util: lower water mark when removing nodes after cost limit reached
See the inline comment for the reasoning here. This is a pretty
common strategy for garbage collectors, other cache-like primtives.
The performance impact is substantial:
$ hg perflrucachedict --size 4 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 100
! inserts w/ cost limit
! wall 1.659181 comb 1.650000 user 1.650000 sys 0.000000 (best of 7)
! wall 1.722122 comb 1.720000 user 1.720000 sys 0.000000 (best of 6)
! mixed w/ cost limit
! wall 1.139955 comb 1.140000 user 1.140000 sys 0.000000 (best of 9)
! wall 1.182513 comb 1.180000 user 1.180000 sys 0.000000 (best of 9)
$ hg perflrucachedict --size 1000 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 10000
! inserts
! wall 0.679546 comb 0.680000 user 0.680000 sys 0.000000 (best of 15)
! sets
! wall 0.825147 comb 0.830000 user 0.830000 sys 0.000000 (best of 13)
! inserts w/ cost limit
! wall 25.105273 comb 25.080000 user 25.080000 sys 0.000000 (best of 3)
! wall 1.724397 comb 1.720000 user 1.720000 sys 0.000000 (best of 6)
! mixed
! wall 0.807096 comb 0.810000 user 0.810000 sys 0.000000 (best of 13)
! mixed w/ cost limit
! wall 12.104470 comb 12.070000 user 12.070000 sys 0.000000 (best of 3)
! wall 1.190563 comb 1.190000 user 1.190000 sys 0.000000 (best of 9)
$ hg perflrucachedict --size 1000 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 10000 --mixedgetfreq 90
! inserts
! wall 0.711177 comb 0.710000 user 0.710000 sys 0.000000 (best of 14)
! sets
! wall 0.846992 comb 0.850000 user 0.850000 sys 0.000000 (best of 12)
! inserts w/ cost limit
! wall 25.963028 comb 25.960000 user 25.960000 sys 0.000000 (best of 3)
! wall 2.184311 comb 2.180000 user 2.180000 sys 0.000000 (best of 5)
! mixed
! wall 0.728256 comb 0.730000 user 0.730000 sys 0.000000 (best of 14)
! mixed w/ cost limit
! wall 3.174256 comb 3.170000 user 3.170000 sys 0.000000 (best of 4)
! wall 0.773186 comb 0.770000 user 0.770000 sys 0.000000 (best of 13)
$ hg perflrucachedict --size 100000 --gets 1000000 --sets 1000000 --mixed 1000000 --mixedgetfreq 90 --costlimit 5000000
! gets
! wall 1.191368 comb 1.190000 user 1.190000 sys 0.000000 (best of 9)
! wall 1.195304 comb 1.190000 user 1.190000 sys 0.000000 (best of 9)
! inserts
! wall 0.950995 comb 0.950000 user 0.950000 sys 0.000000 (best of 11)
! inserts w/ cost limit
! wall 1.589732 comb 1.590000 user 1.590000 sys 0.000000 (best of 7)
! sets
! wall 1.094941 comb 1.100000 user 1.090000 sys 0.010000 (best of 9)
! mixed
! wall 0.936420 comb 0.940000 user 0.930000 sys 0.010000 (best of 10)
! mixed w/ cost limit
! wall 0.882780 comb 0.870000 user 0.870000 sys 0.000000 (best of 11)
This puts us ~2x slower than caches without cost accounting. And for
read-heavy workloads (the prime use cases for caches), performance is
nearly identical.
In the worst case (pure write workloads with cost accounting enabled),
we're looking at ~1.5us per insert on large caches. That seems "fast
enough."
Differential Revision: https://phab.mercurial-scm.org/D4505
#!/usr/bin/env python
"""dummy SMTP server for use in tests"""
from __future__ import absolute_import
import asyncore
import optparse
import smtpd
import ssl
import sys
import traceback
from mercurial import (
pycompat,
server,
sslutil,
ui as uimod,
)
def log(msg):
sys.stdout.write(msg)
sys.stdout.flush()
class dummysmtpserver(smtpd.SMTPServer):
def __init__(self, localaddr):
smtpd.SMTPServer.__init__(self, localaddr, remoteaddr=None)
def process_message(self, peer, mailfrom, rcpttos, data, **kwargs):
log('%s from=%s to=%s\n' % (peer[0], mailfrom, ', '.join(rcpttos)))
def handle_error(self):
# On Windows, a bad SSL connection sometimes generates a WSAECONNRESET.
# The default handler will shutdown this server, and then both the
# current connection and subsequent ones fail on the client side with
# "No connection could be made because the target machine actively
# refused it". If we eat the error, then the client properly aborts in
# the expected way, and the server is available for subsequent requests.
traceback.print_exc()
class dummysmtpsecureserver(dummysmtpserver):
def __init__(self, localaddr, certfile):
dummysmtpserver.__init__(self, localaddr)
self._certfile = certfile
def handle_accept(self):
pair = self.accept()
if not pair:
return
conn, addr = pair
ui = uimod.ui.load()
try:
# wrap_socket() would block, but we don't care
conn = sslutil.wrapserversocket(conn, ui, certfile=self._certfile)
except ssl.SSLError:
log('%s ssl error\n' % addr[0])
conn.close()
return
smtpd.SMTPChannel(self, conn, addr)
def run():
try:
asyncore.loop()
except KeyboardInterrupt:
pass
def _encodestrsonly(v):
if isinstance(v, type(u'')):
return v.encode('ascii')
return v
def bytesvars(obj):
unidict = vars(obj)
bd = {k.encode('ascii'): _encodestrsonly(v) for k, v in unidict.items()}
if bd[b'daemon_postexec'] is not None:
bd[b'daemon_postexec'] = [
_encodestrsonly(v) for v in bd[b'daemon_postexec']]
return bd
def main():
op = optparse.OptionParser()
op.add_option('-d', '--daemon', action='store_true')
op.add_option('--daemon-postexec', action='append')
op.add_option('-p', '--port', type=int, default=8025)
op.add_option('-a', '--address', default='localhost')
op.add_option('--pid-file', metavar='FILE')
op.add_option('--tls', choices=['none', 'smtps'], default='none')
op.add_option('--certificate', metavar='FILE')
opts, args = op.parse_args()
if opts.tls == 'smtps' and not opts.certificate:
op.error('--certificate must be specified')
addr = (opts.address, opts.port)
def init():
if opts.tls == 'none':
dummysmtpserver(addr)
else:
dummysmtpsecureserver(addr, opts.certificate)
log('listening at %s:%d\n' % addr)
server.runservice(
bytesvars(opts), initfn=init, runfn=run,
runargs=[pycompat.sysexecutable,
pycompat.fsencode(__file__)] + pycompat.sysargv[1:])
if __name__ == '__main__':
main()