sidedatacopies: fast path data fetching if revision has no sidedata
When using the side data mode, we know their won't be any copy information
sidedata. Skipping revision restoration give an important speed boost.
In the future, there will be other user of sidedata, reducing the efficiency of
this. We should consider adding a dedicated flag in revlog V2 to preserve this
optimisation. The current situation is good enough for now.
revision: large amount; added files: large amount; rename small amount;
c3b14617fbd7 9ba6ab77fd29
before: ! wall 2.401569 comb 2.400000 user 2.390000 sys 0.010000 (median of 10)
after: ! wall 1.429294 comb 1.430000 user 1.410000 sys 0.020000 (median of 10)
revision: large amount; added files: small amount; rename small amount;
c3b14617fbd7 f650a9b140d2
before: ! wall 3.519140 comb 3.520000 user 3.470000 sys 0.050000 (median of 10)
after: ! wall 1.963332 comb 1.960000 user 1.960000 sys 0.000000 (median of 10)
revision: large amount; added files: large amount; rename large amount;
08ea3258278e d9fa043f30c0
before: ! wall 0.593880 comb 0.600000 user 0.590000 sys 0.010000 (median of 15)
after: ! wall 0.251679 comb 0.250000 user 0.250000 sys 0.000000 (median of 38)
revision: small amount; added files: large amount; rename large amount;
df6f7a526b60 a83dc6a2d56f
before: ! wall 0.013414 comb 0.020000 user 0.020000 sys 0.000000 (median of 220)
after: ! wall 0.013222 comb 0.020000 user 0.020000 sys 0.000000 (median of 223)
revision: small amount; added files: large amount; rename small amount;
4aa4e1f8e19a 169138063d63
before: ! wall 0.002711 comb 0.000000 user 0.000000 sys 0.000000 (median of 1000)
after: ! wall 0.001631 comb 0.000000 user 0.000000 sys 0.000000 (median of 1000)
revision: small amount; added files: small amount; rename small amount;
4bc173b045a6 964879152e2e
before: ! wall 0.000077 comb 0.000000 user 0.000000 sys 0.000000 (median of 12208)
after: ! wall 0.000078 comb 0.000000 user 0.000000 sys 0.000000 (median of 12012)
revision: medium amount; added files: large amount; rename medium amount;
c95f1ced15f2 2c68e87c3efe
before: ! wall 0.410067 comb 0.410000 user 0.410000 sys 0.000000 (median of 23)
after: ! wall 0.207786 comb 0.200000 user 0.200000 sys 0.000000 (median of 46)
revision: medium amount; added files: medium amount; rename small amount;
d343da0c55a8 d7746d32bf9d
before: ! wall 0.097004 comb 0.090000 user 0.090000 sys 0.000000 (median of 100)
after: ! wall 0.038495 comb 0.030000 user 0.030000 sys 0.000000 (median of 100)
Differential Revision: https://phab.mercurial-scm.org/D7074
#!/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))