def is_rate_limit_pass(self, sandesh):
#Check if buffer resize is reqd
if (self.__class__.rate_limit_buffer.maxlen != \
SandeshSystem.get_sandesh_send_rate_limit()):
temp_buffer = copy.deepcopy(self.__class__.rate_limit_buffer)
self.__class__.rate_limit_buffer = util.deque(temp_buffer, \
maxlen=SandeshSystem.get_sandesh_send_rate_limit())
del temp_buffer
#If buffer size 0 return
if self.__class__.rate_limit_buffer.maxlen == 0:
return False
cur_time = int(time.time())
#Check if circular buffer is full
if len(self.__class__.rate_limit_buffer) == \
self.__class__.rate_limit_buffer.maxlen :
# Read the element in buffer and compare with cur_time
if (self.__class__.rate_limit_buffer[0] == cur_time):
#Sender generating more messages/sec than the
#buffer_threshold size
if self.__class__.do_rate_limit_drop_log:
sandesh._logger.error('SANDESH: Ratelimit Drop ' \
'(%d messages/sec): for %s' % \
(self.__class__.rate_limit_buffer.maxlen, \
self.__class__.__name__))
#Disable logging
self.__class__.do_rate_limit_drop_log = False
return False
#If logging is disabled enable it
self.__class__.do_rate_limit_drop_log = True
self.__class__.rate_limit_buffer.append(cur_time)
return True
def __iter__(self):
"""Generate the ancestors of _initrevs in reverse topological order.
If inclusive is False, yield a sequence of revision numbers starting
with the parents of each revision in revs, i.e., each revision is *not*
considered an ancestor of itself. Results are in breadth-first order:
parents of each rev in revs, then parents of those, etc.
If inclusive is True, yield all the revs first (ignoring stoprev),
then yield all the ancestors of revs as when inclusive is False.
If an element in revs is an ancestor of a different rev it is not
yielded again."""
seen = set()
revs = self._initrevs
if self._inclusive:
for rev in revs:
yield rev
seen.update(revs)
parentrevs = self._parentrevs
stoprev = self._stoprev
visit = util.deque(revs)
while visit:
for parent in parentrevs(visit.popleft()):
if parent >= stoprev and parent not in seen:
visit.append(parent)
seen.add(parent)
yield parent
def _updatesample(dag, nodes, sample, always, quicksamplesize=0):
# if nodes is empty we scan the entire graph
if nodes:
heads = dag.headsetofconnecteds(nodes)
else:
heads = dag.heads()
dist = {}
visit = util.deque(heads)
seen = set()
factor = 1
while visit:
curr = visit.popleft()
if curr in seen:
continue
d = dist.setdefault(curr, 1)
if d > factor:
factor *= 2
if d == factor:
if curr not in always: # need this check for the early exit below
sample.add(curr)
if quicksamplesize and (len(sample) >= quicksamplesize):
return
seen.add(curr)
for p in dag.parents(curr):
if not nodes or p in nodes:
dist.setdefault(p, d + 1)
visit.append(p)
def _updatesample(dag, nodes, sample, always, quicksamplesize=0):
# if nodes is empty we scan the entire graph
if nodes:
heads = dag.headsetofconnecteds(nodes)
else:
heads = dag.heads()
dist = {}
visit = util.deque(heads)
seen = set()
factor = 1
while visit:
curr = visit.popleft()
if curr in seen:
continue
d = dist.setdefault(curr, 1)
if d > factor:
factor *= 2
if d == factor:
if curr not in always: # need this check for the early exit below
sample.add(curr)
if quicksamplesize and (len(sample) >= quicksamplesize):
return
seen.add(curr)
for p in dag.parents(curr):
if not nodes or p in nodes:
dist.setdefault(p, d + 1)
visit.append(p)
def is_rate_limit_pass(self,sandesh):
#If buffer size 0 return
if self.__class__.rate_limit_buffer.maxlen == 0:
return False
#Check if buffer resize is reqd
if (self.__class__.rate_limit_buffer.maxlen != \
SandeshSystem.get_sandesh_send_rate_limit()):
temp_buffer = copy.deepcopy(self.__class__.rate_limit_buffer)
self.__class__.rate_limit_buffer = util.deque(temp_buffer, \
maxlen=SandeshSystem.get_sandesh_send_rate_limit())
del temp_buffer
cur_time=int(time.time())
#Check if circular buffer is full
if len(self.__class__.rate_limit_buffer) == \
self.__class__.rate_limit_buffer.maxlen :
# Read the element in buffer and compare with cur_time
if(self.__class__.rate_limit_buffer[0] == cur_time):
#Sender generating more messages/sec than the
#buffer_threshold size
if self.__class__.do_rate_limit_drop_log:
sandesh._logger.error('SANDESH: Ratelimit Drop ' \
'(%d messages/sec): for %s' % \
(self.__class__.rate_limit_buffer.maxlen, \
self.__class__.__name__))
#Disable logging
self.__class__.do_rate_limit_drop_log = False
return False
#If logging is disabled enable it
self.__class__.do_rate_limit_drop_log = True
self.__class__.rate_limit_buffer.append(cur_time)
return True
def __iter__(self):
"""Generate the ancestors of _initrevs in reverse topological order.
If inclusive is False, yield a sequence of revision numbers starting
with the parents of each revision in revs, i.e., each revision is *not*
considered an ancestor of itself. Results are in breadth-first order:
parents of each rev in revs, then parents of those, etc.
If inclusive is True, yield all the revs first (ignoring stoprev),
then yield all the ancestors of revs as when inclusive is False.
If an element in revs is an ancestor of a different rev it is not
yielded again."""
seen = set()
revs = self._initrevs
if self._inclusive:
for rev in revs:
yield rev
seen.update(revs)
parentrevs = self._parentrevs
stoprev = self._stoprev
visit = util.deque(revs)
while visit:
for parent in parentrevs(visit.popleft()):
if parent >= stoprev and parent not in seen:
visit.append(parent)
seen.add(parent)
yield parent
def findcommonmissing(self, common=None, heads=None):
"""Return a tuple of the ancestors of common and the ancestors of heads
that are not ancestors of common. In revset terminology, we return the
tuple:
::common, (::heads) - (::common)
The list is sorted by revision number, meaning it is
topologically sorted.
'heads' and 'common' are both lists of node IDs. If heads is
not supplied, uses all of the revlog's heads. If common is not
supplied, uses nullid."""
if common is None:
common = [nullid]
if heads is None:
heads = self.heads()
common = [self.rev(n) for n in common]
heads = [self.rev(n) for n in heads]
# we want the ancestors, but inclusive
has = set(self.ancestors(common))
has.add(nullrev)
has.update(common)
# take all ancestors from heads that aren't in has
missing = set()
visit = util.deque(r for r in heads if r not in has)
while visit:
r = visit.popleft()
if r in missing:
continue
else:
missing.add(r)
for p in self.parentrevs(r):
if p not in has:
visit.append(p)
missing = list(missing)
missing.sort()
return has, [self.node(r) for r in missing]
def findcommonmissing(self, common=None, heads=None):
"""Return a tuple of the ancestors of common and the ancestors of heads
that are not ancestors of common. In revset terminology, we return the
tuple:
::common, (::heads) - (::common)
The list is sorted by revision number, meaning it is
topologically sorted.
'heads' and 'common' are both lists of node IDs. If heads is
not supplied, uses all of the revlog's heads. If common is not
supplied, uses nullid."""
if common is None:
common = [nullid]
if heads is None:
heads = self.heads()
common = [self.rev(n) for n in common]
heads = [self.rev(n) for n in heads]
# we want the ancestors, but inclusive
has = set(self.ancestors(common))
has.add(nullrev)
has.update(common)
# take all ancestors from heads that aren't in has
missing = set()
visit = util.deque(r for r in heads if r not in has)
while visit:
r = visit.popleft()
if r in missing:
continue
else:
missing.add(r)
for p in self.parentrevs(r):
if p not in has:
visit.append(p)
missing = list(missing)
missing.sort()
return has, [self.node(r) for r in missing]
def _updatesample(dag, nodes, sample, quicksamplesize=0):
"""update an existing sample to match the expected size
The sample is updated with nodes exponentially distant from each head of the
<nodes> set. (H~1, H~2, H~4, H~8, etc).
If a target size is specified, the sampling will stop once this size is
reached. Otherwise sampling will happen until roots of the <nodes> set are
reached.
:dag: a dag object from dagutil
:nodes: set of nodes we want to discover (if None, assume the whole dag)
:sample: a sample to update
:quicksamplesize: optional target size of the sample"""
# if nodes is empty we scan the entire graph
if nodes:
heads = dag.headsetofconnecteds(nodes)
else:
heads = dag.heads()
dist = {}
visit = util.deque(heads)
seen = set()
factor = 1
while visit:
curr = visit.popleft()
if curr in seen:
continue
d = dist.setdefault(curr, 1)
if d > factor:
factor *= 2
if d == factor:
sample.add(curr)
if quicksamplesize and (len(sample) >= quicksamplesize):
return
seen.add(curr)
for p in dag.parents(curr):
if not nodes or p in nodes:
dist.setdefault(p, d + 1)
visit.append(p)
def _updatesample(dag, nodes, sample, quicksamplesize=0):
"""update an existing sample to match the expected size
The sample is updated with nodes exponentially distant from each head of the
<nodes> set. (H~1, H~2, H~4, H~8, etc).
If a target size is specified, the sampling will stop once this size is
reached. Otherwise sampling will happen until roots of the <nodes> set are
reached.
:dag: a dag object from dagutil
:nodes: set of nodes we want to discover (if None, assume the whole dag)
:sample: a sample to update
:quicksamplesize: optional target size of the sample"""
# if nodes is empty we scan the entire graph
if nodes:
heads = dag.headsetofconnecteds(nodes)
else:
heads = dag.heads()
dist = {}
visit = util.deque(heads)
seen = set()
factor = 1
while visit:
curr = visit.popleft()
if curr in seen:
continue
d = dist.setdefault(curr, 1)
if d > factor:
factor *= 2
if d == factor:
sample.add(curr)
if quicksamplesize and (len(sample) >= quicksamplesize):
return
seen.add(curr)
for p in dag.parents(curr):
if not nodes or p in nodes:
dist.setdefault(p, d + 1)
visit.append(p)
def findcommonincoming(repo, remote, heads=None, force=False):
"""Return a tuple (common, fetch, heads) used to identify the common
subset of nodes between repo and remote.
"common" is a list of (at least) the heads of the common subset.
"fetch" is a list of roots of the nodes that would be incoming, to be
supplied to changegroupsubset.
"heads" is either the supplied heads, or else the remote's heads.
"""
knownnode = repo.changelog.hasnode
search = []
fetch = set()
seen = set()
seenbranch = set()
base = set()
if not heads:
heads = remote.heads()
if repo.changelog.tip() == nullid:
base.add(nullid)
if heads != [nullid]:
return [nullid], [nullid], list(heads)
return [nullid], [], heads
# assume we're closer to the tip than the root
# and start by examining the heads
repo.ui.status(_("searching for changes\n"))
unknown = []
for h in heads:
if not knownnode(h):
unknown.append(h)
else:
base.add(h)
if not unknown:
return list(base), [], list(heads)
req = set(unknown)
reqcnt = 0
# search through remote branches
# a 'branch' here is a linear segment of history, with four parts:
# head, root, first parent, second parent
# (a branch always has two parents (or none) by definition)
unknown = util.deque(remote.branches(unknown))
while unknown:
r = []
while unknown:
n = unknown.popleft()
if n[0] in seen:
continue
repo.ui.debug("examining %s:%s\n" % (short(n[0]), short(n[1])))
if n[0] == nullid: # found the end of the branch
pass
elif n in seenbranch:
repo.ui.debug("branch already found\n")
continue
elif n[1] and knownnode(n[1]): # do we know the base?
repo.ui.debug("found incomplete branch %s:%s\n" %
(short(n[0]), short(n[1])))
search.append(n[0:2]) # schedule branch range for scanning
seenbranch.add(n)
else:
if n[1] not in seen and n[1] not in fetch:
if knownnode(n[2]) and knownnode(n[3]):
repo.ui.debug("found new changeset %s\n" % short(n[1]))
fetch.add(n[1]) # earliest unknown
for p in n[2:4]:
if knownnode(p):
base.add(p) # latest known
for p in n[2:4]:
if p not in req and not knownnode(p):
r.append(p)
req.add(p)
seen.add(n[0])
if r:
reqcnt += 1
repo.ui.progress(_('searching'), reqcnt, unit=_('queries'))
repo.ui.debug("request %d: %s\n" %
(reqcnt, " ".join(map(short, r))))
for p in xrange(0, len(r), 10):
for b in remote.branches(r[p:p + 10]):
repo.ui.debug("received %s:%s\n" %
(short(b[0]), short(b[1])))
unknown.append(b)
# do binary search on the branches we found
while search:
newsearch = []
reqcnt += 1
repo.ui.progress(_('searching'), reqcnt, unit=_('queries'))
for n, l in zip(search, remote.between(search)):
l.append(n[1])
p = n[0]
f = 1
for i in l:
repo.ui.debug("narrowing %d:%d %s\n" % (f, len(l), short(i)))
if knownnode(i):
if f <= 2:
repo.ui.debug("found new branch changeset %s\n" %
short(p))
fetch.add(p)
base.add(i)
else:
repo.ui.debug("narrowed branch search to %s:%s\n" %
(short(p), short(i)))
newsearch.append((p, i))
break
p, f = i, f * 2
search = newsearch
# sanity check our fetch list
for f in fetch:
if knownnode(f):
raise error.RepoError(_("already have changeset ") + short(f[:4]))
base = list(base)
if base == [nullid]:
if force:
repo.ui.warn(_("warning: repository is unrelated\n"))
else:
raise util.Abort(_("repository is unrelated"))
repo.ui.debug("found new changesets starting at " +
" ".join([short(f) for f in fetch]) + "\n")
repo.ui.progress(_('searching'), None)
repo.ui.debug("%d total queries\n" % reqcnt)
return base, list(fetch), heads
def findcommonincoming(repo, remote, heads=None, force=False):
"""Return a tuple (common, fetch, heads) used to identify the common
subset of nodes between repo and remote.
"common" is a list of (at least) the heads of the common subset.
"fetch" is a list of roots of the nodes that would be incoming, to be
supplied to changegroupsubset.
"heads" is either the supplied heads, or else the remote's heads.
"""
m = repo.changelog.nodemap
search = []
fetch = set()
seen = set()
seenbranch = set()
base = set()
if not heads:
heads = remote.heads()
if repo.changelog.tip() == nullid:
base.add(nullid)
if heads != [nullid]:
return [nullid], [nullid], list(heads)
return [nullid], [], heads
# assume we're closer to the tip than the root
# and start by examining the heads
repo.ui.status(_("searching for changes\n"))
unknown = []
for h in heads:
if h not in m:
unknown.append(h)
else:
base.add(h)
if not unknown:
return list(base), [], list(heads)
req = set(unknown)
reqcnt = 0
# search through remote branches
# a 'branch' here is a linear segment of history, with four parts:
# head, root, first parent, second parent
# (a branch always has two parents (or none) by definition)
unknown = util.deque(remote.branches(unknown))
while unknown:
r = []
while unknown:
n = unknown.popleft()
if n[0] in seen:
continue
repo.ui.debug("examining %s:%s\n"
% (short(n[0]), short(n[1])))
if n[0] == nullid: # found the end of the branch
pass
elif n in seenbranch:
repo.ui.debug("branch already found\n")
continue
elif n[1] and n[1] in m: # do we know the base?
repo.ui.debug("found incomplete branch %s:%s\n"
% (short(n[0]), short(n[1])))
search.append(n[0:2]) # schedule branch range for scanning
seenbranch.add(n)
else:
if n[1] not in seen and n[1] not in fetch:
if n[2] in m and n[3] in m:
repo.ui.debug("found new changeset %s\n" %
short(n[1]))
fetch.add(n[1]) # earliest unknown
for p in n[2:4]:
if p in m:
base.add(p) # latest known
for p in n[2:4]:
if p not in req and p not in m:
r.append(p)
req.add(p)
seen.add(n[0])
if r:
reqcnt += 1
repo.ui.progress(_('searching'), reqcnt, unit=_('queries'))
repo.ui.debug("request %d: %s\n" %
(reqcnt, " ".join(map(short, r))))
for p in xrange(0, len(r), 10):
for b in remote.branches(r[p:p + 10]):
repo.ui.debug("received %s:%s\n" %
(short(b[0]), short(b[1])))
unknown.append(b)
# do binary search on the branches we found
while search:
newsearch = []
reqcnt += 1
repo.ui.progress(_('searching'), reqcnt, unit=_('queries'))
for n, l in zip(search, remote.between(search)):
l.append(n[1])
p = n[0]
f = 1
for i in l:
repo.ui.debug("narrowing %d:%d %s\n" % (f, len(l), short(i)))
if i in m:
if f <= 2:
repo.ui.debug("found new branch changeset %s\n" %
short(p))
fetch.add(p)
base.add(i)
else:
repo.ui.debug("narrowed branch search to %s:%s\n"
% (short(p), short(i)))
newsearch.append((p, i))
break
p, f = i, f * 2
search = newsearch
# sanity check our fetch list
for f in fetch:
if f in m:
raise error.RepoError(_("already have changeset ")
+ short(f[:4]))
base = list(base)
if base == [nullid]:
if force:
repo.ui.warn(_("warning: repository is unrelated\n"))
else:
raise util.Abort(_("repository is unrelated"))
repo.ui.debug("found new changesets starting at " +
" ".join([short(f) for f in fetch]) + "\n")
repo.ui.progress(_('searching'), None)
repo.ui.debug("%d total queries\n" % reqcnt)
return base, list(fetch), heads
def bisect(changelog, state):
"""find the next node (if any) for testing during a bisect search.
returns a (nodes, number, good) tuple.
'nodes' is the final result of the bisect if 'number' is 0.
Otherwise 'number' indicates the remaining possible candidates for
the search and 'nodes' contains the next bisect target.
'good' is True if bisect is searching for a first good changeset, False
if searching for a first bad one.
"""
clparents = changelog.parentrevs
skip = set([changelog.rev(n) for n in state['skip']])
def buildancestors(bad, good):
# only the earliest bad revision matters
badrev = min([changelog.rev(n) for n in bad])
goodrevs = [changelog.rev(n) for n in good]
goodrev = min(goodrevs)
# build visit array
ancestors = [None] * (len(changelog) + 1) # an extra for [-1]
# set nodes descended from goodrevs
for rev in goodrevs:
ancestors[rev] = []
for rev in changelog.revs(goodrev + 1):
for prev in clparents(rev):
if ancestors[prev] == []:
ancestors[rev] = []
# clear good revs from array
for rev in goodrevs:
ancestors[rev] = None
for rev in changelog.revs(len(changelog), goodrev):
if ancestors[rev] is None:
for prev in clparents(rev):
ancestors[prev] = None
if ancestors[badrev] is None:
return badrev, None
return badrev, ancestors
good = False
badrev, ancestors = buildancestors(state['bad'], state['good'])
if not ancestors: # looking for bad to good transition?
good = True
badrev, ancestors = buildancestors(state['good'], state['bad'])
bad = changelog.node(badrev)
if not ancestors: # now we're confused
if (len(state['bad']) == 1 and len(state['good']) == 1 and
state['bad'] != state['good']):
raise util.Abort(_("starting revisions are not directly related"))
raise util.Abort(_("inconsistent state, %s:%s is good and bad")
% (badrev, short(bad)))
# build children dict
children = {}
visit = util.deque([badrev])
candidates = []
while visit:
rev = visit.popleft()
if ancestors[rev] == []:
candidates.append(rev)
for prev in clparents(rev):
if prev != -1:
if prev in children:
children[prev].append(rev)
else:
children[prev] = [rev]
visit.append(prev)
candidates.sort()
# have we narrowed it down to one entry?
# or have all other possible candidates besides 'bad' have been skipped?
tot = len(candidates)
unskipped = [c for c in candidates if (c not in skip) and (c != badrev)]
if tot == 1 or not unskipped:
return ([changelog.node(rev) for rev in candidates], 0, good)
perfect = tot // 2
# find the best node to test
best_rev = None
best_len = -1
poison = set()
for rev in candidates:
if rev in poison:
# poison children
poison.update(children.get(rev, []))
continue
a = ancestors[rev] or [rev]
ancestors[rev] = None
x = len(a) # number of ancestors
y = tot - x # number of non-ancestors
value = min(x, y) # how good is this test?
if value > best_len and rev not in skip:
best_len = value
best_rev = rev
if value == perfect: # found a perfect candidate? quit early
break
if y < perfect and rev not in skip: # all downhill from here?
# poison children
poison.update(children.get(rev, []))
continue
for c in children.get(rev, []):
if ancestors[c]:
ancestors[c] = list(set(ancestors[c] + a))
else:
ancestors[c] = a + [c]
assert best_rev is not None
best_node = changelog.node(best_rev)
return ([best_node], tot, good)
def bisect(changelog, state):
"""find the next node (if any) for testing during a bisect search.
returns a (nodes, number, good) tuple.
'nodes' is the final result of the bisect if 'number' is 0.
Otherwise 'number' indicates the remaining possible candidates for
the search and 'nodes' contains the next bisect target.
'good' is True if bisect is searching for a first good changeset, False
if searching for a first bad one.
"""
clparents = changelog.parentrevs
skip = set([changelog.rev(n) for n in state['skip']])
def buildancestors(bad, good):
# only the earliest bad revision matters
badrev = min([changelog.rev(n) for n in bad])
goodrevs = [changelog.rev(n) for n in good]
goodrev = min(goodrevs)
# build visit array
ancestors = [None] * (len(changelog) + 1) # an extra for [-1]
# set nodes descended from goodrevs
for rev in goodrevs:
ancestors[rev] = []
for rev in changelog.revs(goodrev + 1):
for prev in clparents(rev):
if ancestors[prev] == []:
ancestors[rev] = []
# clear good revs from array
for rev in goodrevs:
ancestors[rev] = None
for rev in changelog.revs(len(changelog), goodrev):
if ancestors[rev] is None:
for prev in clparents(rev):
ancestors[prev] = None
if ancestors[badrev] is None:
return badrev, None
return badrev, ancestors
good = False
badrev, ancestors = buildancestors(state['bad'], state['good'])
if not ancestors: # looking for bad to good transition?
good = True
badrev, ancestors = buildancestors(state['good'], state['bad'])
bad = changelog.node(badrev)
if not ancestors: # now we're confused
if (len(state['bad']) == 1 and len(state['good']) == 1
and state['bad'] != state['good']):
raise util.Abort(_("starting revisions are not directly related"))
raise util.Abort(
_("inconsistent state, %s:%s is good and bad") %
(badrev, short(bad)))
# build children dict
children = {}
visit = util.deque([badrev])
candidates = []
while visit:
rev = visit.popleft()
if ancestors[rev] == []:
candidates.append(rev)
for prev in clparents(rev):
if prev != -1:
if prev in children:
children[prev].append(rev)
else:
children[prev] = [rev]
visit.append(prev)
candidates.sort()
# have we narrowed it down to one entry?
# or have all other possible candidates besides 'bad' have been skipped?
tot = len(candidates)
unskipped = [c for c in candidates if (c not in skip) and (c != badrev)]
if tot == 1 or not unskipped:
return ([changelog.node(rev) for rev in candidates], 0, good)
perfect = tot // 2
# find the best node to test
best_rev = None
best_len = -1
poison = set()
for rev in candidates:
if rev in poison:
# poison children
poison.update(children.get(rev, []))
continue
a = ancestors[rev] or [rev]
ancestors[rev] = None
x = len(a) # number of ancestors
y = tot - x # number of non-ancestors
value = min(x, y) # how good is this test?
if value > best_len and rev not in skip:
best_len = value
best_rev = rev
if value == perfect: # found a perfect candidate? quit early
break
if y < perfect and rev not in skip: # all downhill from here?
# poison children
poison.update(children.get(rev, []))
continue
for c in children.get(rev, []):
if ancestors[c]:
ancestors[c] = list(set(ancestors[c] + a))
else:
ancestors[c] = a + [c]
assert best_rev is not None
best_node = changelog.node(best_rev)
return ([best_node], tot, good)