jprdonnelly/impala
1
0
Fork 0
mirror of https://github.com/apache/impala.git synced 2025-12-19 18:12:08 -05:00
Code Issues Projects Releases Wiki Activity

IMPALA-6105: Clarify argument order in single_node_perf_run

Browse Source 
single_node_perf_run.py uses git_hash_A vs. git_hash_B, distinguish
them by their position in the command-line
arguments. single_node_perf_run.py calls report_benchmark_results.py,
which uses the "reference vs. input", distinguished by their
command-line flags. The output of report_benchmark_results.py uses
"{empty string} vs Base".

In the long run, I think it would be better to fix all three to use
the same terminology, but this comment hopefully adds clarity.

Change-Id: Ib236ce7e83dc193ef1382f6304444ce58759a639
Reviewed-on: http://gerrit.cloudera.org:8080/8470
Tested-by: Impala Public Jenkins
Reviewed-by: Jim Apple <jbapple-impala@apache.org>
This commit is contained in:
Jim Apple
2017-11-04 15:18:31 -07:00
parent fe90867d89
commit 216642e28d
1 changed files with 22 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
bin/single_node_perf_run.py
View File

@@ -22,7 +22,17 @@
#
# When one hash is given, measures the performance on the specified workloads.
# When two hashes are given, compares their performance. Output is in
# $IMPALA_HOME/perf_results/latest.
# $IMPALA_HOME/perf_results/latest. In the performance_result.txt file,
# git_hash_A is referred to as the "Base" result. For example, if you run with
# git_hash_A = aBad1dea... and git_hash_B = 8675309... the
# performance_result.txt will say at the top:
#
# Run Description: "aBad1dea... vs 8675309..."
#
# The different queries will have their run time statistics in columns
# "Avg(s)", "StdDev(%)", "BaseAvg(s)", "Base StdDev(%)". The first two refer
# to git_hash_B, the second two refer to git_hash_A. The column "Delta(Avg)"
# is negative if git_hash_B is faster and is positive if git_hash_A is faster.
#
# WARNING: This script will run git checkout. You should not touch the tree
# while the script is running. You should start the script from a clean git
@@ -266,7 +276,17 @@ def parse_options():
When one hash is given, measures the performance on the specified workloads.
When two hashes are given, compares their performance. Output is in
$IMPALA_HOME/perf_results/latest.
$IMPALA_HOME/perf_results/latest. In the performance_result.txt file,
git_hash_A is referred to as the "Base" result. For example, if you run with
git_hash_A = aBad1dea... and git_hash_B = 8675309... the
performance_result.txt will say at the top:
Run Description: "aBad1dea... vs 8675309..."
The different queries will have their run time statistics in columns
"Avg(s)", "StdDev(%)", "BaseAvg(s)", "Base StdDev(%)". The first two refer
to git_hash_B, the second two refer to git_hash_A. The column "Delta(Avg)"
is negative if git_hash_B is faster and is positive if git_hash_A is faster.
WARNING: This script will run git checkout. You should not touch the tree
while the script is running. You should start the script from a clean git