mirror of
https://github.com/apache/impala.git
synced 2025-12-30 21:02:41 -05:00
565d15579c
At the moment, a query is the default unit of execution and parallelism in the Impala
performance suite. With this change, we now have the ability to treat a workload as the
unit of execution. A workload is defined as a unique combination of the dataset, scale
factor, a subset (or all) of the queries in the dataset, and a table format (file format,
compression codec and compression scheme).
It introduces two new command line options in bin/run-workload.py:
* --execution_scope
The default scope is 'query', and it maintains previous semantics. The
new scope is 'workload', which toggles the unit of execution to a workload.
* --shuffle_query_exec_order.
Shuffles the order in which queries are executed (only applicable when the
execution_scope if workload), defaults to False.
Change-Id: I790d75f0896210cda8eb999015b0be04246e4c45
Reviewed-on: http://gerrit.ent.cloudera.com:8080/503
Reviewed-by: Ishaan Joshi <ishaan@cloudera.com>
Tested-by: Ishaan Joshi <ishaan@cloudera.com>
58 lines
2.2 KiB
Python
Executable File
58 lines
2.2 KiB
Python
Executable File
#!/usr/bin/env python
|
|
# Copyright (c) 2012 Cloudera, Inc. All rights reserved.
|
|
#
|
|
# Licensed 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.
|
|
#
|
|
# Utility functions for calculating common mathematical measurements. Note that although
|
|
# some of these functions are available in external python packages (ex. numpy), these
|
|
# are simple enough that it is better to implement them ourselves to avoid extra
|
|
# dependencies.
|
|
|
|
import math
|
|
|
|
def calculate_avg(values):
|
|
return sum(values) / float(len(values))
|
|
|
|
def calculate_stddev(values):
|
|
"""Return the standard deviation of a numeric iterable."""
|
|
avg = calculate_avg(values)
|
|
return math.sqrt(calculate_avg([(val - avg)**2 for val in values]))
|
|
|
|
def calculate_median(values):
|
|
"""Return the median of a numeric iterable."""
|
|
if all([v is None for v in values]): return None
|
|
sorted_values = sorted(values)
|
|
length = len(sorted_values)
|
|
if length % 2 == 0:
|
|
return (sorted_values[length / 2] + sorted_values[length / 2 - 1]) / 2
|
|
else:
|
|
return sorted_values[length / 2]
|
|
|
|
def calculate_geomean(values):
|
|
""" Calculates the geometric mean of the given collection of numerics """
|
|
if len(values) > 0:
|
|
return (reduce(lambda x, y: float(x) * float(y), values)) ** (1.0 / len(values))
|
|
|
|
def calculate_tval(avg, stddev, iters, ref_avg, ref_stddev, ref_iters):
|
|
"""
|
|
Calculates the t-test t value for the given result and refrence.
|
|
|
|
Uses the Welch's t-test formula. For more information see:
|
|
http://en.wikipedia.org/wiki/Student%27s_t-distribution#Table_of_selected_values
|
|
http://en.wikipedia.org/wiki/Student's_t-test
|
|
"""
|
|
# SEM (standard error mean) = sqrt(var1/N1 + var2/N2)
|
|
# t = (X1 - X2) / SEM
|
|
sem = math.sqrt((math.pow(stddev, 2) / iters) + (math.pow(ref_stddev, 2) / ref_iters))
|
|
return (avg - ref_avg) / sem
|