streamclone: use backgroundfilecloser (issue4889)
Closing files that have been appended to is slow on Windows/NTFS.
CloseHandle() calls on this platform often take 1-10ms - and that's
on my i7-6700K Skylake processor with a modern and fast SSD. Contrast
with other I/O operations, such as writing data, which take <100us.
This means that creating/appending thousands of files can add
significant overhead. For example, cloning mozilla-central creates
~232,000 revlog files. Assuming 1ms per CloseHandle(), that yields
232s (3:52) of wall time waiting for file closes!
The impact of this overhead can be measured most directly when applying
stream clone bundles. Applying these files is effectively uncompressing
a tar archive (read: it's very fast).
Using a RAM disk (read: no I/O wait), the difference in wall time for a
`hg debugapplystreamclonebundle` for a ~1731 MB mozilla-central bundle
between Windows and Linux from the same machine is drastic:
Linux: ~12.8s (128MB/s)
Windows: ~352.0s (4.7MB/s)
Windows is ~27.5x slower. Yikes!
After this patch:
Linux: ~12.8s (128MB/s)
Windows: ~102.1s (16.1MB/s)
Windows is now ~3.4x faster. Unfortunately, it is still ~8x slower than
Linux. Profiling reveals a few hot code paths that could likely be
improved. But those are for other patches.
This patch introduces test-clone-uncompressed.t because existing tests
of `clone --uncompressed` are scattered about and adding a variation for
background thread closing to e.g. test-http.t doesn't feel correct.
#!/usr/bin/env python
from __future__ import absolute_import
__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 BaseHTTPServer
import os
import select
import socket
import SocketServer
import urlparse
class ProxyHandler (BaseHTTPServer.BaseHTTPRequestHandler):
__base = BaseHTTPServer.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)]))
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(socket.AF_INET, socket.SOCK_STREAM)
try:
if self._connect_to(self.path, soc):
self.log_request(200)
self.wfile.write(self.protocol_version +
" 200 Connection established\r\n")
self.wfile.write("Proxy-agent: %s\r\n" % self.version_string())
self.wfile.write("\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) = urlparse.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(socket.AF_INET, socket.SOCK_STREAM)
try:
if self._connect_to(netloc, soc):
self.log_request()
soc.send("%s %s %s\r\n" % (
self.command,
urlparse.urlunparse(('', '', path, params, query, '')),
self.request_version))
self.headers['Connection'] = 'close'
del self.headers['Proxy-Connection']
for key_val in self.headers.items():
soc.send("%s: %s\r\n" % key_val)
soc.send("\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,
BaseHTTPServer.HTTPServer):
def __init__(self, *args, **kwargs):
BaseHTTPServer.HTTPServer.__init__(self, *args, **kwargs)
a = open("proxy.pid", "w")
a.write(str(os.getpid()) + "\n")
a.close()
if __name__ == '__main__':
from sys import 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..."
BaseHTTPServer.test(ProxyHandler, ThreadingHTTPServer)