def repair_tsdb_data(caches, project, events):
counters, sets, frequencies = collect_tsdb_data(caches, project, events)
for timestamp, data in counters.items():
for model, keys in data.items():
for key, value in keys.items():
tsdb.incr(model, key, timestamp, value)
for timestamp, data in sets.items():
for model, keys in data.items():
for key, values in keys.items():
# TODO: This should use `record_multi` rather than `record`.
tsdb.record(model, key, values, timestamp)
for timestamp, data in frequencies.items():
tsdb.record_frequency_multi(data.items(), timestamp)
def repair_tsdb_data(caches, project, events):
counters, sets, frequencies = collect_tsdb_data(caches, project, events)
for timestamp, data in counters.items():
for model, keys in data.items():
for (key, environment_id), value in keys.items():
tsdb.incr(model, key, timestamp, value, environment_id=environment_id)
for timestamp, data in sets.items():
for model, keys in data.items():
for (key, environment_id), values in keys.items():
# TODO: This should use `record_multi` rather than `record`.
tsdb.record(model, key, values, timestamp, environment_id=environment_id)
for timestamp, data in frequencies.items():
tsdb.record_frequency_multi(data.items(), timestamp)
def save(self, project, raw=False):
from sentry.tasks.post_process import index_event_tags
project = Project.objects.get_from_cache(id=project)
data = self.data.copy()
# First we pull out our top-level (non-data attr) kwargs
event_id = data.pop('event_id')
level = data.pop('level')
culprit = data.pop('culprit', None)
logger_name = data.pop('logger', None)
server_name = data.pop('server_name', None)
site = data.pop('site', None)
checksum = data.pop('checksum', None)
fingerprint = data.pop('fingerprint', None)
platform = data.pop('platform', None)
release = data.pop('release', None)
environment = data.pop('environment', None)
# unused
time_spent = data.pop('time_spent', None)
message = data.pop('message', '')
if not culprit:
# if we generate an implicit culprit, lets not call it a
# transaction
transaction_name = None
culprit = generate_culprit(data, platform=platform)
else:
transaction_name = culprit
date = datetime.fromtimestamp(data.pop('timestamp'))
date = date.replace(tzinfo=timezone.utc)
kwargs = {
'platform': platform,
}
event = Event(
project_id=project.id,
event_id=event_id,
data=data,
time_spent=time_spent,
datetime=date,
**kwargs
)
# convert this to a dict to ensure we're only storing one value per key
# as most parts of Sentry dont currently play well with multiple values
tags = dict(data.get('tags') or [])
tags['level'] = LOG_LEVELS[level]
if logger_name:
tags['logger'] = logger_name
if server_name:
tags['server_name'] = server_name
if site:
tags['site'] = site
if environment:
tags['environment'] = environment
if transaction_name:
tags['transaction'] = transaction_name
if release:
# dont allow a conflicting 'release' tag
if 'release' in tags:
del tags['release']
tags['sentry:release'] = release
event_user = self._get_event_user(project, data)
if event_user:
# dont allow a conflicting 'user' tag
if 'user' in tags:
del tags['user']
tags['sentry:user'] = event_user.tag_value
for plugin in plugins.for_project(project, version=None):
added_tags = safe_execute(plugin.get_tags, event,
_with_transaction=False)
if added_tags:
# plugins should not override user provided tags
for key, value in added_tags:
tags.setdefault(key, value)
# tags are stored as a tuple
tags = tags.items()
# XXX(dcramer): we're relying on mutation of the data object to ensure
# this propagates into Event
data['tags'] = tags
data['fingerprint'] = fingerprint or ['{{ default }}']
for path, iface in six.iteritems(event.interfaces):
data['tags'].extend(iface.iter_tags())
# Get rid of ephemeral interface data
if iface.ephemeral:
data.pop(iface.get_path(), None)
# prioritize fingerprint over checksum as its likely the client defaulted
# a checksum whereas the fingerprint was explicit
if fingerprint:
hashes = [
md5_from_hash(h)
for h in get_hashes_from_fingerprint(event, fingerprint)
]
elif checksum:
hashes = [checksum]
data['checksum'] = checksum
else:
hashes = [
md5_from_hash(h)
for h in get_hashes_for_event(event)
]
# TODO(dcramer): temp workaround for complexity
data['message'] = message
event_type = eventtypes.get(data.get('type', 'default'))(data)
event_metadata = event_type.get_metadata()
# TODO(dcramer): temp workaround for complexity
del data['message']
data['type'] = event_type.key
data['metadata'] = event_metadata
# index components into ``Event.message``
# See GH-3248
if event_type.key != 'default':
if 'sentry.interfaces.Message' in data and \
data['sentry.interfaces.Message']['message'] != message:
message = u'{} {}'.format(
message,
data['sentry.interfaces.Message']['message'],
)
if not message:
message = ''
elif not isinstance(message, six.string_types):
message = force_text(message)
for value in six.itervalues(event_metadata):
value_u = force_text(value, errors='replace')
if value_u not in message:
message = u'{} {}'.format(message, value_u)
if culprit and culprit not in message:
culprit_u = force_text(culprit, errors='replace')
message = u'{} {}'.format(message, culprit_u)
message = trim(message.strip(), settings.SENTRY_MAX_MESSAGE_LENGTH)
event.message = message
kwargs['message'] = message
group_kwargs = kwargs.copy()
group_kwargs.update({
'culprit': culprit,
'logger': logger_name,
'level': level,
'last_seen': date,
'first_seen': date,
'active_at': date,
'data': {
'last_received': event.data.get('received') or float(event.datetime.strftime('%s')),
'type': event_type.key,
# we cache the events metadata on the group to ensure its
# accessible in the stream
'metadata': event_metadata,
},
})
if release:
release = Release.get_or_create(
project=project,
version=release,
date_added=date,
)
group_kwargs['first_release'] = release
group, is_new, is_regression, is_sample = self._save_aggregate(
event=event,
hashes=hashes,
release=release,
**group_kwargs
)
event.group = group
# store a reference to the group id to guarantee validation of isolation
event.data.bind_ref(event)
try:
with transaction.atomic(using=router.db_for_write(EventMapping)):
EventMapping.objects.create(
project=project, group=group, event_id=event_id)
except IntegrityError:
self.logger.info('duplicate.found', extra={'event_id': event.id}, exc_info=True)
return event
environment = Environment.get_or_create(
project=project,
name=environment,
)
if release:
ReleaseEnvironment.get_or_create(
project=project,
release=release,
environment=environment,
datetime=date,
)
grouprelease = GroupRelease.get_or_create(
group=group,
release=release,
environment=environment,
datetime=date,
)
counters = [
(tsdb.models.group, group.id),
(tsdb.models.project, project.id),
]
if release:
counters.append((tsdb.models.release, release.id))
tsdb.incr_multi(counters, timestamp=event.datetime)
frequencies = [
# (tsdb.models.frequent_projects_by_organization, {
# project.organization_id: {
# project.id: 1,
# },
# }),
# (tsdb.models.frequent_issues_by_project, {
# project.id: {
# group.id: 1,
# },
# })
(tsdb.models.frequent_environments_by_group, {
group.id: {
environment.id: 1,
},
})
]
if release:
frequencies.append(
(tsdb.models.frequent_releases_by_group, {
group.id: {
grouprelease.id: 1,
},
})
)
tsdb.record_frequency_multi(frequencies, timestamp=event.datetime)
UserReport.objects.filter(
project=project, event_id=event_id,
).update(group=group)
# save the event unless its been sampled
if not is_sample:
try:
with transaction.atomic(using=router.db_for_write(Event)):
event.save()
except IntegrityError:
self.logger.info('duplicate.found', extra={'event_id': event.id}, exc_info=True)
return event
index_event_tags.delay(
project_id=project.id,
group_id=group.id,
event_id=event.id,
tags=tags,
)
if event_user:
tsdb.record_multi((
(tsdb.models.users_affected_by_group, group.id, (event_user.tag_value,)),
(tsdb.models.users_affected_by_project, project.id, (event_user.tag_value,)),
), timestamp=event.datetime)
if is_new and release:
buffer.incr(Release, {'new_groups': 1}, {
'id': release.id,
})
safe_execute(Group.objects.add_tags, group, tags,
_with_transaction=False)
if not raw:
if not project.first_event:
project.update(first_event=date)
first_event_received.send(project=project, group=group, sender=Project)
post_process_group.delay(
group=group,
event=event,
is_new=is_new,
is_sample=is_sample,
is_regression=is_regression,
)
else:
self.logger.info('post_process.skip.raw_event', extra={'event_id': event.id})
# TODO: move this to the queue
if is_regression and not raw:
regression_signal.send_robust(sender=Group, instance=group)
return event
def _save_aggregate(self, event, hashes, release, **kwargs):
project = event.project
# attempt to find a matching hash
all_hashes = self._find_hashes(project, hashes)
try:
existing_group_id = (h[0] for h in all_hashes if h[0]).next()
except StopIteration:
existing_group_id = None
# XXX(dcramer): this has the opportunity to create duplicate groups
# it should be resolved by the hash merging function later but this
# should be better tested/reviewed
if existing_group_id is None:
kwargs['score'] = ScoreClause.calculate(1, kwargs['last_seen'])
group, group_is_new = Group.objects.create(project=project,
**kwargs), True
else:
group = Group.objects.get(id=existing_group_id)
group_is_new = False
# If all hashes are brand new we treat this event as new
is_new = False
new_hashes = [h[1] for h in all_hashes if h[0] is None]
if new_hashes:
affected = GroupHash.objects.filter(
project=project,
hash__in=new_hashes,
group__isnull=True,
).update(group=group, )
if affected != len(new_hashes):
self._ensure_hashes_merged(group, new_hashes)
elif group_is_new and len(new_hashes) == len(all_hashes):
is_new = True
# XXX(dcramer): it's important this gets called **before** the aggregate
# is processed as otherwise values like last_seen will get mutated
can_sample = should_sample(event.datetime, group.last_seen,
group.times_seen)
if not is_new:
is_regression = self._process_existing_aggregate(
group=group,
event=event,
data=kwargs,
release=release,
)
else:
is_regression = False
# Determine if we've sampled enough data to store this event
if is_new or is_regression:
is_sample = False
else:
is_sample = can_sample
tsdb.incr_multi([
(tsdb.models.group, group.id),
(tsdb.models.project, project.id),
],
timestamp=event.datetime)
tsdb.record_frequency_multi([
(tsdb.models.frequent_projects_by_organization, {
project.organization_id: {
project.id: 1,
},
}),
(tsdb.models.frequent_issues_by_project, {
project.id: {
group.id: 1,
},
}),
],
timestamp=event.datetime)
return group, is_new, is_regression, is_sample
def _save_aggregate(self, event, hashes, release, **kwargs):
project = event.project
# attempt to find a matching hash
all_hashes = self._find_hashes(project, hashes)
try:
existing_group_id = (h[0] for h in all_hashes if h[0]).next()
except StopIteration:
existing_group_id = None
# XXX(dcramer): this has the opportunity to create duplicate groups
# it should be resolved by the hash merging function later but this
# should be better tested/reviewed
if existing_group_id is None:
kwargs['score'] = ScoreClause.calculate(1, kwargs['last_seen'])
group, group_is_new = Group.objects.create(
project=project,
**kwargs
), True
else:
group = Group.objects.get(id=existing_group_id)
group_is_new = False
# If all hashes are brand new we treat this event as new
is_new = False
new_hashes = [h[1] for h in all_hashes if h[0] is None]
if new_hashes:
affected = GroupHash.objects.filter(
project=project,
hash__in=new_hashes,
group__isnull=True,
).update(
group=group,
)
if affected != len(new_hashes):
self._ensure_hashes_merged(group, new_hashes)
elif group_is_new and len(new_hashes) == len(all_hashes):
is_new = True
# XXX(dcramer): it's important this gets called **before** the aggregate
# is processed as otherwise values like last_seen will get mutated
can_sample = should_sample(
event.data.get('received') or float(event.datetime.strftime('%s')),
group.data.get('last_received') or float(group.last_seen.strftime('%s')),
group.times_seen,
)
if not is_new:
is_regression = self._process_existing_aggregate(
group=group,
event=event,
data=kwargs,
release=release,
)
else:
is_regression = False
# Determine if we've sampled enough data to store this event
if is_new or is_regression:
is_sample = False
else:
is_sample = can_sample
tsdb.incr_multi([
(tsdb.models.group, group.id),
(tsdb.models.project, project.id),
], timestamp=event.datetime)
tsdb.record_frequency_multi([
(tsdb.models.frequent_projects_by_organization, {
project.organization_id: {
project.id: 1,
},
}),
(tsdb.models.frequent_issues_by_project, {
project.id: {
group.id: 1,
},
}),
], timestamp=event.datetime)
return group, is_new, is_regression, is_sample
def save(self, project, raw=False):
from sentry.tasks.post_process import index_event_tags
project = Project.objects.get_from_cache(id=project)
data = self.data.copy()
# First we pull out our top-level (non-data attr) kwargs
event_id = data.pop("event_id")
level = data.pop("level")
culprit = data.pop("culprit", None)
logger_name = data.pop("logger", None)
server_name = data.pop("server_name", None)
site = data.pop("site", None)
checksum = data.pop("checksum", None)
fingerprint = data.pop("fingerprint", None)
platform = data.pop("platform", None)
release = data.pop("release", None)
environment = data.pop("environment", None)
# unused
time_spent = data.pop("time_spent", None)
message = data.pop("message", "")
if not culprit:
culprit = generate_culprit(data, platform=platform)
date = datetime.fromtimestamp(data.pop("timestamp"))
date = date.replace(tzinfo=timezone.utc)
kwargs = {"platform": platform}
event = Event(
project_id=project.id, event_id=event_id, data=data, time_spent=time_spent, datetime=date, **kwargs
)
tags = data.get("tags") or []
tags.append(("level", LOG_LEVELS[level]))
if logger_name:
tags.append(("logger", logger_name))
if server_name:
tags.append(("server_name", server_name))
if site:
tags.append(("site", site))
if release:
# TODO(dcramer): we should ensure we create Release objects
tags.append(("sentry:release", release))
if environment:
tags.append(("environment", environment))
for plugin in plugins.for_project(project, version=None):
added_tags = safe_execute(plugin.get_tags, event, _with_transaction=False)
if added_tags:
tags.extend(added_tags)
event_user = self._get_event_user(project, data)
if event_user:
tags.append(("sentry:user", event_user.tag_value))
# XXX(dcramer): we're relying on mutation of the data object to ensure
# this propagates into Event
data["tags"] = tags
data["fingerprint"] = fingerprint or ["{{ default }}"]
for path, iface in event.interfaces.iteritems():
data["tags"].extend(iface.iter_tags())
# Get rid of ephemeral interface data
if iface.ephemeral:
data.pop(iface.get_path(), None)
# prioritize fingerprint over checksum as its likely the client defaulted
# a checksum whereas the fingerprint was explicit
if fingerprint:
hashes = map(md5_from_hash, get_hashes_from_fingerprint(event, fingerprint))
elif checksum:
hashes = [checksum]
else:
hashes = map(md5_from_hash, get_hashes_for_event(event))
# TODO(dcramer): temp workaround for complexity
data["message"] = message
event_type = eventtypes.get(data.get("type", "default"))(data)
event_metadata = event_type.get_metadata()
# TODO(dcramer): temp workaround for complexity
del data["message"]
data["type"] = event_type.key
data["metadata"] = event_metadata
# index components into ``Event.message``
# See GH-3248
if event_type.key != "default":
if "sentry.interfaces.Message" in data and data["sentry.interfaces.Message"]["message"] != message:
message = u"{} {}".format(message, data["sentry.interfaces.Message"]["message"])
if not message:
message = ""
elif not isinstance(message, basestring):
message = force_text(message)
for value in event_metadata.itervalues():
value_u = force_text(value, errors="replace")
if value_u not in message:
message = u"{} {}".format(message, value_u)
message = trim(message.strip(), settings.SENTRY_MAX_MESSAGE_LENGTH)
event.message = message
kwargs["message"] = message
group_kwargs = kwargs.copy()
group_kwargs.update(
{
"culprit": culprit,
"logger": logger_name,
"level": level,
"last_seen": date,
"first_seen": date,
"data": {
"last_received": event.data.get("received") or float(event.datetime.strftime("%s")),
"type": event_type.key,
# we cache the events metadata on the group to ensure its
# accessible in the stream
"metadata": event_metadata,
},
}
)
if release:
release = Release.get_or_create(project=project, version=release, date_added=date)
group_kwargs["first_release"] = release
group, is_new, is_regression, is_sample = self._save_aggregate(
event=event, hashes=hashes, release=release, **group_kwargs
)
event.group = group
# store a reference to the group id to guarantee validation of isolation
event.data.bind_ref(event)
try:
with transaction.atomic(using=router.db_for_write(EventMapping)):
EventMapping.objects.create(project=project, group=group, event_id=event_id)
except IntegrityError:
self.logger.info("Duplicate EventMapping found for event_id=%s", event_id, exc_info=True)
return event
if release:
grouprelease = GroupRelease.get_or_create(
group=group, release=release, environment=environment, datetime=date
)
tsdb.incr_multi([(tsdb.models.group, group.id), (tsdb.models.project, project.id)], timestamp=event.datetime)
frequencies = [
# (tsdb.models.frequent_projects_by_organization, {
# project.organization_id: {
# project.id: 1,
# },
# }),
# (tsdb.models.frequent_issues_by_project, {
# project.id: {
# group.id: 1,
# },
# })
]
if release:
frequencies.append((tsdb.models.frequent_releases_by_groups, {group.id: {grouprelease.id: 1}}))
tsdb.record_frequency_multi(frequencies, timestamp=event.datetime)
UserReport.objects.filter(project=project, event_id=event_id).update(group=group)
# save the event unless its been sampled
if not is_sample:
try:
with transaction.atomic(using=router.db_for_write(Event)):
event.save()
except IntegrityError:
self.logger.info("Duplicate Event found for event_id=%s", event_id, exc_info=True)
return event
index_event_tags.delay(project_id=project.id, group_id=group.id, event_id=event.id, tags=tags)
if event_user:
tsdb.record_multi(
(
(tsdb.models.users_affected_by_group, group.id, (event_user.tag_value,)),
(tsdb.models.users_affected_by_project, project.id, (event_user.tag_value,)),
),
timestamp=event.datetime,
)
if is_new and release:
buffer.incr(Release, {"new_groups": 1}, {"id": release.id})
safe_execute(Group.objects.add_tags, group, tags, _with_transaction=False)
if not raw:
if not project.first_event:
project.update(first_event=date)
first_event_received.send(project=project, group=group, sender=Project)
post_process_group.delay(
group=group, event=event, is_new=is_new, is_sample=is_sample, is_regression=is_regression
)
else:
self.logger.info("Raw event passed; skipping post process for event_id=%s", event_id)
# TODO: move this to the queue
if is_regression and not raw:
regression_signal.send_robust(sender=Group, instance=group)
return event
