contrib/hgclient.py

clone: properly exclude rev-branch-cache from post clone cache warming

When adding "CACHE_REV_BRANCH" to "CACHES_ALL" in e51161b12c7e, I did not
expected it to impact the clone steps. However the "CACHES_POST_CLONE" set is
created rather creatively. (we should fix that, but not on stable)

The benchmark caught a quite significant slowdown one hardlink and ssh-stream
clones. Such slow down can be reduced to around ~5% by fully warming the cache
before the clone. However keeping this expensive step away from the clone
operation fully fix the slowdown and preserve the initial intend.


Example slowdow for hardlink clone

### benchmark.name                               = hg.command.clone
  # bin-env-vars.hg.flavor                       = default
  # bin-env-vars.hg.py-re2-module                = default
  # benchmark.variants.explicit-rev              = none
  # benchmark.variants.issue6528                 = default
  # benchmark.variants.protocol                  = local-hardlink
  # benchmark.variants.pulled-delta-reuse-policy = default
  # benchmark.variants.resource-usage            = default
  # benchmark.variants.validate                  = default
 ## data-env-vars.name = netbeans-2018-08-01-zstd-sparse-revlog
6.8.2:  19.799752
6.9rc0: 29.017493  (+46.55%, +9.22)
after:  19.929341

 ## data-env-vars.name = mercurial-public-2018-08-01-zstd-sparse-revlog
6.8.2:  0.468020
6.9rc0: 1.701294 (+263.51%, +1.23)
after:  0.471934

 ## data-env-vars.name = pypy-2024-03-22-zstd-sparse-revlog
6.8.2:  2.397564
6.9rc0: 5.666641 (+137.41%, +3.28)
after:  2.428085

# A minimal client for Mercurial's command server


import io
import os
import re
import signal
import socket
import struct
import subprocess
import sys
import time

if sys.version_info[0] >= 3:
    stdout = sys.stdout.buffer
    stderr = sys.stderr.buffer
    stringio = io.BytesIO

    def bprint(*args):
        # remove b'' as well for ease of test migration
        pargs = [re.sub(br'''\bb(['"])''', br'\1', b'%s' % a) for a in args]
        stdout.write(b' '.join(pargs) + b'\n')

else:
    import cStringIO

    stdout = sys.stdout
    stderr = sys.stderr
    stringio = cStringIO.StringIO
    bprint = print


def connectpipe(path=None, extraargs=()):
    cmdline = [b'hg', b'serve', b'--cmdserver', b'pipe']
    if path:
        cmdline += [b'-R', path]
    cmdline.extend(extraargs)

    def tonative(cmdline):
        if os.name != 'nt':
            return cmdline
        return [arg.decode("utf-8") for arg in cmdline]

    server = subprocess.Popen(
        tonative(cmdline), stdin=subprocess.PIPE, stdout=subprocess.PIPE
    )

    return server


class unixconnection:
    def __init__(self, sockpath):
        self.sock = sock = socket.socket(socket.AF_UNIX)
        sock.connect(sockpath)
        self.stdin = sock.makefile('wb')
        self.stdout = sock.makefile('rb')

    def wait(self):
        self.stdin.close()
        self.stdout.close()
        self.sock.close()


class unixserver:
    def __init__(self, sockpath, logpath=None, repopath=None):
        self.sockpath = sockpath
        cmdline = [b'hg', b'serve', b'--cmdserver', b'unix', b'-a', sockpath]
        if repopath:
            cmdline += [b'-R', repopath]
        if logpath:
            stdout = open(logpath, 'a')
            stderr = subprocess.STDOUT
        else:
            stdout = stderr = None
        self.server = subprocess.Popen(cmdline, stdout=stdout, stderr=stderr)
        # wait for listen()
        while self.server.poll() is None:
            if os.path.exists(sockpath):
                break
            time.sleep(0.1)

    def connect(self):
        return unixconnection(self.sockpath)

    def shutdown(self):
        os.kill(self.server.pid, signal.SIGTERM)
        self.server.wait()


def writeblock(server, data):
    server.stdin.write(struct.pack(b'>I', len(data)))
    server.stdin.write(data)
    server.stdin.flush()


def readchannel(server):
    data = server.stdout.read(5)
    if not data:
        raise EOFError
    channel, length = struct.unpack('>cI', data)
    if channel in b'IL':
        return channel, length
    else:
        return channel, server.stdout.read(length)


def sep(text):
    return text.replace(b'\\', b'/')


def runcommand(
    server, args, output=stdout, error=stderr, input=None, outfilter=lambda x: x
):
    bprint(b'*** runcommand', b' '.join(args))
    stdout.flush()
    server.stdin.write(b'runcommand\n')
    writeblock(server, b'\0'.join(args))

    if not input:
        input = stringio()

    while True:
        ch, data = readchannel(server)
        if ch == b'o':
            output.write(outfilter(data))
            output.flush()
        elif ch == b'e':
            error.write(data)
            error.flush()
        elif ch == b'I':
            writeblock(server, input.read(data))
        elif ch == b'L':
            writeblock(server, input.readline(data))
        elif ch == b'm':
            bprint(b"message: %r" % data)
        elif ch == b'r':
            (ret,) = struct.unpack('>i', data)
            if ret != 0:
                bprint(b' [%d]' % ret)
            return ret
        else:
            bprint(b"unexpected channel %c: %r" % (ch, data))
            if ch.isupper():
                return


def check(func, connect=connectpipe):
    stdout.flush()
    server = connect()
    try:
        return func(server)
    finally:
        server.stdin.close()
        server.wait()


def checkwith(connect=connectpipe, **kwargs):
    def wrap(func):
        return check(func, lambda: connect(**kwargs))

    return wrap