largefiles: synchronize lfdirstate with dirstate after automated committing
Before this patch, after successful "hg rebase" of the revision
removing largefiles, "hg status" may still show ""R" for such
largefiles unexpectedly.
"lfilesrepo.commit" executes the special code path for automated
committing while rebase/transplant, and lfdirstate entries for removed
files aren't updated in this code path, even after successful
committing.
Then, "R" entries still existing in lfdirstate cause unexpected "hg
status" output.
This patch synchronizes lfdirstate with dirstate after automated
committing.
This patch passes False as "normallookup" to "synclfdirstate", because
modified files in "files()" of the recent (= just committed) context
should be "normal"-ed.
This is a temporary way to fix with less changes. For fundamental
resolution of this kind of problems in the future, lfdirstate should
be updated with dirstate simultaneously. Hooking "markcommitted" of
ctx in "localrepository.commitctx" may achieve this.
This problem occurs, only when (1) the parent of the working directory
is rebased and (2) it removes largefiles, because:
- if the parent of the working directory isn't rebased, returning to
the initial revision (= update) after rebase hides this problem
- files added on "other" branch (= rebase target) are treated not as
"added" but as "modified" (= "normal" status and "unset"
timestamp) at merging
This patch tests also the status of added largefile, but it is only
for avoiding regression.
In addition to conditions above, "hg status" must not take existing
files to reproduce this problem, because existing files make
"match._files" not empty in "lfilesrepo.status" code path below:
def sfindirstate(f):
sf = lfutil.standin(f)
dirstate = self.dirstate
return sf in dirstate or sf in dirstate.dirs()
match._files = [f for f in match._files
if sfindirstate(f)]
Not empty "match._files" prevents "status" on lfdirstate from
returning the result containing problematic "R" files.
This is reason why "large1" (removed) and "largeX" (added) are checked
separately in this patch.
Problematic code path in "lfilesrepo.commit" is used also by "hg
transplant", but this problem doesn't occur at "hg transplant",
because invocation of "updatelfiles" after transplant-ing in
"overridetransplant" causes cleaning lfdirstate up.
This patch tests also "hg transplant" as same as "hg rebase", but it
is only for avoiding regression.
# worker.py - master-slave parallelism support
#
# Copyright 2013 Facebook, Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from i18n import _
import errno, os, signal, sys, threading
import util
def countcpus():
'''try to count the number of CPUs on the system'''
# posix
try:
n = int(os.sysconf('SC_NPROCESSORS_ONLN'))
if n > 0:
return n
except (AttributeError, ValueError):
pass
# windows
try:
n = int(os.environ['NUMBER_OF_PROCESSORS'])
if n > 0:
return n
except (KeyError, ValueError):
pass
return 1
def _numworkers(ui):
s = ui.config('worker', 'numcpus')
if s:
try:
n = int(s)
if n >= 1:
return n
except ValueError:
raise util.Abort(_('number of cpus must be an integer'))
return min(max(countcpus(), 4), 32)
if os.name == 'posix':
_startupcost = 0.01
else:
_startupcost = 1e30
def worthwhile(ui, costperop, nops):
'''try to determine whether the benefit of multiple processes can
outweigh the cost of starting them'''
linear = costperop * nops
workers = _numworkers(ui)
benefit = linear - (_startupcost * workers + linear / workers)
return benefit >= 0.15
def worker(ui, costperarg, func, staticargs, args):
'''run a function, possibly in parallel in multiple worker
processes.
returns a progress iterator
costperarg - cost of a single task
func - function to run
staticargs - arguments to pass to every invocation of the function
args - arguments to split into chunks, to pass to individual
workers
'''
if worthwhile(ui, costperarg, len(args)):
return _platformworker(ui, func, staticargs, args)
return func(*staticargs + (args,))
def _posixworker(ui, func, staticargs, args):
rfd, wfd = os.pipe()
workers = _numworkers(ui)
oldhandler = signal.getsignal(signal.SIGINT)
signal.signal(signal.SIGINT, signal.SIG_IGN)
pids, problem = [], [0]
for pargs in partition(args, workers):
pid = os.fork()
if pid == 0:
signal.signal(signal.SIGINT, oldhandler)
try:
os.close(rfd)
for i, item in func(*(staticargs + (pargs,))):
os.write(wfd, '%d %s\n' % (i, item))
os._exit(0)
except KeyboardInterrupt:
os._exit(255)
# other exceptions are allowed to propagate, we rely
# on lock.py's pid checks to avoid release callbacks
pids.append(pid)
pids.reverse()
os.close(wfd)
fp = os.fdopen(rfd, 'rb', 0)
def killworkers():
# if one worker bails, there's no good reason to wait for the rest
for p in pids:
try:
os.kill(p, signal.SIGTERM)
except OSError, err:
if err.errno != errno.ESRCH:
raise
def waitforworkers():
for _ in pids:
st = _exitstatus(os.wait()[1])
if st and not problem[0]:
problem[0] = st
killworkers()
t = threading.Thread(target=waitforworkers)
t.start()
def cleanup():
signal.signal(signal.SIGINT, oldhandler)
t.join()
status = problem[0]
if status:
if status < 0:
os.kill(os.getpid(), -status)
sys.exit(status)
try:
for line in fp:
l = line.split(' ', 1)
yield int(l[0]), l[1][:-1]
except: # re-raises
killworkers()
cleanup()
raise
cleanup()
def _posixexitstatus(code):
'''convert a posix exit status into the same form returned by
os.spawnv
returns None if the process was stopped instead of exiting'''
if os.WIFEXITED(code):
return os.WEXITSTATUS(code)
elif os.WIFSIGNALED(code):
return -os.WTERMSIG(code)
if os.name != 'nt':
_platformworker = _posixworker
_exitstatus = _posixexitstatus
def partition(lst, nslices):
'''partition a list into N slices of equal size'''
n = len(lst)
chunk, slop = n / nslices, n % nslices
end = 0
for i in xrange(nslices):
start = end
end = start + chunk
if slop:
end += 1
slop -= 1
yield lst[start:end]