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
#!/usr/bin/env python
from __future__ import absolute_import, print_function
__doc__ = """Tiny HTTP Proxy.
This module implements GET, HEAD, POST, PUT and DELETE methods
on BaseHTTPServer, and behaves as an HTTP proxy. The CONNECT
method is also implemented experimentally, but has not been
tested yet.
Any help will be greatly appreciated. SUZUKI Hisao
"""
__version__ = "0.2.1"
import optparse
import os
import select
import socket
import sys
from mercurial import (
pycompat,
util,
)
httpserver = util.httpserver
socketserver = util.socketserver
urlreq = util.urlreq
if os.environ.get('HGIPV6', '0') == '1':
family = socket.AF_INET6
else:
family = socket.AF_INET
class ProxyHandler (httpserver.basehttprequesthandler):
__base = httpserver.basehttprequesthandler
__base_handle = __base.handle
server_version = "TinyHTTPProxy/" + __version__
rbufsize = 0 # self.rfile Be unbuffered
def handle(self):
(ip, port) = self.client_address
allowed = getattr(self, 'allowed_clients', None)
if allowed is not None and ip not in allowed:
self.raw_requestline = self.rfile.readline()
if self.parse_request():
self.send_error(403)
else:
self.__base_handle()
def log_request(self, code='-', size='-'):
xheaders = [h for h in self.headers.items() if h[0].startswith('x-')]
self.log_message('"%s" %s %s%s',
self.requestline, str(code), str(size),
''.join([' %s:%s' % h for h in sorted(xheaders)]))
# Flush for Windows, so output isn't lost on TerminateProcess()
sys.stdout.flush()
sys.stderr.flush()
def _connect_to(self, netloc, soc):
i = netloc.find(':')
if i >= 0:
host_port = netloc[:i], int(netloc[i + 1:])
else:
host_port = netloc, 80
print("\t" "connect to %s:%d" % host_port)
try: soc.connect(host_port)
except socket.error as arg:
try: msg = arg[1]
except (IndexError, TypeError): msg = arg
self.send_error(404, msg)
return 0
return 1
def do_CONNECT(self):
soc = socket.socket(family, socket.SOCK_STREAM)
try:
if self._connect_to(self.path, soc):
self.log_request(200)
self.wfile.write(pycompat.bytestr(self.protocol_version) +
b" 200 Connection established\r\n")
self.wfile.write(b"Proxy-agent: %s\r\n" %
pycompat.bytestr(self.version_string()))
self.wfile.write(b"\r\n")
self._read_write(soc, 300)
finally:
print("\t" "bye")
soc.close()
self.connection.close()
def do_GET(self):
(scm, netloc, path, params, query, fragment) = urlreq.urlparse(
self.path, 'http')
if scm != 'http' or fragment or not netloc:
self.send_error(400, "bad url %s" % self.path)
return
soc = socket.socket(family, socket.SOCK_STREAM)
try:
if self._connect_to(netloc, soc):
self.log_request()
url = urlreq.urlunparse(('', '', path, params, query, ''))
soc.send(b"%s %s %s\r\n" % (
pycompat.bytestr(self.command),
pycompat.bytestr(url),
pycompat.bytestr(self.request_version)))
self.headers['Connection'] = 'close'
del self.headers['Proxy-Connection']
for key, val in self.headers.items():
soc.send(b"%s: %s\r\n" % (pycompat.bytestr(key),
pycompat.bytestr(val)))
soc.send(b"\r\n")
self._read_write(soc)
finally:
print("\t" "bye")
soc.close()
self.connection.close()
def _read_write(self, soc, max_idling=20):
iw = [self.connection, soc]
ow = []
count = 0
while True:
count += 1
(ins, _, exs) = select.select(iw, ow, iw, 3)
if exs:
break
if ins:
for i in ins:
if i is soc:
out = self.connection
else:
out = soc
try:
data = i.recv(8192)
except socket.error:
break
if data:
out.send(data)
count = 0
else:
print("\t" "idle", count)
if count == max_idling:
break
do_HEAD = do_GET
do_POST = do_GET
do_PUT = do_GET
do_DELETE = do_GET
class ThreadingHTTPServer (socketserver.ThreadingMixIn,
httpserver.httpserver):
def __init__(self, *args, **kwargs):
httpserver.httpserver.__init__(self, *args, **kwargs)
a = open("proxy.pid", "w")
a.write(str(os.getpid()) + "\n")
a.close()
def runserver(port=8000, bind=""):
server_address = (bind, port)
ProxyHandler.protocol_version = "HTTP/1.0"
httpd = ThreadingHTTPServer(server_address, ProxyHandler)
sa = httpd.socket.getsockname()
print("Serving HTTP on", sa[0], "port", sa[1], "...")
try:
httpd.serve_forever()
except KeyboardInterrupt:
print("\nKeyboard interrupt received, exiting.")
httpd.server_close()
sys.exit(0)
if __name__ == '__main__':
argv = sys.argv
if argv[1:] and argv[1] in ('-h', '--help'):
print(argv[0], "[port [allowed_client_name ...]]")
else:
if argv[2:]:
allowed = []
for name in argv[2:]:
client = socket.gethostbyname(name)
allowed.append(client)
print("Accept: %s (%s)" % (client, name))
ProxyHandler.allowed_clients = allowed
del argv[2:]
else:
print("Any clients will be served...")
parser = optparse.OptionParser()
parser.add_option('-b', '--bind', metavar='ADDRESS',
help='Specify alternate bind address '
'[default: all interfaces]', default='')
(options, args) = parser.parse_args()
port = 8000
if len(args) == 1:
port = int(args[0])
runserver(port, options.bind)