view tests/f @ 44363:f7459da77f23

nodemap: introduce an option to use mmap to read the nodemap mapping

The performance and memory benefit is much greater if we don't have to copy all
the data in memory for each information. So we introduce an option (on by
default) to read the data using mmap.

This changeset is the last one definition the API for index support nodemap
data. (they have to be able to use the mmaping).

Below are some benchmark comparing the best we currently have in 5.3 with the
final step of this series (using the persistent nodemap implementation in
Rust). The benchmark run `hg perfindex` with various revset and the following
variants:

Before:

 * do not use the persistent nodemap
 * use the CPython implementation of the index for nodemap
 * use mmapping of the changelog index

After:

 * use the MixedIndex Rust code, with the NodeTree object for nodemap access
   (still in review)
 * use the persistent nodemap data from disk
 * access the persistent nodemap data through mmap
 * use mmapping of the changelog index

The persistent nodemap greatly speed up  most operation on very large
repositories. Some of the previously very fast lookup end up a bit slower because
the persistent nodemap has to be setup. However the absolute slowdown is very
small and won't matters in the big picture.

Here are some numbers (in seconds) for the reference copy of mozilla-try:

Revset            Before   After     abs-change speedup

-10000:           0.004622 0.005532   0.000910  ×   0.83
-10:              0.000050 0.000132   0.000082  ×   0.37
tip               0.000052 0.000085   0.000033  ×   0.61
0 + (-10000:)     0.028222 0.005337  -0.022885  ×   5.29
0                 0.023521 0.000084  -0.023437  × 280.01
(-10000:) + 0     0.235539 0.005308  -0.230231  ×  44.37
(-10:) + :9       0.232883 0.000180  -0.232703  ×1293.79
(-10000:) + (:99) 0.238735 0.005358  -0.233377  ×  44.55
:99 + (-10000:)   0.317942 0.005593  -0.312349  ×  56.84
:9 + (-10:)       0.313372 0.000179  -0.313193  ×1750.68
:9                0.316450 0.000143  -0.316307  ×2212.93


On smaller repositories, the cost of nodemap related operation is not as big, so
the win is much more modest. Yet it helps shaving a handful of millisecond here
and there.

Here are some numbers (in seconds) for the reference copy of mercurial:

Revset            Before   After     abs-change speedup
-10:              0.000065 0.000097   0.000032  × 0.67
tip               0.000063 0.000078   0.000015  × 0.80
0                 0.000561 0.000079  -0.000482  × 7.10
-10000:           0.004609 0.003648  -0.000961  × 1.26
0 + (-10000:)     0.005023 0.003715  -0.001307  × 1.35
(-10:) + :9       0.002187 0.000108  -0.002079  ×20.25
(-10000:) + 0     0.006252 0.003716  -0.002536  × 1.68
(-10000:) + (:99) 0.006367 0.003707  -0.002660  × 1.71
:9 + (-10:)       0.003846 0.000110  -0.003736  ×34.96
:9                0.003854 0.000099  -0.003755  ×38.92
:99 + (-10000:)   0.007644 0.003778  -0.003866  × 2.02

Differential Revision: https://phab.mercurial-scm.org/D7894

#!/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))