view tests/f @ 30764:e75463e3179f

protocol: send application/mercurial-0.2 responses to capable clients

With this commit, the HTTP transport now parses the X-HgProto-<N>
header to determine what media type and compression engine to use for
responses. So far, we only compress responses that are already being
compressed with zlib today (stream response types to specific
commands). We can expand things to cover additional response types
later.

The practical side-effect of this commit is that non-zlib compression
engines will be used if both ends support them. This means if both
ends have zstd support, zstd - not zlib - will be used to compress
data!

When cloning the mozilla-unified repository between a local HTTP
server and client, the benefits of non-zlib compression are quite
noticeable:

  engine     server CPU (s)   client CPU (s)    bundle size
zlib (l=6)      174.1            283.2         1,148,547,026
zstd (l=1)       99.2            267.3         1,127,513,841
zstd (l=3)      103.1            266.9         1,018,861,363
zstd (l=7)      128.3            269.7           919,190,278
zstd (l=10)     162.0               -            894,547,179
none             95.3            277.2         4,097,566,064

The default zstd compression level is 3. So if you deploy zstd
capable Mercurial to your clients and servers and CPU time on
your server is dominated by "getbundle" requests (clients cloning
and pulling) - and my experience at Mozilla tells me this is often
the case - this commit could drastically reduce your server-side
CPU usage *and* save on bandwidth costs!

Another benefit of this change is that server operators can install
*any* compression engine. While it isn't enabled by default, the
"none" compression engine can now be used to disable wire protocol
compression completely. Previously, commands like "getbundle" always
zlib compressed output, adding considerable overhead to generating
responses. If you are on a high speed network and your server is under
high load, it might be advantageous to trade bandwidth for CPU.
Although, zstd at level 1 doesn't use that much CPU, so I'm not
convinced that disabling compression wholesale is worthwhile. And, my
data seems to indicate a slow down on the client without compression.
I suspect this is due to a lack of buffering resulting in an increase
in socket read() calls and/or the fact we're transferring an extra 3 GB
of data (parsing HTTP chunked transfer and processing extra TCP packets
can add up). This is definitely worth investigating and optimizing. But
since the "none" compressor isn't enabled by default, I'm inclined to
punt on this issue.

This commit introduces tons of tests. Some of these should arguably
have been implemented on previous commits. But it was difficult to
test without the server functionality in place.

#!/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 glob
import hashlib
import optparse
import os
import re
import sys

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('%s: file not found\n' % f)
            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('file')
            if opts.hexdump or opts.dump or opts.md5:
                content = file(f, 'rb').read()
        elif islink:
            if opts.type:
                facts.append('link')
            content = os.readlink(f)
        elif isstdin:
            content = sys.stdin.read()
            if opts.size:
                facts.append('size=%s' % len(content))
        elif isdir:
            if opts.recurse or opts.type:
                dirfiles = glob.glob(f + '/*')
                facts.append('directory with %s files' % len(dirfiles))
        elif opts.type:
            facts.append('type unknown')
        if not isstdin:
            stat = os.lstat(f)
            if opts.size and not isdir:
                facts.append('size=%s' % stat.st_size)
            if opts.mode and not islink:
                facts.append('mode=%o' % (stat.st_mode & 0o777))
            if opts.links:
                facts.append('links=%s' % 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('newer than %s' % opts.newer)
                else:
                    facts.append('older than %s' % opts.newer)
        if opts.md5 and content is not None:
            h = hashlib.md5(content)
            facts.append('md5=%s' % h.hexdigest()[:opts.bytes])
        if opts.sha1 and content is not None:
            h = hashlib.sha1(content)
            facts.append('sha1=%s' % h.hexdigest()[:opts.bytes])
        if isstdin:
            outfile.write(', '.join(facts) + '\n')
        elif facts:
            outfile.write('%s: %s\n' % (f, ', '.join(facts)))
        elif not quiet:
            outfile.write('%s:\n' % f)
        if content is not None:
            chunk = content
            if not islink:
                if opts.lines:
                    if opts.lines >= 0:
                        chunk = ''.join(chunk.splitlines(True)[:opts.lines])
                    else:
                        chunk = ''.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('%04x: %-47s |%s|\n' %
                                  (i, ' '.join('%02x' % ord(c) for c in s),
                                   re.sub('[^ -~]', '.', s)))
            if opts.dump:
                if not quiet:
                    outfile.write('>>>\n')
                outfile.write(chunk)
                if not quiet:
                    if chunk.endswith('\n'):
                        outfile.write('<<<\n')
                    else:
                        outfile.write('\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("-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, sys.stdout)