diff options
author | Richard Purdie <rpurdie@linux.intel.com> | 2010-08-31 14:49:43 +0100 |
---|---|---|
committer | Chris Larson <chris_larson@mentor.com> | 2010-12-29 23:51:07 -0700 |
commit | 10c771f2f961c61628b283e9962e8aa6df73eab1 (patch) | |
tree | 728856d2da564421c34696c6606b22d2824c52cb /lib/bb/siggen.py | |
parent | edbdf6fc89d915f06b62c5a06726e0e46a940d2e (diff) | |
download | openembedded-core-contrib-10c771f2f961c61628b283e9962e8aa6df73eab1.tar.gz |
Implement task signatures
Includes functionality to find out what changes between two different
signature data dumps.
Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
Signed-off-by: Chris Larson <chris_larson@mentor.com>
Diffstat (limited to 'lib/bb/siggen.py')
-rw-r--r-- | lib/bb/siggen.py | 256 |
1 files changed, 256 insertions, 0 deletions
diff --git a/lib/bb/siggen.py b/lib/bb/siggen.py new file mode 100644 index 0000000000..da8503924f --- /dev/null +++ b/lib/bb/siggen.py @@ -0,0 +1,256 @@ +import hashlib +import logging +import re + +logger = logging.getLogger('BitBake.SigGen') + +try: + import cPickle as pickle +except ImportError: + import pickle + logger.info('Importing cPickle failed. Falling back to a very slow implementation.') + +def init(d): + siggens = [obj for obj in globals().itervalues() + if type(obj) is type and issubclass(obj, SignatureGenerator)] + + desired = bb.data.getVar("BB_SIGNATURE_HANDLER", d, True) or "noop" + for sg in siggens: + if desired == sg.name: + return sg(d) + break + else: + logger.error("Invalid signature generator '%s', using default 'noop'\n" + "Available generators: %s", + ', '.join(obj.name for obj in siggens)) + return SignatureGenerator(d) + +class SignatureGenerator(object): + """ + """ + name = "noop" + + def __init__(self, data): + return + + def finalise(self, fn, d, varient): + return + + def get_taskhash(self, fn, task, deps, dataCache): + return 0 + + def stampfile(self, stampbase, taskname, taskhash): + return "%s.%s" % (stampbase, taskname) + +class SignatureGeneratorBasic(SignatureGenerator): + """ + """ + name = "basic" + + def __init__(self, data): + self.basehash = {} + self.taskhash = {} + self.taskdeps = {} + self.runtaskdeps = {} + self.gendeps = {} + self.lookupcache = {} + self.basewhitelist = (data.getVar("BB_HASHBASE_WHITELIST", True) or "").split() + self.taskwhitelist = data.getVar("BB_HASHTASK_WHITELIST", True) or None + + if self.taskwhitelist: + self.twl = re.compile(self.taskwhitelist) + else: + self.twl = None + + def _build_data(self, fn, d): + + taskdeps, gendeps = bb.data.generate_dependencies(d) + + basehash = {} + lookupcache = {} + + for task in taskdeps: + data = d.getVar(task, False) + lookupcache[task] = data + for dep in sorted(taskdeps[task]): + if dep in self.basewhitelist: + continue + if dep in lookupcache: + var = lookupcache[dep] + else: + var = d.getVar(dep, False) + lookupcache[dep] = var + if var: + data = data + var + if data is None: + bb.error("Task %s from %s seems to be empty?!" % (task, fn)) + self.basehash[fn + "." + task] = hashlib.md5(data).hexdigest() + + self.taskdeps[fn] = taskdeps + self.gendeps[fn] = gendeps + self.lookupcache[fn] = lookupcache + + return taskdeps + + def finalise(self, fn, d, variant): + + if variant: + fn = "virtual:" + variant + ":" + fn + + taskdeps = self._build_data(fn, d) + + #Slow but can be useful for debugging mismatched basehashes + #for task in self.taskdeps[fn]: + # self.dump_sigtask(fn, task, d.getVar("STAMP", True), False) + + for task in taskdeps: + d.setVar("BB_BASEHASH_task-%s" % task, self.basehash[fn + "." + task]) + + def get_taskhash(self, fn, task, deps, dataCache): + k = fn + "." + task + data = dataCache.basetaskhash[k] + self.runtaskdeps[k] = [] + for dep in sorted(deps): + # We only manipulate the dependencies for packages not in the whitelist + if self.twl and not self.twl.search(dataCache.pkg_fn[fn]): + # then process the actual dependencies + dep_fn = re.search("(?P<fn>.*)\..*", dep).group('fn') + if self.twl.search(dataCache.pkg_fn[dep_fn]): + continue + if dep not in self.taskhash: + bb.fatal("%s is not in taskhash, caller isn't calling in dependency order?", dep) + data = data + self.taskhash[dep] + self.runtaskdeps[k].append(dep) + h = hashlib.md5(data).hexdigest() + self.taskhash[k] = h + #d.setVar("BB_TASKHASH_task-%s" % task, taskhash[task]) + return h + + def dump_sigtask(self, fn, task, stampbase, runtime): + k = fn + "." + task + if runtime == "customfile": + sigfile = stampbase + elif runtime: + sigfile = stampbase + "." + task + ".sigdata" + "." + self.taskhash[k] + else: + sigfile = stampbase + "." + task + ".sigbasedata" + "." + self.basehash[k] + + bb.utils.mkdirhier(os.path.dirname(sigfile)) + + data = {} + data['basewhitelist'] = self.basewhitelist + data['taskwhitelist'] = self.taskwhitelist + data['taskdeps'] = self.taskdeps[fn][task] + data['basehash'] = self.basehash[k] + data['gendeps'] = {} + data['varvals'] = {} + data['varvals'][task] = self.lookupcache[fn][task] + for dep in self.taskdeps[fn][task]: + if dep in self.basewhitelist: + continue + data['gendeps'][dep] = self.gendeps[fn][dep] + data['varvals'][dep] = self.lookupcache[fn][dep] + + if runtime and runtime != "customfile": + data['runtaskdeps'] = self.runtaskdeps[k] + data['runtaskhashes'] = {} + for dep in data['runtaskdeps']: + data['runtaskhashes'][dep] = self.taskhash[dep] + + p = pickle.Pickler(file(sigfile, "wb"), -1) + p.dump(data) + + def dump_sigs(self, dataCache): + for fn in self.taskdeps: + for task in self.taskdeps[fn]: + k = fn + "." + task + if k not in self.taskhash: + continue + if dataCache.basetaskhash[k] != self.basehash[k]: + bb.error("Bitbake's cached basehash does not match the one we just generated (%s)!" % k) + bb.error("The mismatched hashes were %s and %s" % (dataCache.basetaskhash[k], self.basehash[k])) + self.dump_sigtask(fn, task, dataCache.stamp[fn], True) + +def dump_this_task(outfile, d): + fn = d.getVar("BB_FILENAME", True) + task = "do_" + d.getVar("BB_CURRENTTASK", True) + bb.parse.siggen.dump_sigtask(fn, task, outfile, "customfile") + +def compare_sigfiles(a, b): + p1 = pickle.Unpickler(file(a, "rb")) + a_data = p1.load() + p2 = pickle.Unpickler(file(b, "rb")) + b_data = p2.load() + + def dict_diff(a, b): + sa = set(a.keys()) + sb = set(b.keys()) + common = sa & sb + changed = set() + for i in common: + if a[i] != b[i]: + changed.add(i) + added = sa - sb + removed = sb - sa + return changed, added, removed + + if 'basewhitelist' in a_data and a_data['basewhitelist'] != b_data['basewhitelist']: + print "basewhitelist changed from %s to %s" % (a_data['basewhitelist'], b_data['basewhitelist']) + + if 'taskwhitelist' in a_data and a_data['taskwhitelist'] != b_data['taskwhitelist']: + print "taskwhitelist changed from %s to %s" % (a_data['taskwhitelist'], b_data['taskwhitelist']) + + if a_data['taskdeps'] != b_data['taskdeps']: + print "Task dependencies changed from %s to %s" % (sorted(a_data['taskdeps']), sorted(b_data['taskdeps'])) + + if a_data['basehash'] != b_data['basehash']: + print "basehash changed from %s to %s" % (a_data['basehash'], b_data['basehash']) + + changed, added, removed = dict_diff(a_data['gendeps'], b_data['gendeps']) + if changed: + for dep in changed: + print "List of dependencies for variable %s changed from %s to %s" % (dep, a_data['gendeps'][dep], b_data['gendeps'][dep]) + if added: + for dep in added: + print "Dependency on variable %s was added" % (dep) + if removed: + for dep in removed: + print "Dependency on Variable %s was removed" % (dep) + + + changed, added, removed = dict_diff(a_data['varvals'], b_data['varvals']) + if changed: + for dep in changed: + print "Variable %s value changed from %s to %s" % (dep, a_data['varvals'][dep], b_data['varvals'][dep]) + if 'runtaskdeps' in a_data and 'runtaskdeps' in b_data and sorted(a_data['runtaskdeps']) != sorted(b_data['runtaskdeps']): + print "Tasks this task depends on changed from %s to %s" % (sorted(a_data['runtaskdeps']), sorted(b_data['runtaskdeps'])) + + if 'runtaskhashes' in a_data: + for dep in a_data['runtaskhashes']: + if a_data['runtaskhashes'][dep] != b_data['runtaskhashes'][dep]: + print "Hash for dependent task %s changed from %s to %s" % (dep, a_data['runtaskhashes'][dep], b_data['runtaskhashes'][dep]) + +def dump_sigfile(a): + p1 = pickle.Unpickler(file(a, "rb")) + a_data = p1.load() + + print "basewhitelist: %s" % (a_data['basewhitelist']) + + print "taskwhitelist: %s" % (a_data['taskwhitelist']) + + print "Task dependencies: %s" % (sorted(a_data['taskdeps'])) + + print "basehash: %s" % (a_data['basehash']) + + for dep in a_data['gendeps']: + print "List of dependencies for variable %s is %s" % (dep, a_data['gendeps'][dep]) + + for dep in a_data['varvals']: + print "Variable %s value is %s" % (dep, a_data['varvals'][dep]) + + if 'runtaskdeps' in a_data: + print "Tasks this task depends on: %s" % (a_data['runtaskdeps']) + + if 'runtaskhashes' in a_data: + for dep in a_data['runtaskhashes']: + print "Hash for dependent task %s is %s" % (dep, a_data['runtaskhashes'][dep]) |