mirror of
https://github.com/apache/impala.git
synced 2025-12-19 18:12:08 -05:00
4028e9c5ec
The stress test never expected to see memory estimates on the order of PB. Apparently it can happen with TPC DS 10000, so update the pattern. It's not clear how to quickly write a test to catch this, because it involves crossing language boundaries and possibly having a massively-scaled dataset. I think leaving a comment in both places is good enough for now. Change-Id: I317c271888584ed2a817ee52ad70267eae64d341 Reviewed-on: http://gerrit.cloudera.org:8080/9846 Reviewed-by: Lars Volker <lv@cloudera.com> Tested-by: Impala Public Jenkins
73 lines
2.2 KiB
Python
73 lines
2.2 KiB
Python
# Licensed to the Apache Software Foundation (ASF) under one
|
|
# or more contributor license agreements. See the NOTICE file
|
|
# distributed with this work for additional information
|
|
# regarding copyright ownership. The ASF licenses this file
|
|
# to you under the Apache License, Version 2.0 (the
|
|
# "License"); you may not use this file except in compliance
|
|
# with the License. You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing,
|
|
# software distributed under the License is distributed on an
|
|
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
|
|
# KIND, either express or implied. See the License for the
|
|
# specific language governing permissions and limitations
|
|
# under the License.
|
|
|
|
import re
|
|
from datetime import datetime
|
|
|
|
NEW_GLOG_ENTRY_PATTERN = re.compile(r"[IWEF](?P<Time>\d{4} \d{2}:\d{2}:\d{2}\.\d{6}).*")
|
|
|
|
def parse_glog(text, start_time=None):
|
|
'''Parses the log 'text' and returns a list of log entries. If a 'start_time' is
|
|
provided only log entries that are after the time will be returned.
|
|
'''
|
|
year = datetime.now().year
|
|
found_start = False
|
|
log = list()
|
|
entry = None
|
|
for line in text.splitlines():
|
|
if not found_start:
|
|
found_start = line.startswith("Log line format: [IWEF]mmdd hh:mm:ss.uuuuuu")
|
|
continue
|
|
match = NEW_GLOG_ENTRY_PATTERN.match(line)
|
|
if match:
|
|
if entry:
|
|
log.append("\n".join(entry))
|
|
if not start_time or start_time <= datetime.strptime(
|
|
match.group("Time"), "%m%d %H:%M:%S.%f").replace(year):
|
|
entry = [line]
|
|
else:
|
|
entry = None
|
|
elif entry:
|
|
entry.append(line)
|
|
if entry:
|
|
log.append("\n".join(entry))
|
|
return log
|
|
|
|
|
|
def parse_mem_to_mb(mem, units):
|
|
mem = float(mem)
|
|
if mem <= 0:
|
|
return
|
|
units = units.strip().upper() if units else ""
|
|
if units.endswith("B"):
|
|
units = units[:-1]
|
|
if not units:
|
|
mem /= 2 ** 20
|
|
elif units == "K":
|
|
mem /= 2 ** 10
|
|
elif units == "M":
|
|
pass
|
|
elif units == "G":
|
|
mem *= 2 ** 10
|
|
elif units == "T":
|
|
mem *= 2 ** 20
|
|
elif units == "P":
|
|
mem *= 2 ** 30
|
|
else:
|
|
raise Exception('Unexpected memory unit "%s"' % units)
|
|
return int(mem)
|