1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
|
import os
import sys
import time
import logging
import select
from signal import SIGKILL
from gconf import gconf
from syncdutils import update_file
class Monitor(object):
def __init__(self):
self.state = None
def set_state(self, state):
if state == self.state:
return
self.state = state
logging.info('new state: %s' % state)
if getattr(gconf, 'state_file', None):
update_file(gconf.state_file, lambda f: f.write(state + '\n'))
def monitor(self):
argv = sys.argv[:]
for o in ('-N', '--no-daemon', '--monitor'):
while o in argv:
argv.remove(o)
argv.extend(('-N', '-p', ''))
argv.insert(0, os.path.basename(sys.executable))
self.set_state('starting...')
ret = 0
def nwait(p, o=0):
p2, r = os.waitpid(p, o)
if not p2:
return
if os.WIFEXITED(r):
return os.WEXITSTATUS(r)
return 1
conn_timeout = 60
while ret in (0, 1):
logging.info('-' * conn_timeout)
logging.info('starting gsyncd worker')
pr, pw = os.pipe()
cpid = os.fork()
if cpid == 0:
os.close(pr)
os.execv(sys.executable, argv + ['--feedback-fd', str(pw)])
os.close(pw)
t0 = time.time()
so = select.select((pr,), (), (), conn_timeout)[0]
os.close(pr)
if so:
ret = nwait(cpid, os.WNOHANG)
if ret != None:
logging.debug("worker died before establishing connection")
else:
logging.debug("worker seems to be connected (?? racy check)")
while time.time() < t0 + conn_timeout:
ret = nwait(cpid, os.WNOHANG)
if ret != None:
logging.debug("worker died in startup phase")
break
time.sleep(1)
else:
logging.debug("worker not confirmed in %d sec, aborting it" % \
conn_timeout)
os.kill(cpid, SIGKILL)
ret = nwait(cpid)
if ret == None:
self.set_state('OK')
ret = nwait(cpid)
elif ret in (0, 1):
self.set_state('faulty')
time.sleep(10)
self.set_state('inconsistent')
return ret
def monitor():
return Monitor().monitor()
|
