true", help="show sha1 hash of the content") parser.add_option("", "--sha256", action="store_true", help="show sha256 hash of the content") parser.add_option("-M", "--md5", action="store_true", help="show md5 hash of the content") parser.add_option("-D", "--dump", action="store_true", help="dump file content") parser.add_option("-H", "--hexdump", action="store_true", help="hexdump file content") parser.add_option("-B", "--bytes", type="int", help="number of characters to dump") parser.add_option("-L", "--lines", type="int", help="number of lines to dump") parser.add_option("-q", "--quiet", action="store_true", help="no default output") (opts, filenames) = parser.parse_args(sys.argv[1:]) if not filenames: filenames = ['-'] visit(opts, filenames, getattr(sys.stdout, 'buffer', sys.stdout))