outgoing: rework the handling of the `missingroots` case to be faster
The previous implementation was slow, to the point it was taking a significant
amount of `hg bundle --type none-streamv2` call. We rework the code to compute
the same value much faster, making the operation disappear from the `hg bundle
--type none-streamv2` profile. Someone would remark that producing a streamclone
does not requires an `outgoing` object. However that is a matter for another
day. There is other user of `missingroots` (non stream `hg bundle` call for
example), and they will also benefit from this rework.
We implement an old TODO in the process, directly computing the missing and
common attribute as we have most element at hand already.
### benchmark.name = hg.command.bundle
# bin-env-vars.hg.flavor = default
# bin-env-vars.hg.py-re2-module = default
# benchmark.variants.revs = all
# benchmark.variants.type = none-streamv2
## data-env-vars.name = heptapod-public-2024-03-25-zstd-sparse-revlog
before: 7.750458
after: 6.665565 (-14.00%, -1.08)
## data-env-vars.name = mercurial-public-2024-03-22-zstd-sparse-revlog
before: 0.700229
after: 0.496050 (-29.16%, -0.20)
## data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog
before: 346.508952
after: 316.749699 (-8.59%, -29.76)
## data-env-vars.name = pypy-2024-03-22-zstd-sparse-revlog
before: 3.401700
after: 2.915810 (-14.28%, -0.49)
## data-env-vars.name = tryton-public-2024-03-22-zstd-sparse-revlog
before: 1.870798
after: 1.461583 (-21.87%, -0.41)
note: this whole `missingroots` of outgoing has a limited number of callers and
could likely be replace by something simpler (like taking an explicit
"missing_revs" set for example). However this is a wider change and we focus on
a small impact, quick rework that does not change the API for now.
#!/usr/bin/env python3
import os
import signal
import sys
import time
if os.name == 'nt':
import ctypes
_BOOL = ctypes.c_long
_DWORD = ctypes.c_ulong
_UINT = ctypes.c_uint
_HANDLE = ctypes.c_void_p
ctypes.windll.kernel32.CloseHandle.argtypes = [_HANDLE]
ctypes.windll.kernel32.CloseHandle.restype = _BOOL
ctypes.windll.kernel32.GetLastError.argtypes = []
ctypes.windll.kernel32.GetLastError.restype = _DWORD
ctypes.windll.kernel32.OpenProcess.argtypes = [_DWORD, _BOOL, _DWORD]
ctypes.windll.kernel32.OpenProcess.restype = _HANDLE
ctypes.windll.kernel32.TerminateProcess.argtypes = [_HANDLE, _UINT]
ctypes.windll.kernel32.TerminateProcess.restype = _BOOL
ctypes.windll.kernel32.WaitForSingleObject.argtypes = [_HANDLE, _DWORD]
ctypes.windll.kernel32.WaitForSingleObject.restype = _DWORD
def _check(ret, expectederr=None):
if ret == 0:
winerrno = ctypes.GetLastError()
if winerrno == expectederr:
return True
raise ctypes.WinError(winerrno)
def kill(pid, logfn, tryhard=True):
logfn('# Killing daemon process %d' % pid)
PROCESS_TERMINATE = 1
PROCESS_QUERY_INFORMATION = 0x400
SYNCHRONIZE = 0x00100000
WAIT_OBJECT_0 = 0
WAIT_TIMEOUT = 258
WAIT_FAILED = _DWORD(0xFFFFFFFF).value
handle = ctypes.windll.kernel32.OpenProcess(
PROCESS_TERMINATE | SYNCHRONIZE | PROCESS_QUERY_INFORMATION,
False,
pid,
)
if handle is None:
_check(0, 87) # err 87 when process not found
return # process not found, already finished
try:
r = ctypes.windll.kernel32.WaitForSingleObject(handle, 100)
if r == WAIT_OBJECT_0:
pass # terminated, but process handle still available
elif r == WAIT_TIMEOUT:
_check(ctypes.windll.kernel32.TerminateProcess(handle, -1))
elif r == WAIT_FAILED:
_check(0) # err stored in GetLastError()
# TODO?: forcefully kill when timeout
# and ?shorter waiting time? when tryhard==True
r = ctypes.windll.kernel32.WaitForSingleObject(handle, 100)
# timeout = 100 ms
if r == WAIT_OBJECT_0:
pass # process is terminated
elif r == WAIT_TIMEOUT:
logfn('# Daemon process %d is stuck')
elif r == WAIT_FAILED:
_check(0) # err stored in GetLastError()
except: # re-raises
ctypes.windll.kernel32.CloseHandle(handle) # no _check, keep error
raise
_check(ctypes.windll.kernel32.CloseHandle(handle))
else:
def kill(pid, logfn, tryhard=True):
try:
os.kill(pid, 0)
logfn('# Killing daemon process %d' % pid)
os.kill(pid, signal.SIGTERM)
if tryhard:
for i in range(10):
time.sleep(0.05)
os.kill(pid, 0)
else:
time.sleep(0.1)
os.kill(pid, 0)
logfn('# Daemon process %d is stuck - really killing it' % pid)
os.kill(pid, signal.SIGKILL)
except ProcessLookupError:
pass
def killdaemons(pidfile, tryhard=True, remove=False, logfn=None):
if not logfn:
logfn = lambda s: s
# Kill off any leftover daemon processes
try:
pids = []
with open(pidfile) as fp:
for line in fp:
try:
pid = int(line)
if pid <= 0:
raise ValueError
except ValueError:
logfn(
'# Not killing daemon process %s - invalid pid'
% line.rstrip()
)
continue
pids.append(pid)
for pid in pids:
kill(pid, logfn, tryhard)
if remove:
os.unlink(pidfile)
except IOError:
pass
if __name__ == '__main__':
if len(sys.argv) > 1:
(path,) = sys.argv[1:]
else:
path = os.environ["DAEMON_PIDS"]
killdaemons(path, remove=True)