opendev
/
puppet-log_processor
Code Issues Proposed changes

log-gearman-worker: remove obsolete GET debug filter, add local filter 

Now that logs have moved into swift, the os-loganalyze middleware that
stripped DEBUG level logs when the URL was given a ?level= parameter
no longer functions.

We move to filtering DEBUG statements directly.  Because services in
devstack now run as systemd services, their log files are actually
journalctl dumps.  Thus we add a new filter for systemd style
timestamps and messages (this is loosely based on the zuul log viewer
at [1]).

[1] 8c1f4e9d6b/web/src/actions/logfile.js

Change-Id: I54087c95c809612758139136d5b3e86b1a6372be
This commit is contained in:
Ian Wienand 2019-08-19 16:58:29 +10:00
parent 5b30a3a6c0
commit 3119c0cddd
1 changed files with 43 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

57
files/log-gearman-worker.py
View File

@ -135,7 +135,7 @@ class CRM114FilterFactory(object):
return CRM114Filter(self.script, path, fields['build_status'])
class SeverityFilter(object):
class OsloSeverityFilter(object):
DATEFMT = '\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}((\.|\,)\d{3,6})?'
SEVERITYFMT = '(DEBUG|INFO|WARNING|ERROR|TRACE|AUDIT|CRITICAL)'
OSLO_LOGMATCH = ('^(?P<date>%s)(?P<line>(?P<pid> \d+)? '
@ -157,11 +157,44 @@ class SeverityFilter(object):
pass
class SeverityFilterFactory(object):
name = "Severity"
class OsloSeverityFilterFactory(object):
name = "OsloSeverity"
def create(self, fields):
return SeverityFilter()
return OsloSeverityFilter()
class SystemdSeverityFilter(object):
'''
Match systemd DEBUG level logs
A line to match looks like:
Aug 15 18:58:49.910786 hostname devstack@keystone.service[31400]: DEBUG uwsgi ...
'''
SYSTEMDDATE = '\w+\s+\d+\s+\d{2}:\d{2}:\d{2}((\.|\,)\d{3,6})?'
DATEFMT = '\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}((\.|\,)\d{3,6})?'
SEVERITYFMT = '(DEBUG|INFO|WARNING|ERROR|TRACE|AUDIT|CRITICAL)'
SYSTEMD_LOGMATCH = '^(?P<date>%s)( (\S+) \S+\[\d+\]\: ' \
'(?P<severity>%s)?.*)' % (SYSTEMDDATE, SEVERITYFMT)
SYSTEMDRE = re.compile(SYSTEMD_LOGMATCH)
def process(self, msg):
m = self.SYSTEMDRE.match(msg)
if m:
if m.group('severity') == 'DEBUG':
return False
return True
def close(self):
pass
class SystemdSeverityFilterFactory(object):
name = "SystemdSeverity"
def create(self, fields):
return SystemdSeverityFilter()
class LogRetriever(threading.Thread):
@ -290,20 +323,15 @@ class LogRetriever(threading.Thread):
def _get_log_data(self, source_url, retry):
encoding = 'raw'
try:
# TODO(clarkb): We really should be using requests instead
# of urllib2. urllib2 will automatically perform a POST
# instead of a GET if we provide urlencoded data to urlopen
# but we need to do a GET. The parameters are currently
# hardcoded so this should be ok for now.
logging.debug("Retrieving: " + source_url + ".gz?level=INFO")
req = urllib2.Request(source_url + ".gz?level=INFO")
logging.debug("Retrieving: " + source_url + ".gz")
req = urllib2.Request(source_url + ".gz")
req.add_header('Accept-encoding', 'deflate, gzip')
r = urllib2.urlopen(req)
except urllib2.URLError:
try:
# Fallback on GETting unzipped data.
logging.debug("Retrieving: " + source_url + "?level=INFO")
r = urllib2.urlopen(source_url + "?level=INFO")
logging.debug("Retrieving: " + source_url)
r = urllib2.urlopen(source_url)
except:
logging.exception("Unable to retrieve source file.")
raise
@ -430,7 +458,8 @@ class Server(object):
self.filter_factories = []
# Run the severity filter first so it can filter out chatty
# logs.
self.filter_factories.append(SeverityFilterFactory())
self.filter_factories.append(OsloSeverityFilterFactory())
self.filter_factories.append(SystemdSeverityFilterFactory())
crmscript = self.config.get('crm114-script')
crmdata = self.config.get('crm114-data')
if crmscript and crmdata: